# Research Papers — 2026-10 · bundle page 25 of 156

> Full-text markdown of papers #1201–1250 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/25
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/24.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/26.md)

### Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents

Authors: Yuanpu Cao, Saket Sathe, Hanyu Wang, Ziyi Yin, Fenglong Ma, Jinghui Chen
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.19439v1

While LLM-based agent systems have demonstrated remarkable proficiency in reasoning and solving complex real-world tasks, they also come with substantial token consumption and inference latency, limiting their practical deployment. To enhance the efficiency of agent systems, recent efforts have focused on transferring agentic capabilities from large-scale models to small language models (SLMs) via supervised fine-tuning-based distillation. Nevertheless, as interaction trajectories grow longer, involving extended reasoning-action chains and extensive environmental feedback, distilled student agents tend to experience progress stagnation: becoming trapped in unproductive loops characterized by persistent failed strategies and difficulty making meaningful progress. Our systematic analysis shows that this phenomenon consistently occurs across diverse SLMs and task domains. To address this issue, we propose Progress-Aware Distillation (ProD), which explicitly detects and penalizes stagnation in student-generated trajectories. ProD encodes the stagnation gap between student and teacher into an adaptive margin for dynamically penalizing possible stagnation. By iteratively applying this procedure, ProD enables student agents to progressively approximate teacher behavior. Extensive experiments involving 8 SLMs, ranging from 0.6B to 8B parameters, on both in-domain and out-of-domain benchmarks, demonstrate that ProD substantially mitigates progress stagnation while enhancing both the success rates and task-completion efficiency of distilled SLM agents.

---

### Learning to Select Features with Manifold Deep Unfolding PCA

Authors: Jingjing Liu, Pei Tai, Xianchao Xiu, Wanquan Liu
Published: 2026-10-14
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.19436v1

Unsupervised feature selection (UFS) is of great significance in image processing and pattern recognition. Nevertheless, existing model-based methods often rely on manually tuned hyperparameters, while deep learning-based methods generally require massive training data. To address these issues, this paper proposes an efficient manifold deep unfolding feature selection network (MDUFS-Net). Technically, we first incorporate the $\ell_{2,0}$-norm into the classic principal component analysis (PCA) framework, then unfold the alternating direction method of multipliers (ADMM)-based iterative algorithm into an end-to-end trainable network, thereby enabling automatic parameter learning. Moreover, a manifold optimization strategy is developed to improve the numerical robustness. On this basis, we further extend MDUFS-Net into an enhanced variant called MDUFS-Net+ by introducing the $\ell_{0}$-norm for more discriminative feature representations. Extensive experiments validate that our proposed MDUFS-Net and MDUFS-Net+ outperform state-of-the-art methods in the UFS task, with promising performance in clustering. Our code is available at https://github.com/xianchaoxiu/MDUFS.

---

### EvoProbe: Evaluation-Driven Benchmark Evolution for LLM Agents

Authors: Qianhong Guo, Wei Xie, Xiaofang Cai, Shuoyoucheng Ma, Chengxin Hu, Baosheng Wang
Published: 2026-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19433v1

Static benchmarks for large language model (LLM) agents face saturation and data contamination risks, motivating continual updates to evaluation tasks. However, aggregate scores and success rates offer limited insight into specific problem-solving bottlenecks and provide limited guidance for subsequent task design. We propose EvoProbe, an evaluation-driven benchmark evolution framework that integrates task generation, diagnostic evaluation, and feedback-driven regeneration into a closed loop. It combines verifiable subtask outcome scoring with evidence-supported multi-judge trajectory evaluation and distills phase-level bottlenecks, success patterns, and failure patterns into diagnostic feedback for generating new executable tasks. Across two rounds of cybersecurity experiments, evaluations of eight models on 66 tasks reveal phase-level performance differences and common failure patterns beyond aggregate scores. In a cross-round comparison with the Examiner model set and solver configuration held fixed, all eight models achieve lower Outcome scores on the updated tasks, with relative decreases of 11.8\% in mean Outcome and 40.0\% in mean Pass\textasciicircum{}3. These results support using fine-grained diagnostics to guide iterative task updates and probe agents' current capabilities and limitations.

---

### Recognition Is Not Grounding: Benchmarking Multilingual Financial Evidence Extraction

Authors: Lingfei Qian, Yan Wang, Xueqing Peng, Polydoros Giannouris, Nadhem Zmandar, Yi Han, Yanguang Liu, Víctor Gutiérrez-Basulto
Published: 2026-10-14
Categories: cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2610.19432v1

Comparing financial disclosures across languages requires identifying shared accounting concepts and recovering all numerical facts that express them. Existing benchmarks evaluate aspects of these capabilities, but provide limited insight into whether both succeed on the same multilingual evidence. In particular, it remains unclear whether language models can recognize these concepts across languages and exhaustively recover their corresponding numerical evidence from the same contexts. We introduce MULTIFINGROUND, a benchmark designed to investigate this recognition-grounding gap in multilingual financial reports. Constructed from FY2025 disclosures of 90 issuers in English, French, and Greek, MULTIFINGROUND aligns independently authored reports through a shared accounting taxonomy and provides traceable fact-level annotations. The benchmark evaluates financial fact identification, concept recognition, exhaustive fact selection, and concept discrimination without candidate labels. Across 15 evaluated models, eight API and open-weight reference models achieve 97.3-99.4\% concept recognition accuracy, yet miss at least one target fact in 26.6-41.9\% of correctly recognized groups. Further analyses reveal substantial variation in concept discrimination and limited gains from the evaluated finance-specialized models. Our findings demonstrate that strong concept recognition can coexist with incomplete evidence recovery, highlighting the importance of evaluating semantic recognition and evidence completeness together.

---

### Comprehensive Comparisons of Reinforcement Learning Algorithms in Autonomous Driving

Authors: Dechen Xie, Mushuang Liu
Published: 2026-10-14
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2610.19429v1

This paper presents a comprehensive comparison of four representative reinforcement learning (RL) methods in autonomous vehicle (AV) decision-making, including: Fitted Value Iteration (FVI), Rollout Classification Policy Iteration (RCPI), Deep Q-Network (DQN), and a discrete-action adaptation of Deep Deterministic Policy Gradient (D-DDPG). The four methods are applied to the same AV decision-making problem at an unsignalized intersection and are compared in terms of optimality and safety, training stability, and training and decision cost. RCPI is the closest to a reference solution and has the most stable training process. However, it is the least data-efficient. D-DDPG reaches the second-smallest gap to a reference solution with the highest data efficiency, but has the least training stability. DQN is the most stable model-free method but has the highest collision rate. FVI achieves a lower collision rate than DQN, but is less data-efficient and less stable. Based on these results, we provide suggestions for selecting a method according to whether a model is available, the budget for training, and whether stable training is required.

---

### How Do LLMs Understand Legal Philosophy? Diagnosing Legal-Philosophical Reasoning in LLMs

Authors: Shuyuan Zheng, Yun-seo Lee, Xing Gao, Jialu Wu, Jiabao Hu, Katrina Qiyao Wang, Xinbo Lin, Qianying Liu, Chuan Xiao, Tao Huang
Published: 2026-10-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.19427v1

Legal reasoning is a fundamental capability for large language models (LLMs) to complete legal AI tasks such as legal judgment prediction. In legal practice, this reasoning is shaped by legal philosophy: a judge's view of the nature and sources of law guides how legal materials are interpreted and applied, so judges working from the same statutes and precedents can reach different judgments. Existing research has largely overlooked whether LLMs can understand legal philosophy and apply it in legal reasoning, an ability we call \textit{legal-philosophical reasoning}. To fill this gap, we introduce LePhilBench, a benchmark for evaluating the legal-philosophical reasoning of LLMs that comprises two benchmarking tasks and a dataset. The two tasks evaluate how well LLMs understand legal philosophy and how well they apply it in legal reasoning, respectively. The dataset is manually and meticulously constructed. Its test set contains 220 U.S. Supreme Court opinions. A law professor designed fourteen annotation questions on legal philosophy, and three law-trained annotators with formal training in jurisprudence answered all fourteen questions for every opinion, yielding 9,240 legal-philosophical labels. LePhilBench takes the first step toward exploring legal-philosophical reasoning in LLMs.

---

### Evaluating Agentic Capabilities Before Post-Training: An End-to-End Approach

Authors: Jiarui Qin, Junjie Huang, Yunjia Xi, Di Yin, Yong Yu, Weinan Zhang, Xing Sun, Weiwen Liu
Published: 2026-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19425v1

Agentic capabilities are increasingly important for modern LLMs, yet remain difficult to evaluate during pretraining. Existing approaches typically rely on static trajectory-derived tasks or likelihood-based proxies, which are lightweight but provide limited visibility into how base models behave in interactive environments. We introduce ASAP (Agent Scaffold Adaptation for Pretraining Evaluation), a lightweight framework for eliciting and evaluating agentic behavior from pretrained base models on end-to-end tasks. Rather than converting base models into chat-style agents, ASAP preserves the completion interface and adapts existing agent scaffolds through structured trajectory continuation, short reference prefixes, and minimal recovery mechanisms. Across software-engineering and deep-research benchmarks, ASAP yields discriminative end-to-end performance across base models and pretraining checkpoints. Beyond aggregate scores, ASAP exposes model-generated execution trajectories, enabling analysis of exploration, editing, testing, recovery, and task completion across training stages. These trajectories provide a behavioral view of how agent-relevant capabilities change during pretraining and how execution patterns differ after post-training. Our results suggest that end-to-end agent evaluation can complement conventional pretraining benchmarks by providing a practical diagnostic of interactive model behavior.

---

### VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness

Authors: Zihao Lin, Haoyu Dong, Haobo Xu, Chi-Chih Chang, Xuying Ning, Yinglong Xia, Shuang Yang, Zhuokai Zhao, Xinying Song, Dongfang Liu, Lifu Huang, Yang Song et al.
Published: 2026-10-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.19424v1

LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reasoning, and memory. Recursive harness evolution can automate their design, but how it can reliably discover generalizable systems from limited, noisy, and repeatedly reused feedback remains unclear. We study this question in agentic video understanding, where rich multimodal evidence and coupled mechanisms make harness optimization challenging. We first introduce VideoHarness-BRSI, a recursive self-improvement framework that evolves video harnesses around a frozen vision-language model. Analyzing over 4,000 evolved candidates, we find it competitive with hand-engineered systems but identify three interconnected failure modes: validation overfitting, search-budget dilution, and the early-experience trap. We trace all three to a common root: the same imperfect validation evidence drives both harness revisions and the proposer's search strategy. We therefore propose VideoHarness-SRSI, an evidence-governed framework in which every search decision rests on evidence that is transferable, sufficient, and gathered before the search commits. It restricts the proposer to content-free feedback, informs exploration with instrumented warm-up experiments, and develops mechanisms in isolated probe-race branches before factorial composition and joint refinement. Across four video understanding benchmarks, VideoHarness-SRSI improves the equally weighted mean held-out score by 6.2% relative to VideoHarness-BRSI and reduces the mean validation-test gap by 37.9%. Reliable harness evolution thus depends on how search is organized and informed, not only on how well it optimizes validation performance.

---

### Beyond the Trial-and-Error Loop: Hybrid Projection and Automated Tuning for Distributed Training

Authors: Anshu Raina, Peyman Razaghi, Yuankai Chen, Cheng Yao, Yao Fu, Vidushi Goyal, Devang Patel, Wen Xie, Zhenyu Gu, Emad Barsoum
Published: 2026-10-14
Categories: cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2610.19423v1

Configuring distributed LLM training across hundreds of GPUs requires jointly optimizing tensor, pipeline, expert, context, and data parallelism alongside micro-batch size, recomputation, sharding, and overlap, a combinatorial space where memory legality can hinge on a single byte of activation accounting. Today, teams navigate it through expensive multi-node trial and error, burning GPU-hours on crashes and suboptimal recipes. We present Primus Projection, which closes this loop with two coupled components. First, a hybrid projection engine that measures what it can and simulates what it cannot: GPU microbenchmarks on as few as a single device capture compute kernels and any in-scope communication; a sub-node downscale-measure-upscale workflow analytically restores out-of-scope collectives, FSDP overlap, and the full pipeline schedule at the multi-node target. A pure simulation mode runs entirely on CPU, enabling pre-silicon planning without any GPU. Second, the Primus Tuning Agent treats the projection engine as a fast scoring oracle (seconds per candidate instead of tens of minutes) and uses it to drive an intelligent search over the configuration space. A deterministic seed planner sweeps single axes; an LLM investigation loop proposes cross-axis combinations the planner cannot reach, with an analytic memory pre-filter that rejects infeasible candidates before any GPU time is spent. Validated on Llama 3.1 (dense) and Mixtral 8x22B (MoE) across two GPU generations, all projections stay within ~10% of measured multi-node throughput, and fidelity holds at production scale: 4.7% error on DeepSeek V3 671B at 1,024 GPUs and 1.9% on Qwen3-235B-A22B at 256 GPUs. In a Mixtral 8x22B case study, the Primus Tuning Agent discovers a configuration delivering +27% throughput over the published 4-node BF16 reference at the same scale, in under 30 minutes of single-node exploration.

---

### AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety

Authors: Chenxu Wang, Xiaoyu Wen, Han Qi, Ziyuan Zhou, Cheng Jin, Chaochao Lu, Qiaosheng Zhang
Published: 2026-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19422v1

Large language model (LLM) agents accomplish complex tasks through multi-turn interactions with external tools. However, malicious content embedded in user queries, tool descriptions, or environment observations can manipulate their decisions and induce unsafe actions. Adversarial co-evolution has emerged as an effective approach to strengthening LLM safety, but existing work primarily focuses on language-level safety or indirect prompt injection in web tasks. In this paper, we introduce AgentSafeEvo, a co-evolutionary reinforcement learning framework for agent safety built on an attacker-defender game spanning diverse tasks and attack types. The attacker learns to construct adversarial agent tasks that expose weaknesses in the defender's tool use, while the defender learns to complete tasks safely under these attacks. We further introduce learnability-guided task weighting, which uses within-task defender-reward variability to adjust each task's contribution to attacker and defender updates. Extensive experiments on agent safety and general capability benchmarks demonstrate that our method improves adversarial robustness while maintaining general agent capabilities.

---

### From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents

Authors: Yue Zhang, Han Lin, Zun Wang, Yidong Huang, Zaid Khan, Mohit Bansal
Published: 2026-10-14
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2610.19420v1

Simulated environments enable scalable training data generation for embodied agents, but more data does not necessarily provide what a particular agent needs to learn. Existing environment-generation pipelines largely optimize generic properties such as realism, diversity, or task coverage, while different pretrained policies can fail for different environmental reasons. We therefore introduce WEDGE, a framework for weakness-guided navigation learning in which the failure modes of a pretrained agent guide the generation of training environments at each adaptation round. Given a pretrained policy, WEDGE uses an LLM to propose executable weakness features from contrasting successful and failed rollouts, automatically validates them on the diagnostic set, and selects the strongest validated weakness based on its success-rate gap. The validated weaknesses are then mapped to the environmental factors that control them. WEDGE varies these factors to construct environments in the difficulty regimes where the policy struggles, producing targeted training experience for adaptation. Across three navigation agents with different adaptation mechanisms, we find that policies exhibit distinct weakness profiles and benefit from different training environments. Weakness-conditioned adaptation consistently outperforms matched random and hard-example alternatives on ProcTHOR, while the resulting gains for Uni-NaVid and Gemini also extend to HM3D after ProcTHOR adaptation. Iterative re-diagnosis further shows that dominant weaknesses can persist or shift as the policy improves, providing updated guidance for subsequent environment construction. Together, these results show that policy failures are not only diagnostic signals, but actionable guidance for constructing training environments that target a policy's current weaknesses.

---

### WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding

Authors: Chenxu Wang, Hangyi Kuang, Bo-Wen Yin, Yuxuan Li, Quan-Sheng Zeng, Yang Zhang, Xu Guo, Xiang Li, Qibin Hou
Published: 2026-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.19419v1

MLLM-based detectors formulate vision-language grounding as autoregressive coordinate generation, yet in dense scenes, they often collapse into a box repetition loop, repeatedly emitting identical boxes until the decoding budget is exhausted. We trace this failure to historical-answer attention takeover: Under full-history autoregression, repeated coordinate tokens in the growing answer history attract disproportionate attention, crowding out the attention sinks needed to attend to new visual evidence. % To break this loop, in this paper, we propose \textbf{Compressed Window Auto-Regression} (WinAR). This new mechanism partitions a long answer sequence into consecutive generation windows and restricts full token-level autoregression to the current window only while compressing each previous window into a fixed set of latent tokens that condition subsequent decoding. This design reduces the repeated exposure to raw historical coordinates that triggers the attention takeover, yet preserves cross-window dependencies essential for coherent multi-object generation. On RSDense, which contains 200-2,000 objects per image, our model WinARDet improves RexOmni F1-score (IoU=0.5) from 32.16 to 39.36 over the baseline, while reducing the redundancy rate from 35.48% to 13.00%. WinARDet also generalizes across decoding strategies and output formats, including parallel box decoding and polygon generation, providing a practical paradigm for long-horizon vision-language grounding across scene densities.

---

### Recursive Formation and First-Class Reuse of Compositional Capabilities

Authors: Hang Lin
Published: 2026-10-14
Categories: cs.PL, cs.AI
arXiv: https://arxiv.org/abs/2610.19414v1

We introduce FormCraft, a framework for representing acquired operations as first-class capabilities that can be recursively composed, directly invoked, and selectively retained in a persistent library through domain-specific verification. The framework separates capability well-formedness and public callability from later admission to persistent storage while preserving formation provenance and operational identity. We formalize recursive compositional closure over a uniform capability space and show that formed composites can be reused through the same public interface without re-forming their historical derivation. Experiments across continuous, discrete, propositional, and sequence domains demonstrate instance-independent reuse, independent checking, persistent acquisition, and reduced reuse-time search work under first-class exposure.

---

### W-JEPA: Wavelet Joint-Embedding Predictive Architecture for Wearable Activity Recognition

Authors: Yogesh Prabhu, Loki Natarajan, Jingjing Zou
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.19411v1

A major challenge in wearable device activity recognition is the heterogeneity across datasets in sensor placement, channel count, sampling rate and subjects. Moreover, the motion patterns that distinguish activities often appear as subtle, scale-specific variations within otherwise similar waveforms. As a result, raw signals are often ambiguous, and models trained on them tend to rely on cues specific to a particular sensor setup or participant, which limits both cross-dataset transfer and generalization to unseen participants. Addressing this requires representations that preserve such activity-relevant, scale-specific variation. We introduce W-JEPA, a self-supervised framework that exploits the multiscale structure of inertial motion and leverages a joint-embedding predictive architecture, by organizing windows into a fixed grid of wavelet tokens indexed by scale, sensor axis, and time. These wavelet tokens help expose activity-specific detail within broadly similar raw signals, and serve as the units of masked latent prediction. W-JEPA predicts masked token representations supplied by an exponential-moving-average (EMA) target encoder. Because recovering a masked token requires relating motion at one scale and axis to motion at other scales and axes, the model learns the cross-scale, cross-axis structure of human movement. Across six wearable activity benchmarks, W-JEPA outperforms state-of-the-art methods under random-window splits and remains the strongest when subjects are held out, improving average macro-F1 by 8.7 percentage points over the strongest published baseline. These results indicate that physically grounded multiscale tokenization, combined together with latent predictive learning, provides a promising foundation for transferable representations of heterogeneous wearable inertial data.

---

### ForkGRPO: Efficient Exploration and Fine-Grained Credit Assignment for Diffusion Language Models

Authors: Zhaoyan Jia, Chengwei Zhou, Gourav Datta, Massoud Pedram
Published: 2026-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.19408v1

Diffusion large language models (dLLMs) have advanced rapidly, yet strengthening their reasoning through reinforcement learning (RL) remains an open challenge. Any-order generation can suffer from entropy degradation, which narrows the reasoning paths available for exploration. Recent work mitigates this issue by applying standard GRPO with left-to-right generation. However, independently generating every rollout from the input prompt can leave alternative continuations from intermediate states underexplored, while trajectory-level advantages assign uniform credit to all tokens without distinguishing the contributions of individual reasoning segments. We propose ForkGRPO, an RL framework that couples efficient exploration with fine-grained segment-level credit assignment. It samples multiple continuations from high-entropy intermediate states along a reference trajectory, prioritizing textual boundaries and reusing shared prefixes. The continuations provide complementary learning signals: within-state group-relative advantages guide which continuations to reinforce, while Monte Carlo state-value differences indicate which reasoning segments improve expected outcomes. Among the evaluated architecture-preserving RL methods, ForkGRPO achieves the best performance on three of four benchmarks, while improving over the directly comparable JustGRPO by up to 1.2 percentage points and using up to 27.8% fewer generated tokens. ForkGRPO-Fast further achieves a $2.49\times$ training wall-clock speedup with negligible accuracy loss.

---

### Vision-Language Models Integrate Conflicting Evidence Like Biased Bayesian Observers

Authors: Josh Barua, Kyle Mahowald, William Rudman
Published: 2026-10-14
Categories: cs.CL, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2610.19407v1

Vision-language models must reconcile conflicting text and images. Prior work has characterized the resulting behavior in terms of modality biases--e.g., a "blind faith in text"--but why preferences vary across models, domains, and input conditions remains unclear. We develop a predictive account from a Bayesian perspective, positing that VLMs combine conditionally independent evidence from each modality with prior beliefs, subject to modality-specific biases. The resulting two-parameter cue combination model accurately predicts VLM preferences under unseen combinations of input degradation and transfers to new forms of unreliability without refitting. Separating evidence strength from integration bias explains how VLMs can follow text even while weighting visual evidence more heavily, reconciling reports of text and vision dominance under a single combination rule.

---

### Scaling LLM Inference via Parallelism: Throughput-Latency Trade-off

Authors: Javad Mirzaei, Jeebak Mitra
Published: 2026-10-14
Categories: cs.DC, cs.AI, cs.LG, cs.PF
arXiv: https://arxiv.org/abs/2610.19405v1

Large Language Model (LLM) serving systems must balance latency and throughput while efficiently utilizing distributed GPU resources. This challenge arises because inference consists of two fundamentally different phases: prefill, which determines time-to-first-token (TTFT), and decode, which determines inter-token latency (ITL). The use of tensor parallelism (TP), pipeline parallelism (PP), and hybrid configurations exposes different trade-offs between these latency dimensions, making the optimal parallelism configuration highly dependent on workload characteristics, latency requirements, and context length. Moreover, despite the widespread adoption of distributed inference, there is still limited understanding of how parallelism configurations should be selected under varying workload conditions and service-level objectives (SLO). In this paper, we develop a systematic framework for characterizing LLM inference parallelism via throughput-latency trade-offs, SLO-aware serving, and long-context scalability. We introduce the notion of parallelism operating regions by constructing TTFT-ITL feasible sets and Pareto frontiers across different workload compositions, thereby revealing a systematic transition from TP-dominant to PP-dominant configurations as workloads become increasingly prefill-heavy. We further formulate SLO-aware parallelism selection using goodput, showing that stringent TTFT requirements favor PP-dominated configurations, whereas relaxed latency constraints progressively shift the optimality toward TP-dominated configurations with higher serving capacity. Finally, we demonstrate that increasing context length fundamentally changes the relative advantages of parallelism configurations, with PP-dominant configurations exhibiting more favorable scalability and SLO attainment in the long-context regime.

---

### ActMOF: Mapping Reticular Synthesis through Active Learning

Authors: Hongrui Sheng, Shutian Liang, Reid A. Coyle, Shyam Chand Pal, Peter Walther, Bin Feng, Xinyu Ding, Zhiling Zheng
Published: 2026-10-14
Categories: cond-mat.mtrl-sci, cs.LG, physics.chem-ph
arXiv: https://arxiv.org/abs/2610.19404v1

Reticular chemistry allows metal-organic frameworks (MOFs) to be designed from their building units, yet their synthesis remains constrained by sparse experimental data, noisy crystallization outcomes, and the absence of benchmarks for comparing active-learning strategies. While data-driven approaches such as Bayesian optimization (BO) can improve synthesis success rates, selecting appropriate optimizers beforehand for mapping MOF crystallization landscapes remains largely empirical. Here we present ActMOF, an experiment-grounded benchmark for comparing search strategies in aluminum-carboxylate MOF synthesis. ActMOF is emulated from experimentally measured microwave syntheses with each encoded condition assigned a crystallinity index calculated based on diffraction peak intensity and full width at half-maximum. By benchmarking policies guided by Gaussian processes (GP), tree ensembles and large language models (LLM), ActMOF placed the GP family among the leading policies for active learning in sparse synthesis landscapes. It then demonstrated transferability by guiding the microwave synthesis of six reticularly related aluminum MOFs. All six campaigns gave crystalline products within a fixed budget of 12 experiments each, and established a reusable testbed for AI-driven MOF synthesis.

---

### Train to Stitch: Topology-Preserving Regularization for Interoperable Representations

Authors: Akshay Malhotra, Nicolas Zilberstein, Shahab Hamidi-Rad
Published: 2026-10-14
Categories: cs.LG, cs.CV, eess.SP
arXiv: https://arxiv.org/abs/2610.19401v1

As large, powerful pre-trained models become more prevalent, there is growing interest in developing methods that allow different neural networks to be seamlessly combined with little or no direct communication between them. Take autoencoder-based data compression as an example: the ability to independently choose architectures and train encoder and decoder models, while still ensuring they work together, could fundamentally transform how such models are built, deployed, and updated. In this work, we introduce a novel approach that leverages topological regularization to align the latent spaces of two independently trained autoencoder models, entirely eliminating the need for coordination during training. We provide a conditional theoretical analysis showing how the structural agreement encouraged by our regularizer can translate into approximate geometric compatibility between independently learned representations. Reconstruction experiments validate this approach empirically, substantially narrowing the interoperability gap across multiple datasets.

---

### KoAGE: Do Large Language Models Know, Learn, and Coin Korean Neologisms?

Authors: SungHo Kim, Eojin Jeon, SangKeun Lee
Published: 2026-10-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.19399v1

Korean neologisms arise through diverse mechanisms, a demanding test of language models beyond lexical memorization. To enable systematic evaluation, we introduce NeoTrace, an automated, rerunnable framework that collects and dates neologisms across genres. Its 4,271 entries support KoAGE, a cutoff-aware benchmark with three acquisition and two generation tasks---the latter, to our knowledge, the first to compare model coinages with attested neologisms under their original materials and community context. Across 21 models, lexical recall diverges from contextual inference: in a five-model temporal analysis, models define only 13-30% of cutoff-year words, yet can infer meaning from one usage. However, structural understanding remains limited: even correct definitions barely improve formation analysis of pre-cutoff neologisms. Given word-building materials, single models often follow human formation mechanisms, whereas multi-agent coinage favors abbreviation and depends on interaction framing. KoAGE thus separates what models know, learn from use, and coin.

---

### SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning

Authors: Dingyi Rong, Yue Shi, Chaofan Ma, Zongrui Wang, Jiezhang Cao, Yixin Cao, Liang He, Ning Liu
Published: 2026-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19397v1

Long-horizon agentic RL is constrained by the futures visited by the current policy. When rollouts fail to reach useful behaviors, improved credit assignment cannot provide supervision for states and actions that were never encountered. On-policy distillation (OPD) introduces teacher guidance on policy-induced states, and recent multi-turn variants improve how this guidance is scheduled, replayed, refined, or validated. However, they do not directly use the oracle-controlled future itself as the training trajectory. We introduce \textbf{State-Rooted Executable Rollout Optimization (SERO)}, which augments on-policy agentic RL with executable oracle continuations. SERO restores a state actually reached by the current policy and lets a training-only oracle continue interacting with the real environment, making the downstream observations and oracle actions themselves available for learning. It then applies \textbf{policy-reachability weighting}, which weights each oracle step by the frozen behavior policy's compatibility with the preceding oracle actions. This allows deeper supervision to become effective as the policy becomes more compatible with the oracle branch. The oracle loss is optimized separately from the base RL estimator and no oracle is used at inference time. We evaluate SERO on two challenging interactive-agent benchmarks, ALFWorld and WebShop, using Qwen2.5-1.5B-Instruct and Qwen2.5-7B-Instruct. On ALFWorld, learning the full executable continuation is substantially more effective than supervising only the root oracle action, while policy-reachability weighting further improves out-of-distribution performance.

---

### EpiGuard: An Autonomous Infectious-Disease Early Warning Agent Platform

Authors: Tonglong Wei, Zheng Yuan, Lingshuai Lin, Yuhui Yao, Xing Xie, Na Zou
Published: 2026-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19396v1

Infectious disease outbreaks often spread rapidly before signs of widespread transmission become apparent, leaving a big challenge for rapid response and effective intervention. However, current infectious-disease early-warning systems face three major challenges: fragmented epidemiological evidence across diverse surveillance sources, highly uneven data availability across diseases and geographic regions, and delayed warning procedure caused by manual data collection, analysis, and reporting. To address these challenges, we present EpiGuard, an autonomous, continually self-improving agentic platform for timely and reliable early warning of more than 50 infectious diseases across different regions. EpiGuard proactively monitors and captures newly released official surveillance records, using the latest available evidence for risk assessments. It dynamically adjusts its analytical strategy across three evidence availability regimes, enabling reliable risk assessment under diverse data conditions, ranging from the absence of historical observations to sparse and abundant evidence. Moreover, EpiGuard learns from the successful execution process by preserving effective data-acquisition and analytical procedures as reusable standard operating procedures, enabling it to progressively generalize to previously unseen diseases and regions. We use officially released infectious-disease surveillance data from the China CDC and the United States CDC to evaluate EpiGuard's effectiveness. Experimental results demonstrate that EpiGuard outperforms state-of-the-art forecasting systems, improving forecasting performance by 9.68% and 14.04% on the China CDC and U.S. CDC datasets, respectively.

---

### Selective Next-Location Prediction with MetaModelSelect: A Lightweight Post-Hoc Confidence Metamodel

Authors: Calvin Jary, Nafiseh Kahani
Published: 2026-10-14
Categories: cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2610.19394v1

Next-location prediction can support proactive mobile-network decisions, but acting on unreliable predictions can waste resources. We apply MetaModelSelect, a lightweight post-hoc confidence metamodel, to selective cellular next-location prediction. The mobility-specific model combines a learned embedding of the predicted location with the four largest softmax probabilities and Softmax Concentration. It learns whether a frozen recurrent neural network's top-1 prediction is correct, using only its outputs and without retraining the backbone. On path-balanced Changchun cellular mobility trajectories, we evaluate backbones trained with cross-entropy (CE) and self-adaptive training plus entropy minimization (SAT+EM), comparing against eight scalar confidence scores, two location-aware lookup methods, and a raw-logit multilayer perceptron. Relative to maximum softmax probability, MetaModelSelect achieves mean per-run reductions in area under the risk--coverage curve (AURC), excess AURC (E-AURC), and area under the generalized risk--coverage curve (AUGRC) of 2.6%, 4.2%, and 3.0% for CE, and 2.0%, 3.3%, and 1.9% for SAT+EM. It also achieves the lowest reported mean risk at every evaluated partial coverage. The results show that MetaModelSelect improves confidence ranking in this mobility setting while leaving the underlying location predictor unchanged.

---

### Fully sequential Gaussian process regression for preference learning

Authors: Ilya O. Ryzhov
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.19391v1

We study continuous global optimization problems in which the objective function cannot be directly evaluated; rather, we observe only which of two selected design points appears to perform better, subject to noise. Such comparisons complicate the use of Gaussian process regression because they yield non-Gaussian posteriors. We consider a fully sequential approximation, based on moment-matching, that yields a fast closed-form update of the metamodel's mean and covariance. We then propose DOVE, a fully sequential sampling policy that combines an information gain criterion with randomized sampling designed to control error accumulation. Under fairly standard regularity conditions, we prove convergence rates for both statistical error and expected simple regret that depend on kernel smoothness. To our knowledge, these are the first such rates for fully sequential approximate Bayesian inference in continuous global optimization.

---

### ELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologies

Authors: Sangmin Lee, Yejin Jeon, David Ifeoluwa Adelani
Published: 2026-10-14
Categories: cs.CL, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2610.19388v1

Massively multilingual speech modeling has made remarkable progress in recent years, yet existing training resources and benchmarks still underrepresent much of the linguistic long tail. To address this gap, we introduce ELARSpeech, a large-scale multilingual speech resource comprising 30,202 hours of speech across 675 underrepresented languages, curated from the Endangered Languages Archive. Combining human-annotated and unlabeled recordings, the corpus spans diverse recording conditions, domains, and language families. Beyond corpus construction, our experiments show how ELARSpeech supports extending ASR and TTS capabilities to diverse underrepresented languages, with further benefits from pseudo-labeling unlabeled data. At the same time, our speech representation analysis reveals remaining limitations in transferring existing multilingual models to the linguistic long tail. Together, ELARSpeech provides both a resource and a testbed for extending multilingual speech technology further into the linguistic long tail. We publicly release the dataset, all trained ASR and TTS models, and the complete data construction pipeline to facilitate research on long-tail multilingual speech technologies.

---

### The Sum of All Summaries: PROPALIGN for Graded Proposition Salience Evaluation

Authors: Lin Ai, Emma Thronson, Katherine Conhaim, Amir Zeldes
Published: 2026-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.19387v1

Identification and ranking of salient propositions in documents is indirectly involved in many AI tasks, but few papers define proposition salience scores clearly, make diverse data available, or evaluate models directly on the task. This paper proposes PROPALIGN, a multiple-summary-based approach for propositional salience score estimation, and releases PROPALIGNBANK, an accompanying dataset for the method with 138K alignments of over 35K propositions. We compare several approaches to salient proposition extraction in English across a broad range of spoken and written genres, and demonstrate that naively asking models for judgments leads to inconsistencies. By contrast, graded, summary-based metrics are more stable. We further observe that while single models perform worse than humans, an ensemble of models incorporating linguistic features approaches manual annotation quality ceilings. In addition, analyses of the model outputs suggest insights into how models can extract salient information with and without the use of summaries.

---

### STRATA: Self-Maintaining Structured Experience Graphs for Self-Evolving Language Agents

Authors: Guanhua Zhu, Hanwen Li, Zhi Wei, Mengnan Du, Chenxi Yuan
Published: 2026-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19386v1

Large language model (LLM) agents can self-evolve at test time by accumulating experience: retrieving relevant memories before acting and writing new lessons back afterwards. Yet most are single-level: trajectories, distilled workflows and reasoning items all land in one undifferentiated pool indexed by embedding similarity, with no typed abstraction hierarchy. They never forget or deduplicate, and are prone to negative transfer, where a superficially similar but directionally opposite experience is recalled and its concrete steps are copied verbatim, actively harming the agent. We introduce STRATA, a structured, outcome-grounded, self-maintaining memory that organizes experience into a three-layer graph of atomic skills and code snippets, task workflows and generalized meta-frameworks, connected by typed edges. STRATA maintains itself through five mechanisms sharing one similarity geometry: a multi-dimensional similarity that scores retrieval by operation and target; a typed reflector crystallizing procedures from successes and pitfalls from failures; community detection that induces meta-frameworks; pressure-triggered garbage collection with articulation-point protection; and contrast edges that flag confusable, direction-opposite experiences. Across four interactive benchmarks (AppWorld, WebArena, ALFWorld, ScienceWorld), two frozen backbones and seven baselines, STRATA attains the best average score while simultaneously using the lowest latency and fewest environment steps of any memory-augmented method, and 44% fewer lines of injected memory than the most context-hungry baseline. We isolate two failure modes of prior memories: single-level memory degrades sharply as the task set grows, and single-level concrete memories suffer catastrophic negative transfer, which contrast edges repair, lifting ScienceWorld from 78.7 to 96.7 within the same system.

---

### RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning

Authors: Zinan Ling, Yang Xiao, Ruimeng Ye, Sijia Liu, Bo Hui
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.19385v1

Large Language Model (LLM) unlearning is often evaluated primarily by target suppression and clean retain utility. These metrics can miss a local failure mode: a model may perform well on standard retain prompts, yet degrade on benign reasoning when prompts lie near the forgotten domain. This phenomenon is termed forget-adjacent utility loss. A fundamental question is: where should forget representations go after they leave the removed behavior? Successful unlearning depends not only on whether forget-conditioned representations depart from the harmful computation, but also on the direction in which they are redirected afterward. We propose RA$^2$ (Retain-Anchored Attraction), a latent-space unlearning method that redirects forget-token states toward nearby retain-supported representations while preserving higher-layer behavior on retain data. On WMDP and MUSE, RA$^2$ yields higher forget-adjacent utility than strong unlearning baselines at similar broad-utility levels. These results show that the migration direction of forget representations materially affects benign behavior near the forget boundary. Our code is available at https://github.com/ZacLing/retain_anchored_attraction.

---

### ixi-sLM: On-Device sLM for AI Call Agent Service

Authors: Han-Sang Lee, Kyuho Lee, Juneyoung Park, Seongbae Lee, Jin Kyu Park, Minjae Kim, Yuri Hong, Jinwoo Lee, Youngwook Kwon, Seongwan Kim, Seungheon Hyeon, Jaeho Lee et al.
Published: 2026-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19382v1

Running an AI call agent on-device makes it private, network-independent, and free of per-query cloud cost, but shipping one as a real-world service imposes constraints a cloud deployment never faces: ~1GiB memory budget, in-call latency and thermal limits, static-integer NPU execution, Korean STT input far from sLM pretraining, and cloud-level quality expectations. We bring ixi-sLM, a 1.2B Korean sLM, to mobile NPUs through ON-DEVICE MODELING: domain-adaptive modeling trims the vocabulary by call frequency to shrink the embedding and LM head that take nearly half the model under INT4 transformer weights and refits the tokenizer to call speech (18% fewer tokens on call traffic), while task-aware quantization calibrates on real calls and assigns per-module mixed precision by activation sensitivity. A single domain-adapted model runs ixi-O's two production services, AI Call Summary and AI Call Answering, at 94% of a state-of-the-art cloud LLM's task-weighted quality; our on-device modeling carries that quality onto the NPU with only a marginal drop in overall score, in an 803MiB model (28% of FP16) at 23% of the CPU's per-call energy. The same recipe deploys across Qualcomm and Apple NPUs and serves several million ixi-O subscribers in production.

---

### EvoWeave: Composing Reusable Agent Experience through Operation Level Graphs

Authors: Guanhua Zhu, Bo Shen, Lei Zhang, Fadi Deek, Zhi Wei, Mengnan Du, Chenxi Yuan
Published: 2026-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19381v1

Different tasks often require interactive agents to perform similar operations at intermediate steps. Retrieving an entire past workflow can introduce irrelevant steps, whereas retrieving isolated operations can discard the dependencies needed to reuse them. We introduce EvoWeave, a framework for experience memory that represents abstract states as nodes and reusable operations as directed edges with input and output contracts, provenance, and capability references. A planner decomposes the current task into a dependency graph; operation retrieval and bounded directed search then assemble relevant experience fragments. An execution agent can inspect these fragments and their referenced capabilities, while reflection separates concrete execution evidence from reusable abstractions. We study the framework across four benchmarks, five evaluation settings, and three language model backbones. Across backbones, AppWorld Normal and Challenge task goal completion average 51.91 and 27.99, respectively, exceeding the baseline without memory by 6.99 and 4.99 percentage points. An AppWorld ablation associates directed connections with an additional improvement of 2.08 points over independent operation cards. The results motivate composition of reusable operations while exposing tradeoffs in retrieval overhead and conditions for valid reuse.

---

### Learning What to Keep: Transfer-Aware Personal Skill Learning from User Feedback

Authors: Li Wang, Chen Zhang, Yirong Yang, Xingyu Chen, Jinkun Zhao, Tianhao Peng, Wenjun Wu
Published: 2026-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.19380v1

User feedback enables LLMs to refine reusable personalized skills, but often mixes persistent preferences with request-specific corrections. Indiscriminately retaining both risks negative transfer, motivating selective retention at the level of individual requirements. We frame this challenge as selective transfer over atomic rules and propose SkillGrain, a framework for learning reusable personalized skills from user feedback. SkillGrain decomposes feedback into independently actionable rules, predicts their transferability, and retains only those suitable for future requests. To learn these decisions, we combine rubric-guided skill rewards with fine-grained credit assignment that separately evaluates rule content and retention decisions. We further jointly optimize skill induction and skill-conditioned generation through reinforcement learning, ensuring that learned skills support downstream personalization. We construct a benchmark spanning five personalized writing tasks to evaluate cross-request generalization. Experiments across three base models in both in-domain and out-of-domain settings show that SkillGrain achieves the best overall average performance among competing methods.

---

### Robust Explanatory Analysis for Structured Optimization Networks (REASON) in Learning

Authors: Vahid Jebraeeli, Hamid Krim, Keisuke Fujii
Published: 2026-10-14
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2610.19378v1

We seek a hierarchical resolution of residual error under a composite learning objective as a principled mechanism for identifying and exploiting additional information, particularly under distribution shift and perturbation. Inspired by the System 1/System 2 paradigm, we formulate this principle as a two-loop mechanism serving a common inference goal. A fast, System 1-like loop resolves the residual addressable by the available evidence; the remaining epistemic residual triggers a medium speed, System 2-like loop that actively acquires additional evidence and measures its informational value through residual reduction. Over nested solution spaces, the medium-loop optimum is provably no worse than the fast-loop optimum. Experiments show that the resulting two-loop model consistently improves upon the fast loop at approximately half the computation of the medium loop, including under unseen corruptions, and, when provided a cleaner observation, outperforms staged classifiers and learning-to-defer methods at equal computational cost.

---

### DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents

Authors: Tianle Chen, Pushkar Singh, Ketan Todi, Biswajit Paria, Qijia He, Wenqi Wang, Yuwen Tan, Jike Zhong, Sugato Basu, Deepti Ghadiyaram, Arjun Akula
Published: 2026-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19376v1

Language-model agents that run long tasks often redo work they have already done: they re-issue a tool call they made earlier and get back exactly the same observation, a step that adds no new information. We identify this failure as a loop. Loops appear natively in Qwen, Llama, and Gemini agents and become far more common once the agent's history is compressed to fit its context window. To reduce these loops, we propose DeLoop, a self-supervised training method. DeLoop builds on a simple observation: the agent's own rollout can provide the supervision needed to learn from its loops. We use a looping action as a negative example and the first later non-looping action in the same rollout as a positive example. DeLoop learns from these pairs through direct preference optimization and does not require task rewards, gold answers, or LLM judges. On CodeGym under compression, DeLoop reduces the share of Qwen3-8B tasks containing loops from 57.3% to 6.1%. It also uses about one third as many steps per task, with similar task success. On Qwen3-32B, DeLoop reduces loops and steps while raising task success from 37.7% to 44.8%.

---

### One-Step Prediction Fidelity Is a Poor Proxy for Planning Performance in JEPA World Models

Authors: Joshua Cheung, Zhang He
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.19375v1

Latent world models are routinely selected, checkpointed and ablated on one-step prediction loss, on the assumption that a model which predicts the next latent better is a better model. In model-based RL this assumption is known to be unreliable; we ask whether it also fails for latent world models, where the training target is the model's own embedding and the loss is not expressed in interpretable units. We introduce a frozen-decoder protocol reporting one-step error in physical units, decomposed into the part already present in the encoder's representation and the part the predictor adds. Applying it to a recent end-to-end JEPA world model across three continuous-control environments, we move the metric by fine-tuning and measure goal-conditioned planning on the same checkpoints, with three training seeds and paired planning seeds throughout. Within one environment, a per-epoch ladder shows the relationship saturating after a single epoch: the first epoch improves fidelity by 32% and planning by 4.4 pp, but across the fifteen checkpoints that follow -- a further 15% fidelity improvement, monotone in every training seed -- the correlation between one-step error and planning success is r = -0.010. This is not a task-ceiling artifact: stratifying by a model-independent measure of training-data support, planning in the lowest-support stratum starts at 80%, leaving ample headroom, and is nonetheless flat from epoch 1 onward. Across environments the exchange rate is equally unstable: a 93% fidelity reduction on TwoRoom yields -0.7 pp of planning, while a 40% reduction on PushT yields +4.9 pp (+1.1, +8.9). All results replicate under a decoder-free measure, latent drift. We also show that a matched continued-training control absorbs the entire fidelity gain we had attributed to an auxiliary objective.

---

### Evaluating Compressed Memory: Dependence, Utility, and Content Benefit

Authors: Minsu Oh, Seunghui Jwa, Chanjun Park, Yeo-Chan Yoon
Published: 2026-10-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.19373v1

Does a language model answer better because its compressed memory contains useful document information? Replacing memory vectors with zeros can lower a trained model's score without showing that it outperforms a model trained without memory. We combine zeroing with separately trained models that cannot access stored text or receive the same constant input for every document. Across nine systems, some models rely on memory yet perform worse than the trained alternative. For example, in experiments that predict states in generated stories, zeroing memory worsens a model's prediction loss, yet a model trained without memory achieves lower loss than the original model with intact memory. On TriviaQA, giving xRAG memory from another question's passage raises F1, which measures word overlap with accepted answers, from 19.38 without a document to 24.78. Its effect on how often outputs contain an accepted answer is statistically uncertain. The question's retrieved passage scores higher still (29.88 F1). Thus a gain over no document alone does not establish that the gain requires the question's passage. Evaluations must therefore specify the comparison model, absolute performance, and generation and scoring conditions.

---

### Policy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy Rewards

Authors: Min-Young Yu
Published: 2026-10-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.19372v1

Runtime policy verifiers can prevent agents from executing disallowed actions, but their decisions are typically used only for enforcement and discarded afterward. We ask whether these decisions can instead become verifiable policy rewards for training the agents they guard. We introduce Policy-Verified Self-Training (PVST), a post-training paradigm in which an agent generates its own interaction trajectories and an executable policy verifier, here a deterministic gate compiled from a written policy, evaluates whether each action complies. Compliant trajectories are reinforced, and violations become negatives for preference optimization; beyond the gate and the benchmark's task-success signal, PVST needs no stronger teacher model, no human preference labels and no attack-specific supervision, although rollouts are collected in the benchmark's attacked environment. On held-out AgentDojo tasks under prompt injection, policy-verified preference training of Qwen3-8B reduces violating trajectories from 37.2% to 10.3 $\pm$ 0.9% (three seeds) and successful attacks from 12.4% to 0.5% at equal or higher pooled task utility, although utility falls on travel, compared with 22.0% when negatives are selected by an attack oracle and 31.9 $\pm$ 0.9% with negatives that contain no violation. The learned behavior holds under an attack template never used in training (37.7% to 11.0%) and on a suite excluded from training (34.8% to 16.7%), and the retained verifier's intervention rate falls from 39.2% to 8.8% (seed 0). Our analysis identifies two conditions under which the verdict is most informative: success must not already imply compliance, and guarded actions must appear in both permitted and forbidden contexts.

---

### The Impact of Detector Architecture, Model Scale, and Scene Density on Multi-Pedestrian Tracking

Authors: Pedro Manoel Herminio Alves, Dalton Cézane Gomes Valadares, Cláudio de Souza Baptista
Published: 2026-10-14
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.19369v1

Pedestrian tracking in video is important for applications such as surveillance and scene analysis, but it becomes more challenging in crowded scenarios with frequent occlusions and rapid motion. This paper analyzes how detector architecture, model scale, scene density, and inference regime affect the tracking of multiple pedestrians. We compare the YOLO11, RT-DETR, and YOLO26 detector families with the ByteTrack and BoT-SORT trackers on sequences from the MOT17, MOT20, and SOMPT22 benchmarks. For YOLO26, we also compare traditional overlap filtering via Non-Maximum Suppression (NMS) with end-to-end inference. The RT-DETR family achieved the highest mean scores on the HOTA tracking quality metric across all three benchmarks with both trackers, with a more pronounced advantage on MOT20, albeit at a higher computational cost. On MOT17 and SOMPT22, YOLO26 variants, especially YOLO26-L with NMS, offered favorable combinations of quality and speed compared with RT-DETR. In the YOLO26 inference comparison, the end-to-end mode did not yield consistent tracking gains over the NMS-based regime. Taken together, these results provide a practical guide for selecting detectors and trackers for this task based on application priorities.

---

### Beyond Corrected Actions: Training LLM Agents on Textual Critiques

Authors: Thomas Zeng, Zelei Cheng, Mingyang Zhou, Sambit Sahu, William Campbell, Genta Indra Winata
Published: 2026-10-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.19367v1

Large language models (LLMs) are increasingly used for multi-turn agentic tasks that require interactions with users and environments over extended sequences of actions. A common approach to improving LLM agents is to use more capable expert models to provide training supervision, either by behavior cloning the expert's trajectories or by using the expert to correct the actions in trajectories generated by the weaker student model. However, expert LLMs can provide richer supervision than actions alone: they can directly generate textual critique that explain why specific actions are incorrect. We study whether training on such feedback benefits LLM agents and propose Critique-Augmented Agentic Fine-Tuning (CAFT), a framework that elicits textual expert feedback on student-generated trajectories. For each incorrect action, the expert yields both a corrected action and a textual critique explaining the student's mistake--which we then use as the training target for fine-tuning. Across four student models from the Nemotron 3 and Gemma 4 families on the agentic domains $τ^2$-Bench Airline+Retail and WebShop, adding critiques to action-level supervision improves performance by 8% on average over action-only distillation. Additionally, CAFT checkpoints can also provide a better warm start for reinforcement learning than expert-trajectory distillation. Our results demonstrate that textual critiques can strengthen supervision for multi-turn LLM agents.

---

### Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory

Authors: Minghao Guo, Qingyue Jiao, Xiujin Liu, Jianhong Pang, Ruimeng Yang, Naihao Xu, Liwei Che, Haochen Xue, Ziqi Wang, Xinying Cai, Jiaxuan Luo, Jiaxin Deng et al.
Published: 2026-10-14
Categories: cs.AI, cs.CL, cs.RO
arXiv: https://arxiv.org/abs/2610.19366v1

Multimodal models and agents have emerged to enable AI systems to learn from and interact with the real world more like humans by integrating information across multiple modalities. However, enabling multimodal agents to continually acquire useful information from complex, heterogeneous multimodal data remains a significant challenge as they move toward long-horizon tasks and lifelong settings. Addressing this challenge requires effective memory mechanisms that can maintain continuity across sessions, adapt to changing users and environments, and refine memory-management policies through accumulated experience. We introduce a two-axis analytical framework for multimodal agent memory structured around two key questions: how multimodal information is formed and represented (Axis I, Formation and Representation), and how its management adapts with accumulated experience (Axis II, Memory Management). Axis I, Formation and Representation, characterizes what information is retained and how it is encoded (e.g., modality-specific embeddings, textual and structured records, latent and parametric representations) to support subsequent reasoning and action. Axis II, Memory Management, distinguishes three tiers: T1 Static Memory reuses fixed memory; T2 Dynamic Memory updates memory through a stable policy; and T3 Self-Evolving Memory updates memory through an evolving policy. Based on this framework, we synthesize recurring design patterns and derive principles for balancing source fidelity with abstraction, maintaining temporal validity and provenance, grounding memory use in recoverable evidence, and evolving memory policies over time. Furthermore, we discuss the challenges and potential future directions for the memory mechanism of multimodal agents.

---

### DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment

Authors: Tianzhuo Yang, Shaoheng Yan, Lin Lu, Jiawei Chen, Kaile Wang, Fanyu Meng, Minglu Liu, Yaodong Yang
Published: 2026-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19365v1

Safety alignment teaches language models to refuse harmful requests, yet the internal accessibility of hazardous concepts can retain traces of earlier training. Can checkpoints with equally safe behavior differ in what remains accessible behind their refusals? In this work, we investigate this question through paired training histories and a direct audit of intermediate representations. We introduce DANGERLENS, a probe that maps hidden states into vocabulary space and uses blinded semantic judgments to distinguish harmful goals and operational means from hazard recognition and safety control. Experiments on three Qwen1.5 scales show that checkpoints with prior harmful exposure generally retain greater hazardous concept accessibility after the same safety alignment, with the strongest separation in intermediate and later layers. The same harmful update also produces different behavioral trajectories from closely matched starting points. Human relevance validation and readout ablations reinforce the measured accessibility contrast. Our findings show that training history remains visible inside behaviorally matched models and motivate internal accessibility audits alongside output safety evaluations.

---

### Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context

Authors: Bo Li, Yue Yang, Yujin Huang, Siao Liu, David Lemphers, Sara E Rodriguez Gomez, Luke Borgnolo, Can Wang, Xin Zheng
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.19364v1

Dynamic graph learning models how entities and their relations evolve from historical observations to predict future graph states. Existing methods do not fully address dynamic graph world modelling, which requires learning transitions from temporal context to future latent graph states. This is difficult for three reasons: nodes and relations rely on different historical evidence, structural evolution is path-dependent, and future snapshots provide sparse and realization-specific targets. We propose Dynamic Graph World Modelling (DyG-WM), the first framework to jointly predict future node and relation representations from temporal context by answering three questions: what has evolved, how it evolved, and what will evolve next. To capture what has evolved, a historical node-relation context encoder summarizes node-neighborhood trajectories and pair-specific histories. To characterize how it evolved, a node-relation path-signature encoder captures ordered structural changes. To predict what will evolve next, a dual-level joint-embedding objective predicts target-snapshot node and relation representations without reconstructing the raw graph. Experiments on 12 link-prediction and two node-classification datasets demonstrate the effectiveness of DyG-WM across both tasks.

---

### Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems

Authors: Taro Yano, Yoichi Ishibashi, Masafumi Oyamada
Published: 2026-10-14
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.19362v1

Best-of-N sampling is a simple inference-time scaling strategy for large language models, yet its behavior under incomplete reward models remains poorly understood. We study Best-of-N as a competition between the extreme reward tails of correct and incorrect responses. This view shows that success depends not only on the probability of sampling a correct response, but also on whether correct responses dominate incorrect ones in the upper tail. Using extreme value theory, we characterize three asymptotic regimes: correct-tail-dominant, incorrect-tail-dominant, and critical explaining both monotonic gains and reward-hacking-induced degradation. We further derive finite-sample scaling laws for representative reward distributions, showing that, under Gaussian rewards, incorrect responses with sufficiently large variance can dominate selection even when their mean reward is lower. Unlike oracle selection, convergence with an incomplete selector can be polynomial rather than exponential. Finally, we propose a lightweight tail-tension criterion to estimate when additional sampling may become harmful. Experiments on synthetic data and real reward model scores are consistent with the theoretically predicted regimes, scaling laws, and diagnostic behavior, suggesting that tail competition provides a unified lens on Best-of-N sampling for verifiable problems.

---

### VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement

Authors: Kyusong Lee, Heting Ying, Tiancheng Zhao
Published: 2026-10-14
Categories: cs.CV, cs.CL, cs.RO
arXiv: https://arxiv.org/abs/2610.19361v1

Embodied visual tracking requires a robot to identify a designated target from visual observations and control its own motion to follow that target through an environment. Following an isolated person is a comparatively simple demonstration of embodied visual tracking, but following the intended person among distractors remains challenging. Existing methods exhibit a substantial drop in success from single-target to distractor tracking, motivating a focus on the shared spaces that person-following robots must navigate. We present \method{}, a vision--language waypoint policy built around the hypothesis that visual and language representations should be aligned before tracking-specific motion is learned. The policy combines complementary frozen visual encoders, multiscale temporal context, a transformer backbone, and a lightweight head for robot-centric waypoint prediction. Its training progresses through vision--language alignment, multimodal reasoning mid-training, and tracking specialization on 19,532 oracle episodes. Compared with 41.54\% distractor-tracking success for our earlier OmTrackVLA model, the complete multi-stage recipe achieves 55.80\%. We then explore on-policy refinement using filtered oracle labels for states visited by the policy. This preliminary study adds 2.42 percentage points of distractor-tracking success, reaching 58.22\%, while reducing collision rate by 1.99 pts. The final policy records the highest distractor- and ambiguous-tracking success rates among the compared methods. These results support staged multimodal learning as a promising direction for tracking among distractors and motivate further study of on-policy refinement for person following in shared spaces.

---

### Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering

Authors: Weilun Xu, Zipeng Sun
Published: 2026-10-14
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.19359v1

Activation steering adds a vector to a model's hidden states to control a named behaviour. A gain on that behaviour, however, does not show that the vector controls it directly: it may act through a component shared with neighbouring behaviours, which unsteered and random baselines cannot separate. We introduce the competing-target test: a vector is compared with the vector built the same way for a competing target, and an equivalence test states when their difference is below a useful margin. We apply it in open-weight models to vectors for Kantian deontology, which judges an act by the rule it follows, and act utilitarianism, which judges it by the welfare it produces. On held-out situations, prompting a framework raises its score and lowers the other's, whereas vectors for either framework move both scores alike, and none reaches the margin. The two vectors share most of their direction, a request to apply some framework; the same construction separates an optimistic from a pessimistic tone, whose vectors share much less. What a vector shares with its competitors therefore sets what it controls: steering a perspective can deliver a mixture, and measuring a disposition can measure its neighbours, unless tested against the competing target.

---

### Asymptotic Behavior of Transformers

Authors: Katy Blumer, Da-Cheng Juan, Jon Kleinberg, Ravi Kumar, Cyrus Rashtchian, Andrew Tomkins
Published: 2026-10-14
Categories: cs.LG, cs.AI, math.ST
arXiv: https://arxiv.org/abs/2610.19358v1

In this paper we study the behavior of transformer networks generating text over long periods of time. We show that even a three-token, single-layer attention-only transformer can fail to converge. We then study a rich class of transformers with arbitrary finite depth, layer normalization, MLPs, RoPE encodings, and an arbitrary mix of local and global layers. Every transformer in this class has a softmax temperature threshold above which its empirical cache distribution converges to a unique limit, independent of initial conditions. We show further that, while each transformer has a temperature threshold, the supremum of this set is infinite, so there is no global minimal temperature that forces all transformers to converge.

---

### BFHD: Bidirectional Feature Harmonization Decomposition for Heterogeneous Clinical Assessments

Authors: Yuanhao Zhuo, Zixi Qin, Ling Qin, Wanqing Li
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.19352v1

Clinical assessments are often collected using heterogeneous assessment systems across centers and time, leading to records that mix different but related sets of measurements. This motivates harmonization beyond total-score linking. We formulate clinical harmonization at the measurement level as a bidirectional recoverability problem: given paired observations from two assessment systems, the goal is to identify which measurements can be reliably translated in both directions within an application-defined tolerance, while separating non-translatable components. We propose Bidirectional Feature Harmonization Decomposition (BFHD), a feasibility-driven framework that enforces bidirectionally coupled translation and uses feature-wise output gating to produce an explicit decomposition in the original measurement space. Experiments on synthetic data and real clinical assessment pairs show that BFHD achieves broader feasible harmonization coverage and improved subset stability compared to baselines.

---

### Subdata Selection for Measurement-Constrained Linear Regression under Model Misspecification

Authors: Yundi Kong, Min Yang, Ping-Shou Zhong
Published: 2026-10-14
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2610.19351v1

In many modern applications, obtaining response variables is costly, time-consuming, or technically challenging, making it impractical to measure outcomes for all available units. In such settings, covariates may be available for a large pool of candidates, but responses can only be collected for a small, carefully selected subset, making the choice of which units to measure a consequential decision. Most existing subsampling methods are developed for massive datasets, emphasizing the trade-off between statistical accuracy and computational cost, and typically relying on the assumption of a correctly specified model. These features limit their suitability in measurement-constrained settings, where statistical efficiency is paramount and model misspecification is often unavoidable. To address these challenges, we develop a new subset selection framework for linear regression that accommodates potential model misspecification. The proposed approach targets predictive expected loss and yields an A-optimality-type criterion that depends only on covariate information, requiring no response observations at the selection stage. We refer to this method as Expected Loss Optimal Selection (ELOS). By focusing on predictive risk rather than model-based optimality, ELOS remains well-defined and robust under misspecification. Simulation studies and real data applications demonstrate that ELOS achieves strong predictive performance and compares favorably with existing methods across a range of scenarios.

---

### Where to Start, How to Move: Analyzing Curricula under GRPO for Long-Horizon LLM Agents

Authors: Minchan Kim, Sungho Bae, Youngjin Kim, Hyunwoo Park
Published: 2026-10-14
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2610.19349v1

Group Relative Policy Optimization (GRPO) provides no reward-relative learning signal when all rollouts receive identical rewards. In long-horizon tasks that require multiple interactions, rewards are given only upon successful task completion, making all-fail groups common early in training and limiting opportunities to practice later steps. Guide Assisted GRPO replays a successful reference prefix before the learner continues. We study how initial positions, handoff units, and movement rules affect unassisted task completion. Across three model sizes on BFCL, starting near completion is more effective under a fixed turn-level threshold rule. Finer handoffs alone do not consistently help, but outcome-informed tool-call selection outperforms GRPO on trained and untrained task categories. Guided starts also improve AppWorld success on both evaluation splits. These findings highlight where learning starts and how starting positions move as key curriculum choices.

---

### Integrated Novelty Detection Systems: From Sensor Networks to Multi-Novelty Computer Vision

Authors: Irené Tematelewo
Published: 2026-10-14
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2610.19347v1

Novelty detection is crucial in various technological and scientific domains. Its importance spans from ensuring the reliability of sensor networks to enhancing the adaptability of computer vision systems. As AI systems become increasingly sophisticated and complex, effective anomaly detection is essential for maintaining reliability and accuracy. This work addresses novelty detection in weather sensor networks and computer vision. In weather sensor networks, particularly for monitoring rainfall, detecting blocked rain gauges can significantly impact data reliability, food security, and disaster management. This work evaluates four existing quality control methods for detecting blocked rain gauges and demonstrates their limitations, particularly in detecting clusters of faulty sensors. By comparing methods such as the Conditional Mixture Model (CMM), PSWQ (Fz-filter), Kernel Regression, and Gaussian Method, we identify their shortcomings and propose three novel quality control techniques that integrate probabilistic fault detection and consistency-based diagnosis framework to improve timely detection of blocked sensors, while reducing false alarms. In the realm of computer vision, current systems often fail to handle multiple types of novelty due to their focus on single-novelty scenarios. We highlight the need for integrated systems capable of handling multiple types of novelty. To support this, we introduce the Novel Snapshot Serengeti (NOVEL-SS) dataset, derived from the Snapshot Serengeti camera trap data, which includes various forms of novelty. We also present the DCA (Detect, Characterize, and Accommodate) baseline system, designed to handle multiple novelty by detecting, characterizing, and accommodating them. This work aims to advance the robustness and adaptability of novelty detection systems across both weather sensor networks and computer vision applications.

---

### When Is Smaller Greener? Right-Sizing Language Models for Agentic AI

Authors: Sajid Siraj, Maria Barbati
Published: 2026-10-14
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2610.19345v1

AI agents use large language models (LLMs) to plan and act over multiple steps, yet models are usually compared per call rather than per completed task. This paper asks: which model should an agent use to complete tasks reliably while minimising energy, cost and time? We show that per-call comparisons can be misleading for agentic AI. Because a task succeeds only if all required steps succeed, small differences in per-step reliability can produce large differences in overall task success. Failed attempts also consume resources. We therefore evaluate models using energy, cost and time per successfully completed task, treating the completed task as the functional unit. On this basis, we develop a decision model for choosing LLMs in agentic workflows. The model applies to tasks with binary or graded outcomes and to settings with or without retries. We show that each resource has a crossover task length at which a smaller, less reliable model ceases to be the greener, cheaper or faster option. These crossovers divide tasks into three regimes: for short tasks smaller models are preferred, for long tasks larger models are preferred, and only between these extremes do preferences among objectives matter. We embed these results in a two-stage framework that separates efficiency from preference. A Pareto screen first removes models that are never competitive; a weighted decision is required only when a genuine trade-off remains. A pilot study of 15 open-weight models from five developers, ranging from 0.6B to 27B parameters, on two multi-step agent tasks with measured GPU energy supports the predicted structure. The model with the lowest energy per completed task changes with task length and task type, and observed crossover points generally match those predicted from per-step measurements. These findings provide a practical framework for right-sizing language models in agentic AI.

---