# Research Papers — 2026-10 · bundle page 136 of 156

> Full-text markdown of papers #6751–6800 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-10/page/136
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/135.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/137.md)

### Robust Tensor Completion via Reflective Convolution Nuclear Norm Minimization

Authors: Weiguo Zhou, Feng Zhang, Wenjin Qin, Jianwen Huang
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.04979v1

Robust tensor completion recovers multidimensional data from partial observations corrupted by sparse gross errors. Existing convolutional low-rank models typically construct translated copies using circular continuation, which introduces artificial wrap-around neighborhoods for finite nonperiodic data. We propose reflective convolution nuclear norm minimization (RCNNM), which replaces circular shifts with endpoint-nonrepeating reflection. The resulting lifting has nonuniform entry multiplicities and satisfies a weighted Gram identity that supports both the recovery analysis and the optimization method. Under random sampling and sparse corruption, we establish high-probability exact recovery of the underlying tensor and sparse errors, together with stability under bounded dense perturbations. We further develop a two-block ADMM with a closed-form entrywise tensor update, while singular-value thresholding is implemented through the smaller right Gram matrix. Experiments on synthetic tensors, BSDS color images, and CAVE multispectral images show that RCNNM consistently improves over its circular-lifting counterpart, with the clearest gains near image boundaries. In particular, average boundary-PSNR improvements reach 3.26 dB while global reconstruction quality remains competitive.

---

### What Will Post-Training Fix? Per-Problem Gains Are Shared Across Independent RL Runs, and Existing Checkpoints Predict Them Better Than A Priori Signals

Authors: Xiaoxian Duan
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.04978v1

Data selection, curricula and the evaluation of post-training recipes all assume that we can tell, before training, which problems a model will improve on. We test this assumption directly. For two base models, DeepSeek-R1-Distill-Qwen-1.5B and Qwen2.5-Math-1.5B, we evaluate eighteen post-training runs on up to 1532 competition math problems with many samples per problem, and compare signals available before training against a noise ceiling derived from the agreement between disjoint subsets of runs. Three findings hold on both base models. What post-training fixes is shared: independent runs agree on which rarely solved problems improve, with a noise ceiling of about 0.9, yet the two base models agree with each other only at rho=0.25 - the shared component belongs to the base model, not to the problem. A priori signals capture a minority of it: base pass rate, the likelihood of a correct solution, a larger model's pass rate and their combinations explain only 0.30 and 0.24 of the explainable variance in gains. Existing checkpoints are the better predictor: the per-problem gains of a single checkpoint from another family predict a new run better than every a priori signal, alone or combined (0.52 vs. 0.33 and 0.34 vs. 0.17 against the combined signals). The conclusions hold on problems from 2025-2026 competitions and when the baselines on the two sides of every comparison are estimated independently. We propose the noise ceiling as a standard companion to per-problem signals.

---

### Do LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation

Authors: Jerry Wang, Zhengxiang Wang, Ting Yu Liu, Hsin-Ling Hsu, Yi-Cheng Lai, Tengfei Ma
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.04977v1

Large language models (LLMs) are increasingly used as interactive agents and simulators, yet it remains unclear whether they can recover latent sequential structure beyond surface action frequencies. This distinction is critical for behavioral simulation, where actions are often shaped by prior context rather than marginal frequencies alone. We study this question using controlled two-player Rock--Paper--Scissors interactions and a one-player stochastic n-gram continuation task. Across these experiments, we test whether LLMs can identify latent strategies, follow simple Markov rules, and sustain higher-order conditional dependencies. Our framework separates distribution matching from conditional rule following. Results show that longer context does not improve identification, correct recognition does not ensure faithful simulation, and higher-order dependencies substantially degrade rule recovery. Apparent behavioral fidelity can therefore mask incorrect generative mechanisms.

---

### Priced Guidance: Can Language Models Generate Future Research Ideas?

Authors: Kaiyue Wen, Tengyu Ma, Percy Liang
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.04976v1

We evaluate language models' capability to generate novel research ideas through the lens of compression. We aim to lower-bound the potentially tiny probability that a language model generates the essence of a future research idea without any hints. Rather than estimate this probability through expensive repeated sampling, our Priced Guidance framework measures the compression cost: how many additional bits of information are needed to guide the model to recover the target idea. We prove that if the model can recover the target idea with at most K bits of guidance in expectation, then it can generate the idea without any guidance with probability at least $2^{-K}$. In our framework, the language model, called the generator, can pose a sequence of multiple-choice questions and specify a probability distribution over possible answers. A guide, which is a language model with access to the target idea, selects answers. If a selected answer has prior probability p, the generator pays $-\log_2 p$ bits. The generator aims to produce an idea that matches the essence of the target idea with minimal cumulative cost. This cumulative cost equals, up to an additive constant, the number of bits of information sent by the guide. Using this methodology, we evaluate five generator LLMs (Opus 5, Fable 5.1, GPT-6 Astra, GPT-5.6 Sol, and GLM 5.3) on the core ideas in 87 recent high-quality deep learning papers and we use LLM as judge to determine whether the generated idea matches the target in terms of the central research object and defining mechanism. Fable 5.1 achieves the lowest median compression cost at 69.9 bits, substantially lower than gzip's median of 5,712 bits for losslessly compressing the summary of the target idea. A uniform ensemble of Fable 5.1, Opus 5, and Astra further reduces the median compression cost to 55.8 bits and improves the generation probability lower bound by 18,000 times.

---

### Runtime Authorization of Self-Generated Subgoals in Long-Horizon Tool-Using AI Agents

Authors: Genliang Zhu, Chu Wang
Published: 2026-10-04
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2610.04975v1

Long-horizon tool-using AI agents create subgoals, replan, delegate work, and compose sibling results. Per-tool permission checks cannot establish that a changing goal graph remains within the principal-approved task. We address this authorization gap in a finite structured domain with one principal and one authorization root. Each proposed goal-graph mutation carries a version-bound witness that its continuation traces, resources, obligations, invariants, and closing condition refine the active root contract; every protected effect is rechecked at an atomic commit boundary. Free-form goal text supplies no authority. We prove trace-policy and modeled forbidden-state preservation under explicit mediation, abstraction, freshness, and atomicity assumptions, plus conditional root-success preservation, a separation result for memoryless allowlists, exact finite-domain decidability, and universal-safety monotonicity under sound abstraction refinement. An executable model explores 340 states and 419 transitions. Across 96 matched cases covering 25 structural schemas, the complete mechanism commits zero forbidden states in 48 drifted cases and completes all 48 benign counterparts. Two public upstream runtime paths execute 258 native dispatches across 32 cases, with every case-level decision and receipt chain matching. A frozen host-local study covers 129 synthetic one-factor-at-a-time cells, all matching fixed decisions and reasons. A history-aware continuation comparator blocks every modeled bad trace prefix but commits all operations in 11 cases whose violations lie in typed resources, freshness, or explicit-join evidence outside its trace projection. Within the registered structured domains, runtime authorization preserves useful replanning while preventing self-generated subgoals from becoming a source of new authority.

---

### IREA: Intermediate Representation-based Embedding Alignment for Normative RAG

Authors: Mirae Han, Sihyeong Yeom, Harksoo Kim
Published: 2026-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.04974v1

Large language models (LLMs) have shown strong performance across various tasks, but they still struggle with questions involving ethical judgment. Previous studies have attempted to train LLMs on ethical standards, but the diversity and relativity of ethical norms make them difficult to fully internalize in model parameters. As an alternative, we introduce normative RAG, a retrieval-augmented approach that supports ethical judgment using external normative knowledge. Normative retrieval involves a distinct asymmetry between context rich narrative queries and generalized normative statements. Existing factual retrieval methods rely on query-only expansion into a document-like form, making them insufficient for resolving this asymmetry. Therefore, we propose Intermediate Representation-based Embedding Alignment (IREA), a bidirectional alignment method that maps both text types into a shared situation-behavior representation. This representation captures ethically salient contextual and behavioral information in a normalized form, reducing surface-level discrepancies and improving alignment in the embedding space. Experimental results show that IREA improves normative retrieval and downstream ethical judgment across multiple settings, demonstrating the effectiveness of bidirectional alignment for normative RAG.

---

### TrajLong: Co-Designing Agentic and Long-Context Supervision for Mid-Training

Authors: Miao Peng, Qintong Zhang, Nuo Chen, Yuhan Li, Guochen Yan, Xinran Gu, Hongqiu Wu, Hai Wang, Lydell Huang, Wentao Zhang, Jia Li
Published: 2026-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.04973v1

LLM agents for coding, search, and workplace tasks increasingly rely on long-context capabilities to effectively aggregate and reason over extended interaction histories. Recent work has incorporated agent trajectories into mid-training stage, drawing on their naturally long and interaction-rich structure. Yet how to organize the information within these trajectories into effective mid-training supervision remains underexplored. In this work, we investigate the relationship between long-context and agent atomic capabilities and introduce TrajLong, a novel framework that compiles trajectories into long-context training tasks with dense supervision, targeting three representative atomic capabilities: evidence grounding, cross-evidence aggregation, and temporal state maintenance. We mid-train Qwen3-14B-Base and Qwen3-30B-A3B-Base with data compiled by TrajLong, followed by supervised fine-tuning. Experiments on 6 long-context and 12 agent benchmarks demonstrate broad performance gains, with controlled ablations showing improvements over raw and masked trajectory baselines. Capability-level analyses further reveal task-dependent associations between long-context and agent atomic capabilities. These findings suggest that the shared capability demands of long-context reasoning and agent execution provide a principled basis for designing mid-training data to develop downstream agent capabilities.

---

### Hamiltonian Metric Learning and Energy-Based Training: A Dissipative Geometric Framework for Optimization

Authors: Sparsho Chakraborty, Mohammad Alamgir, Nishanth M, Akshit Nanda, Ram Prasad Padhy, Sayan Mukherjee
Published: 2026-10-04
Categories: cs.LG, math.OC, quant-ph
arXiv: https://arxiv.org/abs/2610.04969v1

Optimization in machine learning is usually expressed through iterative rules that update model parameters using information from the loss landscape. In this work, we study an alternative viewpoint in which parameter optimization is treated as the evolution of a dissipative dynamical system. The model parameters are regarded as generalized coordinates, the loss acts as a potential energy, and a positive-definite metric defines the local kinetic geometry of parameter space. Starting from a variational formulation, we derive the corresponding Hamiltonian dynamics, the geometric force generated by a position-dependent metric, and a metric-compatible Rayleigh dissipation law. The resulting continuous system satisfies a monotonic energy-dissipation relation, while its discrete form allows the influence of curvature on the optimization trajectory to be studied directly. We illustrate the framework using a controlled CIFAR-10 image-reconstruction problem for which the optimum is known analytically. With the image Hessian used as the metric, the curvature dependence of the quadratic modal dynamics is removed. We then reparameterize the same image as a matrix product state, producing a genuinely position-dependent metric and a nonzero geometric force. Poincaré return maps provide a complementary phase-space view of the resulting contraction dynamics. These examples establish HAMLET as a geometric, energy-based framework for studying optimization as dissipative motion in parameter space. On a five-seed MNIST MLP benchmark, HAMLET attains the highest mean test accuracy (97.95\%) and the lowest mean test negative log-likelihood (0.0696) among the three evaluated optimizers.

---

### One Token Can Be Enough: Bridging Prompting and Activation Steering with Prefix Steering

Authors: Xudong Zhu, Zhihui Zhu
Published: 2026-10-04
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2610.04967v1

Prompting guides language model behavior through the initial context, whereas activation steering often intervenes throughout generation. A natural question is whether steering can produce effects on subsequent computation similar to those of prompting. Under fixed-state attention assumptions, we establish sufficient conditions for single- and multi-token steering to match prompt-induced attention-head outputs, and characterize how changes in input representations affect this match and its approximation error. This attention-level connection leads us to ask whether, at the behavioral level, steering can also guide subsequent generation through a brief initial intervention. We study Prefix Steering, which applies existing steering directions and operators over a short span starting at the final prompt token, with no further direct intervention afterward. We examine how intervention duration and strength jointly shape the control-capability trade-off. Across four models and five tasks, intervention over a short span, even a single token, often retains much of full steering's behavioral control while better preserving general capabilities, offering a trade-off competitive with, and in some settings better than, prompting and alternative steering-strength policies. Prefix Steering also remains effective on final-answer formatting tasks after reasoning, suggesting that a brief initial intervention can influence behavior expressed well after steering ends. These findings challenge the common practice of steering every generated token and motivate a more dynamical view of activation steering, in which a brief intervention can alter the trajectory of subsequent generation without continued intervention.

---

### BACAM: Behavior-Aware Continual Agent Merging for Multi-Turn Interaction

Authors: Shuaitong Li, Baochen Xiong, Xiaoshan Yang, Xizhe Zheng, Yifan Xu, Jianhao Huang, Changsheng Xu
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.04966v1

Model merging offers a way to integrate the capabilities of specialized experts, but existing agent merging methods typically require all of them to be available at once. We study continual agent merging, which integrates incoming experts sequentially without retaining previously merged experts. Yet merging in parameter space or feature subspaces does not ensure that the merged model acquires an incoming expert's behavior on interaction trajectories. Moreover, updates toward a new expert can disrupt the merged model's previously integrated interactive behavior. Therefore, we propose Behavior-Aware Continual Agent Merging (BACAM), which learns parameter-wise merging gates from candidate-generated trajectories using expert-guided behavioral supervision. Task-level stability-plasticity control and tensor-level conflict-aware update budgets limit interference with existing capabilities while allowing new ones to be acquired. The learned gates are folded into the model weights without additional inference-time parameters. Across four interactive tasks - web shopping, tool use, information retrieval, and embodied interaction - BACAM achieves an average success rate of 62.82%, exceeding the strongest evaluated merging baseline by 21.69 percentage points. Our code is publicly available at https://github.com/shuaitongli/BACAM.

---

### MAGIC: Topology-Aware Analytic Graph Few-Shot Class-Incremental Learning

Authors: Junlin Chen, Yuhan Wang, Xuefei Wang, Xiao Wang, Ruijie Wang, Jianxin Li
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.04963v1

Graph few-shot class-incremental learning (GFSCIL) requires a model to continually recognize emerging classes from only a few labeled nodes while preserving previously acquired knowledge. Beyond the catastrophic forgetting inherited from conventional graph continual learning, GFSCIL presents two distinctive challenges: extremely limited novel-class supervision causes severe overfitting, while cross-session edges---edges connecting newly arriving nodes with historical nodes---alter historical propagation neighborhoods and thereby induce representation drift. We propose MAGIC, a replay-free GFSCIL framework that combines a frozen graph representation backbone (e.g., an intrinsically parameter-free backbone such as SGC or a pretrained graph foundation model) with closed-form analytic continual learning. To alleviate novel-session overfitting, MAGIC learns a topological prior from the base graph that can characterize both homophilous and heterophilous relations, and injects this prior through Potts Markov random field inference to refine supervision for novel classes. To mitigate representation drift, MAGIC transfers previous predictions from the old representations of affected historical nodes to their updated representations through drift-aware analytic distillation. Experiments across five datasets and eight baselines demonstrate the effectiveness of MAGIC. Under the 5-shot setting, MAGIC improves Mean Accuracy and Final Accuracy by 5.48 percentage points and 9.33 percentage points on average, and reduces Performance Drop by 10.78 percentage points on average compared with the best baselines. MAGIC also shows clear advantages under the 1- and 3-shot settings, with larger gains as the number of supports increases. Moreover, MAGIC requires substantially less training time.

---

### Building LLM Agent Systems the Deep Learning Way: From Modular Design to Architecture Search

Authors: Tao Feng, Pengrui Han, Zhongjie Dai, Jiaxuan You
Published: 2026-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.04961v1

Large Language Models (LLMs) have revolutionized AI research and enabled exciting agent systems. To build a complex LLM agent system, most existing research relies on insights from other domains or heuristics to manually build the agent system. However, this approach often requires heavy hand-engineering and fails to fully optimize for the downstream task of interest. Inspired by the tremendous success of deep learning, we propose to construct LLM agent systems in a modular manner, similar to building a deep neural network. Our key insight is to make analogies between LLM building blocks, such as retrievals, memories, and prompting strategies, and the successful deep learning modules, such as MLPs, attention, and recurrent modules. We further design forward inference and feedback mechanisms for LLMs, where prompts in LLMs are considered as the weights in deep models, and the prompt optimization from feedback is analogous to the back-propagation algorithm. We additionally leverage a search algorithm to search for the best configuration of LLM agent systems, similar to the neural architecture search (NAS) in deep learning research. Comprehensive experimental results demonstrate that the proposed deep learning recipe for LLM agent systems is highly effective, in particular: (1) Organizing LLM modules into deep-learning-style architectures yields noticeable performance gain; (2) Automatic prompt optimization, equivalent to backpropagation, is efficient in incorporating feedback from the task of interest and achieves at least 5% performance improvement; (3) NAS equivalent algorithm works well for further optimizing the LLM agent system architecture with 11% performance gain compared with randomly designed architectures. Overall, our research demonstrates the exciting opportunity of transferring the success of deep learning to building LLM agent systems.

---

### Trinity: One Differentiable Physics for Training, Refining and Scoring Generative Floorplanners

Authors: Shih-Ying Yeh, Tzu-Sian Wang, Xuehai Wang, Jia-Hua Lee, Daniel Z. Kaplan, Ming-Qi Xu, Wuqian Tang, Chun-Yao Wang, Shang-Hong Lai, Chun-Yi Lee
Published: 2026-10-04
Categories: cs.LG, cs.AR
arXiv: https://arxiv.org/abs/2610.04957v1

Floorplanning arranges the blocks of a chip and decides their shapes under objectives that press blocks together, short wirelength and a small outline, and constraints that hold them apart, non-overlap, clusters, MIB shapes and boundary blocks. Recent diffusion placers train on reference layouts alone and leave this coupled system to guidance, post-hoc loops and a legalizer, reporting only the endpoint, which hides what the generator contributes. We re-implement four of them under one recipe on FloorSet, score raw, refined and legalized layouts on one scale, and propose Trinity, a flow-matching floorplanner whose six differentiable functions for the constraints and objectives are its training loss term, the energy of a closed-form refiner after sampling and the base of a soft cost for every stage. The network thus learns the correction prior placers apply in their samplers, and sampling needs no guidance. Stage by stage, the training term lowers a plain transformer's raw soft cost by 26% and matters most at short budgets, the shared refiner decides more of the final cost than the generator and matches a ported placer's loop in 16 to 660 times fewer steps, Trinity's refined soft cost is 36% below the best ported pipeline, the soft cost ranks settings as the contest's hard cost does, and on the FloorSet val set the pipeline reaches a mean hard cost of 1.014 in 1.63 s per case.

---

### From Overloaded to Guaranteed: High-Throughput Multi-SLO Enforcement for LoRA-Assisted On-Premise LLM Deployment

Authors: Zeshen Zhang, Han Zhao, Weihao Cui, Quan Chen, Yu Liu, Yongjun Deng, Jing Yang, Jiuchen Shi, Chen Chen, Youmin Chen, Yu Feng, Minyi Guo
Published: 2026-10-04
Categories: cs.CL, cs.DC
arXiv: https://arxiv.org/abs/2610.04956v1

As Large Language Models (LLMs) become essential in privacy-sensitive sectors like hospitals and government agencies, the on-premise LLM servers offer a cost-effective and secure alternative to public cloud services. However, these resource-constrained servers struggle to guarantee heterogeneous Service Level Objectives (SLOs) when serving multiple LoRA-adapted services simultaneously. Existing serving frameworks suffer from severe SLO violations due to the computational overhead of LoRA layers and the rigid nature of batch scheduling. To address this, we propose HALO, a scheduling method tailored for LoRA-assisted on-premise LLM deployment. HALO introduces two key innovations: a spatial multiplexing strategy that overlaps Base and LoRA computations by partitioning GPU Streaming Multiprocessors (SMs), and an SLO-aware scheduler that decouples request execution based on "request-level slack." By prioritizing urgent tasks and utilizing idle budget for traffic shaping, HALO significantly mitigates resource contention. Our evaluation demonstrates that HALO minimizes SLO violations while improving throughput compared to state-of-the-art baselines.

---

### Kapture: Capturing Cardiac Dynamics with Koopman-Governed Learning for Efficient Radar-Based Electrocardiogram Recovery

Authors: Tong Wu, Jing Peng, Ziqi Feng, Yuanyuan Zhang
Published: 2026-10-04
Categories: eess.SP, cs.AI
arXiv: https://arxiv.org/abs/2610.04955v1

Millimeter-wave (mmWave) radar enables unobtrusive, contactless electrocardiogram (ECG) reconstruction for cardiac monitoring. Time-frequency spectrograms preserve fine cardiac patterns but often require large backbones to separate ECG-relevant features from respiration, motion, multipath, and subject-dependent interference. We propose Kapture, a parameter-efficient Koopman-governed framework that projects radar hidden states into a low-dimensional observable space and identifies a regularized full linear evolution operator from adjacent observable states. The Koopman-predicted observables refine subsequent hidden states for ECG reconstruction. To suppress predictable interference dynamics, a temporal contrastive objective pulls neighboring states together and separates non-neighbors, while reconstruction supervision preserves task relevance. Using approximately 80 minutes of quasi-static radar-ECG recordings containing realistic noise from body movements and other sources, Kapture consistently improves reconstruction across matched backbone widths, with the largest gains under aggressive compression. The compact configuration approaches the full-width reference accuracy with 68.1% fewer parameters and 91.3% fewer profiler-covered floating-point operations (FLOPs), while the full-width configuration delivers the strongest overall reconstruction performance. Our code will be made publicly available after potential publication.

---

### EDISCO: Equivariant DIScrete Diffusion for Euclidean Combinatorial Optimization

Authors: Ruogu Chen, Jie Han
Published: 2026-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.04953v1

Euclidean combinatorial optimization problems (ECOPs), such as the Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP), possess inherent symmetries under the two-dimensional Euclidean group E(2), including rotations, reflections, and translations. Existing learning-based methods, including recent diffusion-based methods, rely on data augmentation or regularization to approximate E(2)-equivariance. This paper presents EDISCO, the first discrete diffusion model for ECOPs with exact E(2)-invariant generative distributions over node-index solutions. EDISCO introduces an E(2)-equivariant edge-score network coupled with a categorical continuous-time Markov chain over discrete edge variables, and exact posterior sampling provides efficient multi-step inference. This design gives EDISCO a local geometric inductive bias: edge neighborhoods with the same relative geometry and combinatorial context are represented consistently regardless of absolute position or orientation, making learning more efficient and inference more robust than non-equivariant methods. EDISCO outperforms previous learning-based state-of-the-art solvers on synthetic TSP from 100 to 10000 nodes and CVRP from 50 to 2000 customers, while using only 33-50% of the training instances. Trained only on uniform synthetic data, EDISCO also outperforms competing learning-based baselines under spatial distribution shift and CVRP constraint-tightness shift. Code is available at https://github.com/ValleyC/EDISCO.

---

### How Should Teachers Be Prepared? RL on Student-Induced States for On-Policy Distillation

Authors: Xiaoyu Ma, Haoyue Liu, Zhichao Wang, Jionghao Zhu, Xiaoying Tang
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.04950v1

On-policy distillation (OPD) improves the reasoning capabilities of small language models through token-level teacher supervision on student-generated trajectories. Yet can teachers that excel at solving problems independently also guide student reasoning effectively? Prior work shows that when student prefixes follow reasoning paths that differ from the teacher's own or contain errors, teachers can be less accurate when continuing from these prefixes than when solving problems independently. To this end, we propose Prep-OPD, which uses reinforcement learning (RL) before distillation to train the teacher to adapt to the student's existing reasoning state and correct course when errors arise. Training optimizes teacher continuations from fixed student prefixes using final-answer correctness as the reward. The prepared teacher then trains the student through trajectory guidance and token-level supervision. We evaluate Prep-OPD on eight mathematical reasoning benchmarks, using Qwen3-4B-Instruct-2507 as the teacher and Qwen3-0.6B and Qwen3-1.7B as students. With the 4B teacher and 1.7B student, Prep-OPD improves average accuracy over standard OPD and the strongest baseline, Relay-OPD, by 8.28 and 2.30 percentage points, respectively. Controlled experiments further show that teacher RL conditioned on student-generated prefixes yields higher student accuracy than problem-start teacher RL with and without handoff on Qwen3-1.7B. Reusing the same prepared teacher also improves Qwen3-0.6B.

---

### A Unified Dynamics Framework for Reinforcement Learning and Classical Control of a Six-DOF Pipeline-Tracking ROV in NVIDIA Isaac Sim

Authors: Cheng Siong Chin, M. Venkateshkumar, Jianhua Zhang
Published: 2026-10-04
Categories: cs.RO, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2610.04949v1

Reinforcement learning controllers for underwater vehicles are usually trained against one physics representation and deployed against another, so reported performance does not always describe behavior outside training. This paper presents a pipeline-tracking architecture for a six-degree-of-freedom remotely operated vehicle (ROV) in which one Universal Scene Description (USD) scene supplies the real BlueROV2-Heavy mass, added-mass, damping, buoyancy, and thruster parameters to both halves of the system: a vectorized NumPy implementation of Fossen's marine-craft equations, and an interactive NVIDIA Isaac Sim deployment applying the identical equations as PhysX forces at every step. The Coriolis-centripetal term is the primary dynamics model in both branches; a controlled ablation on PPO and TRPO shows that including it does not destabilize either algorithm and modestly improves tracking, about 19 percent lower standoff RMS error for TRPO. Five reinforcement learning algorithms, PPO, soft actor-critic, TD3, DDPG, and TRPO, are trained against one environment, reward, and randomized evaluation harness through a checkpoint-compatibility layer scoring any policy with the same code. The pipeline is extended with six classical baselines, PID, sliding-mode, fuzzy logic, feedback linearization, model predictive control, and an adaptive neuro-fuzzy inference system, driven by the same guidance geometry and thruster allocation as the learned policies. Under Coriolis-enabled dynamics, PPO, TRPO, and feedback linearization reach the strongest combination of 100 percent success and competitive accuracy; PID, fuzzy control, and the neuro-fuzzy baseline also reach 100 percent success with looser tracking; DDPG and TD3 each show a specific, explainable failure mode rather than a general weakness of off-policy learning; and classical control remains a strong baseline against the best learned policies.

---

### Bridging the EHR Divide: Asymmetric Contrastive Learning for Cross-National Medical Representation Transfer

Authors: Qingyang Zhang
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.04946v2

Cross-system transfer of longitudinal Electronic Health Record (EHR) representations is challenging because clinical coding, patient populations, and healthcare workflows differ substantially across institutions and countries. We introduce Asymmetric Supervised Contrastive Learning (Asymmetric SupCon), a task-specific pre-training objective motivated by the heterogeneity of negative clinical outcomes. The objective clusters patients sharing a target positive outcome without explicitly attracting negative trajectories toward one another. We pre-train temporal Transformer encoders on longitudinal records from 3.98 million patients in the Taiwanese National Health Insurance Research Database (NHIRD) and transfer them to two U.S. EHR datasets, MIMIC-IV and EHRSHOT. A hybrid semantic mapping pipeline combining direct mappings with embedding-based retrieval enables transfer across heterogeneous clinical vocabularies. On MIMIC-IV, NHIRD pre-training consistently improves over random initialization while substantially narrowing the performance gap to task-specific in-domain pre-training. On EHRSHOT, the transferred models show particularly strong few-shot performance for incident disease prediction. A controlled objective ablation under a matched pre-training scale shows that Asymmetric SupCon achieves higher mean AUPRC than direct supervised BCE transfer on all four evaluated tasks and Standard SupCon on three of four, with a 0.003 AUPRC deficit on readmission. These results support asymmetric contrastive pre-training as an effective approach for task-specific cross-national EHR representation transfer. Code is available at https://github.com/qingYzhang/Asymmetric_SupCon.

---

### TempoBridge: Source-Conditioned Flow Matching with Optimal Transport Couplings for Single-Cell Population Transitions

Authors: Bowen Han, Lingbei Meng, Shihuan Luo, Yupeng Zang, Wenlin LI, Peize He, Yaodi Luo, Lian Zhang, Jianqing Zhu, Jinchao Xu
Published: 2026-10-04
Categories: cs.LG, cs.AI, q-bio.GN
arXiv: https://arxiv.org/abs/2610.04945v2

Destructive single-cell measurements provide unpaired population snapshots rather than observations of the same cells across conditions. Local cell states and transition requests may also be insufficient to distinguish responses across source populations. We introduce TempoBridge, a common source-conditioned transport formulation for temporal, genetic, and chemical population transitions. Source cells initialize latent transport and provide a fixed empirical population summary. The velocity field receives this summary alongside the evolving cell state, flow time, and a structured transition descriptor. Minibatch optimal transport (OT) supplies couplings only for conditional flow-matching training paths; inference requires neither target expression nor OT computation. On held-out donors, TempoBridge achieves an Energy distance of 0.129 versus 0.144 for scGen. Genetic mean-expression $L_2$ error is 2.261 versus 3.156 for scGPT-scratch under Seen 2/2. On held-out compounds, condition-averaged drug-effect correlation is 0.598 versus 0.561 for the CellFlow adapter. Temporal ablations show higher mean distributional error after removing source context, replacing optimal transport with random pairing, or replacing flow matching with static residual regression. Together, these results demonstrate the predictive utility of a common source-conditioned transport formulation across held-out donors, gene combinations, and compounds.

---

### Near-Optimal Complexity of Finite-Sum Nonconvex-Strongly-Concave Minimax Optimization

Authors: Qihao Zhou
Published: 2026-10-04
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2610.04944v1

We characterize, up to logarithmic factors, the minimax expected query complexity of finite-sum nonconvex-strongly-concave optimization under mean-squared averaged smoothness. For randomized zero-respecting incremental first-order algorithms, the complexity is $\tildeΘ(n+\min\{\sqrt{n}\,κ,n^{3/4}\sqrtκ\}\,LΔ\varepsilon^{-2})$ throughout $κ=L/μ\ge1$, under exact dual initialization and for $0<\varepsilon^2\le c_0LΔ$, where $c_0>0$ is universal. This characterization is our main result. A dual-chain construction provides the lower bound and matches the existing Catalyst upper bound for $κ\ge\sqrt{n}$. For $1\leκ\le\sqrt{n}$, we introduce recursive proximal descent-ascent (RPDA), which retains a recursive gradient estimator across proximal subproblems and attains $\tilde{O}(n+\sqrt{n}\,κLΔ\varepsilon^{-2})$ with a fixed query budget. Both upper bounds guarantee an expected squared primal gradient at most $\varepsilon^2$. Under individual smoothness, we also prove $Ω(n+\min\{κ,\sqrt{nκ}\}\,LΔ\varepsilon^{-2})$ for every $κ\ge1$. It matches the polynomial upper rate for a bilinear subclass when $κ\ge n$; the intermediate-condition-number gap remains open.

---

### Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning

Authors: Jing Xie, Haochen Yuan, Yunbo Wang
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.04942v1

Time-series question answering (TSQA) requires grounding linguistic queries and diverse answer formats in complex numerical observations. However, existing methods heavily overfit to specific datasets and struggle to generalize when input series, question contexts, and answer requirements shift simultaneously. To address this challenge, we propose TSHarness, an agentic framework that establishes a decoupled workflow for cross-dataset zero-shot TSQA. At its core, TSHarness divides and conquers numerical perception and contextual reasoning via a structured Time-Series Perception State (TPS). Guided by a reusable memory of analytical knowledge, a learned Tool Selector adaptively invokes numerical tools to extract salient statistical and temporal features into the TPS. The answering agent then performs semantic reasoning over the TPS to generate target outputs, triggering iterative re-perception through the feedback loop when evidence is deemed insufficient. By separating numerical feature extraction from question-specific reasoning, TSHarness eliminates the need for target-side training or answer feedback, providing a generalizable, cost-efficient foundation for zero-shot TSQA.

---

### Software World Models: From Consequence Prediction to Decision Value

Authors: Tongli Su, Yuntong Hu, Liang Zhao, Bowen Zhu, JayaSai Somasundaram, Hasibul Haque
Published: 2026-10-04
Categories: cs.LG, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2610.04940v1

A coding agent may safely modify one repository while silently breaking downstream services, libraries, or datastores that depend on it. Exhaustively running integration tests after every agent action is impractical, so the agent must predict these failures before executing them. Existing software world models predict the agent's own observations, while static change-impact analysis only identifies where a change may propagate. We instead introduce the Software World Model (SWM), which models the broader system affected by a code change and predicts its blast set: the components that the change will break. SWM follows three stages: explore, learn, and act. Explore executes candidate changes from restored system states, prioritizing regions where observed failures contradict the dependency graph. Learn fine-tunes a language model on these execution outcomes to predict downstream breakage. Act converts sampled predictions into per-consumer break probabilities for change ranking, proactive migration, and deciding when another execution is worth its cost. On held-out synthetic systems, SWM improves blast-set F1 from 0.431 for static reachability to $0.571\pm0.037$, more than halves ranking regret, and improves migration return at all nine evaluation checkpoints. The two methods are complementary: reachability is stronger on dependencies represented in the graph, while SWM recovers failures caused by couplings the graph misses. Experiments on held-out real libraries further show that predicting structured failure outcomes, rather than only scalar risk, is important for downstream decision quality.

---

### A Graph-Based Inspection and Intervention Tool for Assessing Mechanistic Learning in PINNs

Authors: Adwait Patkhedkar, Alifaraz Lakhani, Prathmesh Mohite, Abhijeet Salunke
Published: 2026-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.04939v1

We ask whether physically meaningful correspondences discovered inside a trained scientific model remain meaningful outside the conditions under which they were discovered. We introduce GIIT (Graph-based Inspection and Intervention Tool), which represents governing physics as a computational physics dependency graph, maps graph nodes to internal network components via sensitivity- and trend-based discovery, and tests the resulting mapping under targeted intervention. Evaluating on temporal extrapolation out-of-distribution (OOD) regimes of increasing severity, we find that temporal extrapolation is associated with layer-wise correspondence drift and reduced functional correspondence. Specifically, while the model achieves low physics residual in-distribution (1.915 x 10-4 on full ID and 1.01 x 10-4 on an ID sub-window t in (0.5, 0.8)), the functional mapping changes even before leaving the training domain, and the shift continues as the evaluation window extends beyond the training domain: residual error increases from 2.81 x 10-2 on the boundary-crossing window (t in (0.5, 1.5)) to 3.30 x 10-1 on severe OOD (t in (1, 2)), accompanied by a systematic leftward shift of internal layer mappings, where the average winner layer index drops from 5.71 (ID) to 3.00 (ID sub-window) down to 2.29 (severe OOD). Only 2 of 7 physical nodes maintain stable layer assignments across the boundary-crossing window, and only 1 of 7 under severe extrapolation, revealing potential internal functional correspondence changes before severe degradation in conventional output metrics. Additional results for linear oscillatory systems are further detailed in the appendix.

---

### D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform

Authors: Jieke Wu, Qijie Zhu, Weimin Wu, Zeqi Ye, Minshuo Chen, Han Liu
Published: 2026-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.04938v2

We propose D-DOIT (Discrete Doob-Oriented Inference-time Transformation), a training-free and efficient adaptation method for discrete diffusion models with generic rewards. D-DOIT formulates adaptation as sampling from a reward-tilted target distribution and realizes this transport through Doob's h-transform of the discrete diffusion reverse kernel, using only reward values rather than reward gradients. Unlike continuous diffusion, masked discrete diffusion samples categorical token-reveal transitions rather than continuous state updates. D-DOIT derives the corresponding discrete Doob's h-transform, which guides sampling by reweighting reverse transition probabilities instead of adding a drift correction. To make this transformation practical, D-DOIT avoids expensive future rollouts. At each guided step, D-DOIT samples candidate next states, uses the model prediction head to complete each candidate into a clean sequence, evaluates each completion with the reward oracle, and resamples the next state with probabilities proportional to the rewards. An optional late-stage best-of-K refinement further improves sample quality by branching trajectories only near the end of denoising, avoiding the $K$-fold cost over the full trajectory. Empirically, across regulatory DNA design and protein inverse folding benchmarks, D-DOIT outperforms training-free guidance baselines. It improves enhancer activity and cell-type specificity while preserving sequence naturalness, and achieves the highest success rate in protein inverse folding.

---

### Learning under Localized Minority Imbalance

Authors: Amin Hosseininasab, Steven M. Shugan
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.04936v1

Class-imbalance methods implicitly assume that the minority class is uniformly undersampled relative to the majority class. However, in many real-world settings, minority instances may be disproportionately under-observed in certain regions of the feature space. For example, small businesses that go bankrupt may disappear from records, while those that survive remain visible, making bankruptcy appear less common among small firms than it actually is. This gives rise to localized minority imbalance (LMI), a challenge that is often overlooked and extends beyond general class-count imbalance. We show that under LMI, existing imbalance mitigation techniques can fit observation-induced biases in the training data and generalize poorly to under-observed regions of the true minority distribution. To address this, we propose a tree-based stratified approach that recursively partitions the feature space with the goal of reducing within-stratum LMI distortion. For each resulting stratum, we pair its majority instances with the full observed minority set and train a base classifier to create an ensemble. Extensive experiments over benchmark tabular datasets simulated with LMI show that our stratified ensembling approach outperforms popular and state-of-the-art imbalance mitigation techniques. We also introduce a gold-standard evaluation protocol that uses unbiased test sets, and demonstrate that conventional hold-out evaluation from the same LMI-biased data can substantially mislead performance. Overall, our results highlight that the cause of imbalance is as important as the correction method.

---

### DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling

Authors: Seongheon Park, Heecheol Kim, Shulin Tian, Lilika Makabe, Namiko Saito, Katsushi Ikeuchi, Sharon Li, Yasuyuki Matsushita
Published: 2026-10-04
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.04933v1

Scaling robot data and model capacity has improved Vision-Language-Action (VLA) policies, but further progress is constrained by the high cost of robotic data. Verifier-guided test-time scaling offers an efficient alternative by sampling multiple action candidates and selecting the one most likely to lead to task success at inference time. Existing classification-based verifiers learn from trajectory-level outcomes but treat all visited states equally, even though their value for candidate discrimination can vary across a trajectory. At many states, plausible actions are similar and provide limited discrimination signal, while only a sparse set of decision-critical states admits meaningfully different actions that can substantially affect downstream outcomes. To address this, we propose DiVeR, which estimates decision criticality from the dispersion of sampled action representations. DiVeR then uses this signal to reweight verifier learning toward states where action selection is most consequential, without requiring step-level annotations or additional environment interaction. Across LIBERO, RoboCasa, and real-world experiments on a Franka Research 3 robot, DiVeR consistently improves task success through more effective verifier-guided action selection, while adding negligible verifier inference overhead.

---

### Billion-Scale Thumbnail Optimization for Uncurated Short-Form Videos via Multi-Armed Bandits

Authors: Ying Han, Ling Liu, Fabio Soldo, Vu Nguyen, Danio Wang, Liz Kidd, Yongle Cao, Theodore Rose, Su-Lin Wu, Romer Rosales
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.04931v1

This paper introduces a real-time thumbnail optimization system deployed at a global $O(B)$ scale on a major short-form video platform. Unlike traditional long-form content, where custom thumbnails are heavily curated by creators, a considerable fraction of short-form videos are published without human-selected artwork. To address this uncurated corpus, we present a fully automated, end-to-end framework that replaces static default frames with dynamic, data-driven selections across billions of videos. To the best of our knowledge, this is the first published work demonstrating an online Multi-Armed Bandit framework successfully deployed at an $O(B)$ scale for uncurated short-form video discovery. Our solution pairs a multi-stage candidate generation pipeline with a low-latency serving infrastructure. By initializing the exploration framework with image-specific priors derived from a deep visual quality model, the system minimizes exploration costs and dynamically serves optimal thumbnails at serving time. Global deployment demonstrates statistically significant improvements in core user discovery and engagement metrics.

---

### Prompt Dominance and Asymmetric Verifier Costs: Empirical Ablations of GRPO at 1B Scale on GSM8K

Authors: Yi Hou
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.04928v1

This paper studies GRPO at 1B scale from both directions: what estimator choices do to the learning signal, and what a degraded reward signal does to what is learned. We train OLMo-2-0425-1B on GSM8K with a from-scratch implementation and measure both sides in controlled sweeps, including a verifier-quality experiment that degrades the training reward and the test-time selector identically. Four results stand out. The prompt is the first-order decision: the zero-shot prompt leaves the base model at 0.08% (its outputs are degenerate continuations, not wrong answers), so almost no group carries a gradient, and training succeeds because the 3-shot prompt reaches 18.3%. At this scale the estimator variants sit within seed noise, with Dr. GRPO ahead on both seeds. In the off-policy regime, clipping is the whole story: training on data without a clipped ratio loses 4-6 points relative to the on-policy reference, while GRPO-style clipping and GSPO recover the loss entirely. Finally, the same weak verifier is far cheaper in RL than in test-time selection: a 10%-flip verifier leaves RL's attainable gain intact (91% and 106% retained across two seeds) where selection retains 57%, and a format-only verifier leaves RL with 16-30% of its gain and selection with essentially nothing. Flip noise acts as an affine transform on the expected reward, and the group-normalized advantage with Adam's rescaling removes it exactly; the residual is a second-order variance effect that the matched-step comparison at a 30% flip rate tests.

---

### Assembling Insights for Agentic Machine Learning Engineering Systems

Authors: Bihui Jin, Yinxi Li, Kaiyuan Wang, Pengyu Nie
Published: 2026-10-04
Categories: cs.SE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.04927v1

Agentic machine learning engineering (MLE) is an emerging AI4SE application for complex ML tasks and a step toward recursive self-improvement of AI systems. Recent agentic MLE systems show the value of leveraging insights from related MLE tasks: some systems condition code generation on expert domain knowledge, which is implicitly curated from peer MLE tasks; some systems have a loop of solving an MLE task, gathering memory to benefit future tasks. However, insight collection and injection remain ad hoc, and existing evaluations often do not control insight sources, making data leakage a threat to validity. To close these gaps, we systematically study how insights from related MLE tasks affect agentic MLE systems, and how their impact depends on insight type and injection method. We introduce MLE-InsightBench, a benchmark of 160 Kaggle competitions across 12 domains. To prevent leakage, one competition per domain is held out as the target, while the remaining 148 serve as sources only when they cannot have been influenced by the target task, such as through later editions or reused solutions. We also develop MLE-InsightForge, an insight assembly agent that explores source competitions, top human solutions, and writeups to construct three insight types: 12 domain insights summarizing best practices, 148 competition insights describing winning solutions, and 16 improvement insights capturing generic debugging and optimization strategies. These insights are injected either as on-demand skills or as an upfront playbook. In our evaluation, the extracted insights improve the normalized private-test score by 123.9% over a no-insight baseline. Controlled experiments further show that the three insight types are complementary; the better injection mode (skill vs. playbook) varies by tasks, with skills more cost-effective overall; and the gains generalize across backend LLMs.

---

### TSAE: Structured Sparse Autoencoders for Interpreting Time-Series Forecasting Models

Authors: Baoxi Liu, Yi Xie
Published: 2026-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.04925v1

Time-series forecasting informs critical decisions in energy dispatch, industrial operations, and environmental monitoring; understanding the patterns models rely on is essential for assessing reliability and identifying failures. Input attribution identifies important variables and time segments but offers limited insight into internal features, while standard sparse autoencoder (SAE) objectives do not directly constrain cross-variable structure or temporal continuity. We introduce TSAE, a structured sparse autoencoder for forecasting representations that decomposes hidden states into individually inspectable features. TSAE organizes cross-variable structure through shared and variable-routed private dictionaries, separates feature detection from magnitude estimation with gated encoding, and constrains neighboring sparse-code changes according to raw-segment similarity. These mechanisms support analysis of variable context, activation strength, and temporal evolution. Forecast-consistency fine-tuning further improves preservation of the frozen forecaster's outputs. The accompanying TSEVAL protocol separately audits fidelity, feature coherence, and physical calibration to ground feature interpretation. In three-seed experiments with frozen PatchTST on ETTh1, ETTh2, and ETTm1, TSAE achieves the lowest hidden-state reconstruction error, normalized forecast-reconstruction error (NFRE), and feature transition rate among five SAEs at comparable per-token activity. NFRE decreases by 4.3-26.4% relative to the next-best mean. Dataset-dependent tradeoffs in selectivity, physical correlation, and calibration show that fidelity and temporal-stability gains require independent semantic validation to support feature interpretation.

---

### TRACE: Time-Adaptive Residual Attention Control with Content-Style Decomposition for Training-Free Diffusion Style Transfer

Authors: Duc Khoan Le, Kim Ngoc Tran, Minh Nhat Le, Thanh An Tran, Viet Toan Nguyen, Khanh An Lay, Tran Thai Son, Hoang Pham Minh
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.04922v1

Reference-guided style transfer aims to preserve the semantic structure of a content image while transferring the visual appearance of a style reference. Recent diffusion-based methods achieve impressive stylization quality by exploiting strong pretrained generative priors. However, training-free approaches still face a difficult trade-off among style fidelity, content preservation, and content leakage. Direct style injection may unintentionally transfer semantic content from the style image, while fixed guidance schedules often ignore the time- and state-dependent nature of diffusion sampling. To address these limitations, we propose TRACE, a training-free diffusion style transfer framework with Time-adaptive Residual Attention Control and Content-Style Decomposition. TRACE first performs offline CLIP-based subspace analysis to separate content and style directions from paired data. During inference, it removes content-related components from the style reference and style-related components from the content reference to reduce leakage. It then injects style information through residual cross-attention and applies uncertainty-aware guidance to adapt the guidance signal at each denoising step. Experiments show that TRACE achieves a favorable trade-off between stylization and preservation. Compared with optimal-control-based baselines, TRACE substantially improves style fidelity (+17.28 CSD and +34.10 SRA). While, compared with stylization methods, it better preserves content structure (+12.80 DINO, +5.52 CLIP-I, and -8.19 LPIPS) and reduces directional semantic leakage by 29.5% in DCL. Our code is publicly available at https://github.com/pixelchemy-research/TRACE.

---

### Complex Agents, Shallow Tests: Demystifying and Enhancing Test Adequacy of Agent Harness in the Wild

Authors: Yifan Xiong, Jingyi Ge, Zhenpeng Chen, Yiling Lou
Published: 2026-10-04
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2610.04921v1

LLM-based agentic systems are emerging as a new software paradigm. Modern agents are typically composed of backbone LLMs and a surrounding harness that serves as the operational software infrastructure for agent execution. As agent harnesses grow increasingly complex, agents suffer from diverse harness implementation bugs, raising substantial reliability concerns. In this work, we conduct the first empirical study to systematically investigate the test adequacy of harness in real-world agentic systems. Our analysis reveals that agent harness remains substantially undertested. In particular, LLM-dependent harness (LDH) code, despite its critical role in processing LLM outputs and governing agent behavior, receives limited testing attention, with less than half of its lines and branches covered by existing tests. Motivated by these findings, we further propose HarnessTester, the first harness-oriented test generation technique that incorporates explicit agent-harness contract support to construct contract-faithful test setups and extensively exercise LDH code. Our evaluation shows that HarnessTester substantially outperforms state-of-the-art general-purpose test generation techniques in achieving 75.95%/84.76% larger line/branch coverage gains and 69.89% larger mutation-score gains. Furthermore, HarnessTester detects 122 real-world harness bugs in widely-used agentic systems (e.g., OpenClaw), among which, 88 bugs are previously-unknown bugs and 69 bugs have been confirmed by agent developers. These results highlight the practical effectiveness of HarnessTester in improving test adequacy and assuring the reliability of real-world agentic systems.

---

### PWM: Personalized World Models with Online Reinforcement Learning

Authors: Zhexin Lou, Guancheng Lu, Zeyu Zhang, Yi Zhang, Yang Zhao, Hao Tang
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.04920v2

Pretrained world models can generate diverse environments, yet users often want to explore a particular scene specified by their own video. This requires learning the scene's visual identity while retaining the quality of action-conditioned generation. We introduce Personalized World Models (PWM), a framework for customizing interactive world models from short scene videos through online reinforcement learning. In PWM, the support trajectory and its associated controls provide reward feedback on continuations sampled from the current policy. In the GRPO instantiation, group-relative optimization updates a compact LoRA adapter using a unified reward for scene appearance, visual continuity, and motion, while base-policy anchoring regularizes changes to the pretrained generation prior of a frozen Yume-5B backbone. The same adaptation procedure is applied across real and rendered environments. We also instantiate PWM with DiffusionNFT as an alternative reward-guided optimization method for learning the scene-specific adapter. We also introduce PWM-Bench, comprising 150 customization tasks across Indoor, Outdoor, and Gaming, with paired evaluation on held-out continuations. The GRPO and DiffusionNFT instantiations of PWM improve customization over native Yume in 71.3% and 65.3% of the evaluated scenes, respectively, with positive mean gains across all three domains. For the GRPO instantiation, matched SFT comparisons further demonstrate higher mean customization gains and better mean image-quality scores in every domain, while retaining frame-level visual quality close to the pretrained model.

---

### Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning

Authors: Lin Qiu, Yao Liu, Diyi Hu, Hanqing Zeng, Onur Gungor, Chujie Chen, Jiayi Liu, Jianyu Wang, XueLin Zheng
Published: 2026-10-04
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2610.04918v1

Reinforcement learning with verifiable rewards scales multimodal reasoning, but an outcome reward says how much a trajectory is worth, not how that value should be spread over the decisions that produced it. We introduce Residual Visual Credit Optimization (RVCO), which treats token credit as a conserved routing problem. A controlled visual intervention yields a per-token evidence response; robust within-trajectory coordinates remove incidental scale; and a budgeted entropic router distributes a fixed amount of sequence utility according to perceptual dependence. A residual support path guarantees positive credit at every valid position, and an analytic correction restores the prescribed credit mass exactly. The resulting field is selective, bounded, full-support, and invariant to response-local score shifts, and recovers hard token selection as a limiting case. Across four model families and seven reasoning benchmarks, RVCO improves accuracy over strong RLVR baselines while maintaining late-stage optimization stability, corruption robustness, and competitive training cost. Rewards, rollouts, and the group-relative advantage estimator are unchanged; only the geometry of token-level credit differs.

---

### PreAct-Nav: Agentic Reasoning Before Action for Urban Navigation

Authors: Jing Xie, Shouwei Ruan, Yubin Wang, Yuxiang Zhang, Junwei Yang, Songchang Jin, Dianxi Shi
Published: 2026-10-04
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2610.04916v1

Urban navigation requires embodied agents to pursue long-horizon goals through local decisions based on egocentric observations. However, existing agentic navigation methods often struggle to translate distant goals into coherent local decisions in large-scale physical environments. Their reliance on linguistic reasoning over transient observations or limited history constrains anticipation of the consequences of actions and future conditions, despite the importance of such foresight for navigating long and complex urban routes. To bridge this gap, we propose PreAct-Nav, an agentic navigation framework that equips frozen policies with anticipatory reasoning for robust urban navigation. Our central idea is to anchor local decisions in persistent medium-horizon subgoals, assess the consequences of predicted actions before execution, and continually update the reasoning context using actual outcomes. At its core, a navigation memory module maintains the active subgoal and relevant experience across decisions, translating distant goals into actionable intermediate objectives. We further introduce a predictive world sandbox that uses an action-conditioned world model (AC-WM) to forecast world dynamics conditioned on candidate movements. A vision-language model (VLM) reasoner interprets these predictions under the current subgoal to retain or revise actions. After execution, real observations are used to assess outcomes, correct inconsistent assumptions, and update memory to continue or reformulate the subgoal. Extensive evaluations demonstrate that the proposed PreAct-Nav improves action selection through memory updates and visual prediction, with more pronounced gains on longer routes and routes with more turns.

---

### Are We Measuring Scientific Intelligence? Rethinking the Evaluation of AI Scientists

Authors: Kate Zhang, Yuante Li
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.04915v1

AI agents can now carry out data-driven scientific analyses end to end, and benchmarks assess them by giving an agent a question and a dataset and scoring its final answer against a fixed key. These benchmarks assume that a correct answer was derived from the supplied data, a property we call evidence grounding. However, an agent can also reach the key from prior knowledge or by ruling out the other options, and a score based on a single run cannot tell these cases apart. We show how to test this assumption and find that it often fails. For each question, we build versions of its data files in which the evidence for the answer is left intact, withdrawn or reversed, check each edit with a pre-registered reference statistic, and run the same agent on every version. We then measure evidence-grounded accuracy, which credits a correct answer only if the agent also responds when the evidence is withdrawn and follows it when it is reversed. We evaluate three agent scaffolds and five models on 18 single-cell questions from BAISBench and four synthetic problems from GeneBench-Pro. On the single-cell questions, the Claude agents are 95% accurate and answer 83% correctly without any data, but their evidence-grounded accuracy is only 41%. Hiding gene names raises the share of runs that follow reversed evidence from 58% to 93% on ten gene tasks, suggesting that prior knowledge competes with the supplied data. The benchmark score and LLM judges can also reward answers that ignore the changed evidence. Measuring scientific intelligence rather than recall therefore requires checking whether answers follow the evidence and whether scores reward them for it.

---

### Monitorability Disposition in Large Reasoning Models

Authors: Shahriar Golchin, Marc Wetter
Published: 2026-10-04
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.04914v1

Monitoring the chain-of-thought (CoT) of large reasoning models (LRMs) is a common way to detect misbehavior in real-world practice. However, current monitoring is passive: a separate model inspects the session only after execution. This means harm may already have occurred before it is caught. An active alternative is to have the model self-report its misbehavior as it happens. Whether models are willing to do this, however, is unknown. We introduce "monitorability disposition": a model's willingness to make itself monitorable and stay monitored throughout inference when warranted. We measure it as the fraction of warranted cases in which a model self-reports its own misbehavior via tool calls to available monitoring channels. We evaluate four LRMs on three misbehaviors (sycophancy, reward hacking, and bias) while varying the available monitors (AI and human) and the pressure to use the monitoring tools. We find that when tool use is optional, models self-report in only about 16% of warranted cases on average. Increasing tool-use pressure does not improve reporting where it matters: high-severity misbehavior is never self-reported. Models also systematically select the monitor they perceive as least strict. Overall, we identify monitorability disposition as a new contributing factor to model monitorability: when sufficiently strong, it keeps models seeking monitorability throughout inference.

---

### Static Bootstrap Placement for Encrypted Language Model Decoding

Authors: Halil Ibrahim Kanpak, Didem Unat
Published: 2026-10-04
Categories: cs.CR, cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2610.04912v1

Language models increasingly serve prompts that carry private data, and secure inference under homomorphic encryption lets a client outsource the computation without revealing the prompt. Existing secure inference systems run a forward pass without consuming a token under encryption, and generating text with them requires a client round trip at every generated token. Keeping the loop on the server instead requires selecting and consuming a token under encryption, and placing bootstraps for a loop body that grows with the context. We build AR-HE, which runs the whole loop on the server, selects each token under encryption, retrieves its embedding, and writes it back into the encrypted state. The client sends one prompt and remains offline until the output. One rule places every bootstrap in the run, without search, so the bootstrap cost of a token is a formula in the context length that is known before the run starts. The schedule skips work whose result cannot reach the output, packs bootstraps that share an operand, and keeps the keys and values of past positions in an encrypted cache. With every optimization applied, generating a GPT-2 small token costs 544 seconds on one NVIDIA H100, down from 4715 seconds without optimization. The prompt step before it costs 4630 seconds. The cache alone takes a generated step from 11751 bootstraps to 1072. The formula predicts every step we measured, including steps of a model it was not derived from.

---

### VideoResearchAgent: Grounded Task Synthesis and Sim-to-Real RL for Open-Web Video Research

Authors: Yuhang Zhou, Fei Li, Yuxi Wu, Bin Zhu, Jingjing Chen
Published: 2026-10-04
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2610.04911v1

Existing deep research agents are designed primarily for text- and image-based web sources, while video reasoning systems typically assume that relevant videos are provided in advance. We study open-web video research, where an agent must autonomously discover relevant videos, navigate their temporal content, and ground answers in visual evidence. Training such agents at scale is challenging as live video interaction is slow and unreliable, whereas fixed local simulation can induce retrieval-specific shortcuts that fail to transfer to the open web. We introduce VideoResearchAgent, a scalable training framework to address these challenges. First, we introduce controllable task synthesis pipeline to synthesize multi-hop research tasks from timestamped visual evidence while filtering text-only shortcuts. Second, we build a field-aligned local video simulator that preserves deployment-facing search and watch interactions while accelerating video search by a factor of 34.5-64.6. Third, we introduce Retrieval-Domain-Randomized GRPO (RDR-GRPO), which diversifies candidate rankings, distractors, metadata, and result structure during training to reduce overfitting to simulated retrieval. On Video-BrowseComp, the VideoResearchAgent trained using Qwen3.5-4B achieves 40.48% accuracy, comparable to Gemini-3-Flash-Preview, while reducing cumulative API-token consumption by 74.9% relative to the untrained model. Together, these results establish an accurate and efficient training recipe for open-web video research.

---

### Why Subliminal Learning Needs So Much Data: A Noisy Inverse View through Steering Vector Recovery

Authors: Luoyu Chen, Xiaoyu Ding, Weiqi Wang, Chenhan Zhang, Zhiyi Tian, Jianhuan Huang, Shui Yu
Published: 2026-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.04907v1

Subliminal learning lets a student inherit a teacher's behavioral trait from semantically unrelated data, yet published demonstrations typically require tens of thousands of carrier examples. We ask where this data requirement comes from. Our testbed is subliminal steering: the teacher trait is a known residual-stream vector $Δ_T$, so transfer can be measured directly as parameter recovery. On identical carrier prefixes, we compare token-level (hard) NLL supervision with full-distribution (soft) KL supervision. At initialization the two objectives give nearly collinear gradients, and both align poorly with $Δ_T$. Under iterative optimization, however, they diverge: soft supervision recovers $Δ_T$ almost exactly from a few hundred carriers, while hard supervision stays well below it even with tens of thousands. We explain this gap by casting steering-vector distillation as a noisy linear inverse problem. Locally, the carrier task maps the trait through its Fisher matrix $F$, so gradients point toward $FΔ_T$ rather than $Δ_T$. Gradient descent then acts as a progressively less-damped inverse of $F$. With soft targets, this inverse restores low-curvature directions. With hard labels, it also amplifies the sampling noise in those same directions. The result is an optimal inversion depth that grows with the number of independent carriers. Experiments on Qwen2.5-7B and Gemma-2-9B confirm four predictions: the Fisher distortion of the initial gradient, recovery ordered from steep to flat directions, an optimal depth that shifts with data scale, and the finding that resampling completions from a fixed prompt pool works as well as adding new prompts. In this setting, large carrier datasets are needed less to reveal the trait than to suppress label noise amplified by Fisher inversion. Code is available at \url{https://github.com/luoyuchenmlcv/subliminal-data}.

---

### Scaling Verifiable Environments for Long-horizon Work Agents

Authors: Jiazheng Zhang, Long Ma, Yunxian Yang, Zhiheng Xi, Zhikai Lei, Yajie Yang, Chenyang Liao, Enyu Zhou, Yang Nan, Yuchen Tian, Senjie Jin, Yibo Wang et al.
Published: 2026-10-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.04906v3

Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long-horizon interaction and trustworthy verification. However, hand-crafted environments incur prohibitive engineering overhead that prevents environment scaling, whereas synthesis methods sacrifice workspace complexity, realism, or grounded verifiability. To bridge this gap, we introduce WorkForge, a scalable synthesis framework for constructing verifiable work-agent environments from real-world resources. Starting from expert workflows, WorkForge first identifies the resources, decisions, and deliverables required by each workflow. It then retrieves relevant real-world files and organizes them into a workspace. WorkForge inspects the workspace to extract concrete, checkable facts about its content. These factual anchors fix which task types the workspace can support and how their outcomes can be verified. Therefore, WorkForge derives each task's instructions, solution plan, and complementary programmatic and semantic verifiers directly from these factual anchors, keeping verification traceable to observable workspace evidence. Furthermore, we construct 16.7K verifiable environments across 40 professional domains, with workspaces collectively covering 60 file types. Post-training Qwen3.5-35B-A3B-Base improves GDPVal from 45.5 to 73.6 and APEX Score from 5.0 to 21.3, while enabling Qwen3.5-27B to achieve highly competitive performance and outperform strong competitors. Our analyses confirm the efficacy of the proposed method and reveal consistent scaling behaviors across both data volume and interaction horizons.

---

### ScopeSAE: Model-Scope Feature Discovery with Interpretable Layer Selection

Authors: Qingwen Zeng, Zehao Fu, Shuyu Meng, Linghan Huang, Jiayi Zhang, Chenglin Wu, Ling Chen, Huaming Chen
Published: 2026-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.04905v1

Sparse autoencoders (SAEs) are a central tool in mechanistic interpretability. However, existing SAEs are primarily trained per layer. The modeling subspace is therefore fixed by layer identity, independent of which token-layer states actually drive each prediction. We argue that this constraint contributes to several limitations observed in layer-wise SAEs, including low feature utilization, high dictionary redundancy, and features that lack direct behavioral grounding. In this paper, we propose ScopeSAE, which selects the modeling subspace per token by attributing each prediction to its most influential token-layer state via normalized gradient-based attribution, and learns features over the resulting prediction-relevant subspace. Empirically, ScopeSAE yields an effect we term reconstruction-better-than-original. Written-back reconstructions of the SAE produce lower next-token cross-entropy than the original activations, an outcome that, to our knowledge, has not previously been reported for SAEs. Through interventional analyses and a KL fine-tuning counter-experiment, we show that this effect is attributable to ScopeSAE's prediction-relevant subspace itself rather than to architectural changes. ScopeSAE further improves effective feature count, interpretability, utilization, and dictionary redundancy over existing layer-based baselines, suggesting that choosing the SAE modeling subspace by predictive relevance leads to more useful and behaviorally meaningful features.

---

### Self-Evaluating Recursive Agents

Authors: TianYi Lyu, Xiaozhe Li, Yang Li, Yongkang Chen, Kefei Tian, Junbo Niu, Zican Hu, Hongbo Liu, Mingliang Xiong, Qingwen Liu
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.04902v1

Recursive language-model agents decompose tasks and delegate subtasks to child instances of the same policy, forming a tree of work. Training them, however, is hard: the final outcome is verifiable, but the self-invented intermediate subtasks are numerous and carry no ground truth. Existing methods score each node with a verifier or judge, which is costly at scale and blind to decomposition quality. We argue that a recursive agent must learn three coupled capabilities within one set of weights: decomposing problems into subtasks, solving them, and evaluating the outcomes, each requiring its own training signal. SERA (Self-Evaluating Recursive Agents) turns evaluation into a learned capability of the policy itself. Before delegating, the parent writes a rubric of weighted success criteria for each child subtask; a ranking objective against verified outcomes then trains rubric generation so that the criteria track genuine subtask success. In addition, a complementary leaf-coverage signal provides direct credit for task decomposition. Our central finding is that \emph{training} the policy to generate aligned rubrics is what drives the gains: because the same weights both evaluate and execute, learning to judge subtasks sharpens the agent's ability to solve them. Notably, external supervision is also reduced: the judge is consulted only to train the rubric generator, while solving is trained against the agent's own rubric scores, which outperform direct use of the judge. Beyond training, the learned rubric doubles as an inference-time selector for tree search. On TextCraft-Synth and TextWorld-Sync, SERA improves over strong recursive-agent baselines by 5.38 and 13.14 points on average, and rubric-guided tree search at inference adds a further 2.43 points on TextWorld-Sync.

---

### Rewrite What Matters: Adaptive Multilingual Query Rewriting for Reasoning via Agentic Reinforcement Learning

Authors: Rui Qi, Yufeng Chen, Yunlong Liang, Chuan Meng, Sijin Lu, Ge Shi, Jinan Xu, Fandong Meng, Kaiyu Huang
Published: 2026-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.04899v1

In multilingual scenarios, queries with equivalent semantics but in different languages could guide the model into different reasoning trajectories, leading to performance disparities. To mitigate this gap, previous studies typically apply a one-size-fits-all query rewriting strategy, such as translation, which overlooks the fact that different scenarios require diverse types of semantic transformations. In this paper, we propose mRewriter-R1, an agentic multilingual query rewriting framework with reinforcement learning. Unlike single-turn rewriting, mRewriter-R1 formulates multilingual query rewriting as a multi-turn sequential decision-making process, where the model dynamically performs multi-aspect optimization through adaptive operator selection. Experimental results demonstrate that mRewriter-R1 outperforms all strong multilingual rewriting baselines on different large reasoning backbones. Further analyses show that the learned policy can adaptively decide on rewriting operators according to query characteristics, exhibiting strong generalization ability across diverse reasoning tasks, and plug-and-play compatibility with heterogeneous reasoning language models.

---

### A Systematic Analysis of the Predictive Power of LM Surprisal in Reading Chinese

Authors: Hongao Zhu, Muxiaoqiao Xu, Yikang Liu, Siyuan Song, Yuxia Wang, Byung-Doh Oh, Hai Hu
Published: 2026-10-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.04898v2

This study analyzes the predictive power of LM-derived, token-level surprisal on Mandarin Chinese reading times. We first propose the Shortest Matching Sequence (SMS), an alignment scheme that maps between the word segmentation assumed by eye-tracking corpora and the LMs' subword tokenization, as the two tokenizations often disagree in the context of Mandarin Chinese. Then, using a suite of Chinese-Pythia models (14M-1.4B) trained on scratch with 30B tokens, we examine how well surprisal predicts first fixation duration, gaze duration, and total reading time in three paragraph-level eye-tracking corpora of Mandarin Chinese (GECO-CN, HKP, and MECO). Contrary to previous null findings, our results show that surprisal is predictive of Chinese reading times. However, whether predictive power scales with model size and the amount of training is corpus-specific: bigger models predict better in GECO-CN, whereas inverse scaling emerges in HKP and, at the largest sizes, in MECO. Subsequently, we tested one possible explanation for the inverse scaling in HKP and found that checkpoints whose surprisal remains closer to $n$-gram statistics are better predictors of reading. All in all, the predictive power of surprisal on Chinese reading time measurements is corpus-specific, which cautions against drawing scaling conclusions from a single corpus.

---

### SFlexRCA: Lightweight, Scalable, and Flexible Root Cause Analysis for IIoT Edge Systems

Authors: Amr M. Zaki, Farhoud Jafari, Honggeun Ji, Komal Sarda, Marin Litoiu
Published: 2026-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.04893v1

Industrial Internet of Things (IIoT) systems generate high-dimensional sensor telemetry from interconnected components, where faults can propagate across the system. To address these challenges, we propose SFlexRCA (Scalable and Flexible Root Cause Analysis), a topology-free RCA framework designed for resource-constrained IIoT environments. SFlexRCA transforms multivariate telemetry into compact orthogonal representations and applies shared lightweight linear modeling, avoiding explicit graph construction, message passing, and per-variable or lag-specific parameter growth. We evaluate SFlexRCA on three publicly available IIoT datasets, BATADAL, SWaT, and WADI, spanning different numbers of monitored variables, temporal characteristics, and training-data regimes. SFlexRCA is compared with 10 statistical, causal, and non-causal baselines in terms of RCA accuracy, training efficiency, inference latency, and memory consumption. In addition, inference efficiency and memory consumption are evaluated on Raspberry Pi 3 and Raspberry Pi 5, while energy consumption is additionally measured on Raspberry Pi 5. We further investigate temporalcontext sensitivity, architectural and loss components, and alternative representations. Notably, SFlexRCA maintains strong localization performance on BATADAL despite its limited normal-operation training data, while its compact shared architecture avoids the parameter growth associated with causal and graph-based approaches. Its lightweight shared architecture further enables efficient deployment on resource-constrained IIoT edge devices. The SFlexRCA code is available at https://github.com/theamrzaki/RootCause- Analysis-Correlation-Attentive-Modeling.

---

### ForkPilot: Self-Evolving Policy for Retrospective Search in Long-Horizon Agents

Authors: Xinyue Zeng, Shivam Shandilya, Guilherme Potje, Leonardo Nunes, Rakshanda Agarwal, Ranveer Chandra, Emre Kiciman, Dawei Zhou, Tusher Chakraborty
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.04889v1

Interactive language-model agents increasingly solve complex tasks through long-horizon, multi-call reasoning, where errors in beliefs or actions can compound across tool interactions. Retrospective search can recover from such failures but is prone to misallocation. Delayed outcomes obscure the contribution of intermediate search decisions, leading to Attribution Complexity, while evolving execution evidence leads to Adaptation Complexity, where previously learned estimates become stale. To address these challenges, we first introduce Search Value Dynamics (SVD), which characterizes the evolving trade-off between the gain and cost of retrospective search. Building on SVD, we propose ForkPilot, a self-evolving two-stage policy-learning framework. In the first stage, ForkPilot learns a search-value policy offline from completed trajectories through automatically constructed outcome comparisons. In the second stage, it makes search decisions based on current observations and then self-evolves by incorporating newly completed trajectories into subsequent policy updates. We evaluate ForkPilot across 6 diverse benchmarks and 7 widely used LLM backbone families, including four open-source families, GPT-5.6 Sol, and Opus 4.8 in a production agentic system, against 9 competitive baselines, including a real-world harness deployment used by hundreds of thousands of paid users. ForkPilot achieves comparable state-of-the-art performance while reducing token usage by up to 59.2%, demonstrating its efficacy.

---

### No Hindsight for LLM Fact-Checkers: Measuring Leakage Channels in Misinformation Detection

Authors: Kuan-Hua Wu Lu, Yohanes Andre Setiawan
Published: 2026-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.04888v1

As automated fact-checking scales on social media, large language model (LLM) verdict scores can look stronger than warranted. One reason is that evaluations mix in information that was not knowable at claim time. Two channels are easy to conflate: outcomes memorized in pre-training and retrieved evidence published after the claim. Yet standard benchmarks rarely separate the two. In this study we measure both channels on AVeriTeC and QuanTemp++ by reconstructing point-in-time evidence conditions and probing for outcome information encoded in model representations. We find substantial evidence of parametric leakage, that can be hidden by the aggregate accuracy, while a simple representation bottleneck reduces this future leakage more efficiently than a mutual-information-based training penalty. We also find that allowing post-claim evidence inflates zero-shot accuracy by 6.3 points in AVeriTeC while the effect is negligible in QuanTemp++, where retrieval provides little post-claim evidence. These results show that misinformation benchmarks can overstate fact-checking performance when they do not account for what information was actually available at claim time.

---

### Reflection-Robust 6DoF Object Tracking with Light Fields

Authors: Nikolai Goncharov, Donald G. Dansereau
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.04883v1

Tracking the 6DoF pose of a moving rigid object is fundamental to robotics and autonomous driving, but existing trackers assume that object appearance is stable across a sequence, an assumption that breaks down on reflective surfaces whose appearance changes as they mirror the environment. We introduce a light field based reflection-robust 6DoF tracker that turns this apparent nuisance into a pose cue. Per frame, our method recovers depth robustly against reflections, back-projects it into a point cloud, and estimates surface normals. It then decomposes the object's view-dependent appearance into a diffuse albedo and the environment map it reflects, resulting in a relightable surface light field. Starting from a coarse initialization, we relight it by the recovered environment map and optimize the pose on the photometric loss. Because a moving object mirrors new parts of the scene, the environment map fills in as the sequence proceeds, sharpening this signal over time. To evaluate this approach, we introduce a light field tracking dataset re-rendered from a robotic manipulation benchmark at four controlled reflectivity levels, each paired with simulated depth that reproduces how consumer RGB-D sensors fail on shiny surfaces. Additionally, we evaluate on two captured light field sequences. Our method trails the strongest baselines on diffuse objects and is the only one that holds its accuracy on fully reflective objects, where every baseline degrades.

---