# Research Papers — 2026-09 · bundle page 62 of 266 > Full-text markdown of papers #3051–3100 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/62 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/61.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/63.md) ### Beyond the Training Horizon: Mechanisms and Limits of Length Generalization in Looped Transformers Authors: Jia Liang, Xi Jin, Liangming Pan Published: 2026-09-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.33144v1 Looped Transformers can generalize to reasoning chains longer than those encountered during training, but the computations enabling this behavior and limiting its extent remain unclear. We mechanistically compare two looped-Transformer configurations, which we call the Matched-Recurrence Looped Transformer (MR-Loop) and Decoupled-Recurrence Looped Transformer (DR-Loop), reflecting their respective recurrence-training schemes. We evaluate polynomial iteration, finite-state composition, and knowledge-graph traversal using detailed mechanistic analysis. Attention analysis, intermediate-state decoding, and causal interventions reveal distinct mechanisms learned under final-answer supervision. MR-Loop updates an intermediate state at a fixed readout while advancing relation selection through adjacent-token interactions and a transferable progress cue. DR-Loop instead propagates intermediate states across relation positions, forming an advancing computational frontier. However, both mechanisms become unreliable at greater depths: MR-Loop exhibits degradation of its readout state and progress cues, while DR-Loop exhibits declining reliability of state propagation. Limited self-correction allows local errors to persist and compound. Across both models, we uncover a common representational principle: recurrent states encode not only task-relevant content but also its computational status, whether that content remains in a form that can support subsequent computation. Transferable live-consumed and fresh-aged residual directions causally control whether represented information can participate in subsequent computation, including beyond the training horizon. We further show that length generalization need not rely on faithful step-by-step reasoning, as Looped Transformers can exploit task structure without explicitly representing every intermediate state. --- ### CAME: Company-Aware Evidence-Memory Experts for Interpretable Quarter-Ahead Revenue Forecasting Authors: Ya-Wen Wu, Meng-Fen Chiang, Kuang-Da Wang, Wen-Chih Peng Published: 2026-09-27 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.33143v1 Quarter-ahead revenue forecasting requires company-scale numerical accuracy, strict temporal validity, and company-specific interpretation of narrative disclosures. LLMs can distill textual evidence but can produce scale-misaligned forecasts, whereas history-based anchors are stable but miss forecast-time signals such as product transitions, supply constraints, and management guidance. We introduce CAME (Company-Aware Evidence-Memory Experts), a residual-forecasting framework that refines a no-leakage statistical anchor when current semantic evidence and prior error patterns justify an adjustment. On a development-inclusive rolling backtest of 336 company-quarters from 12 large public technology and platform firms, CAME achieves the lowest aggregate point-estimate error among the reported methods, with statistically supported macro-sMAPE gains over the matched Statistical Anchor, and outperforms History + Guidance on all six aggregate metrics. CAME also links adjustments to source-linked evidence cards and guarded memory traces, supporting forecast inspection, provenance, and failure localization. --- ### Knowing Is Not Choosing: What Explicit Verification Adds Beyond Generative Preference Authors: Yilong Li, Chengpo Yan, Aayan Arish, Suman Banerjee Published: 2026-09-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.33142v2 Generating a correct answer does not mean that a language model will select it. We separate factual recall into three steps: generating a correct candidate, ranking the available candidates, and selecting the final answer. Pre-generation readouts predict factual recall and which questions sampling will cover across three model families, but say little about whether an available correct answer will ultimately be selected. Explicit verification with $P(\mathrm{True})$ improves within-question ranking over mean log-likelihood in Gemma, Qwen3, and Llama, with AUROC gains of $0.08$--$0.12$. In a prospectively defined Gemma cohort, verification raises plurality accuracy by about $5$ points, and still gains about $2$ points over chat-template likelihood, a stronger generative baseline. The advantage is strongest for relations with common-answer priors and depends on access to the entity; masking the entity removes the ranking advantage in larger Qwen models. Finally, the measured benefit depends on how correctness is defined: recall-oriented reference matching can credit option lists favored by likelihood and substantially understate the improvement seen under human semantic judgments. Prior work shows that models can carry latent factual knowledge and judge candidate answers; we show that these capabilities do not collapse into a single notion of ``knowing,'' and trace where information is gained, lost, or mismeasured between availability, ranking, and final choice. --- ### On Device Agentic Operation Caches -- Classifier-Centric NL-to-Action Generation Authors: Moghis Fereidouni, Anthony Arnold, Sumit Gulwani, Mark Marron, A. B. Siddique Published: 2026-09-27 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.33141v1 Agentic AI is increasingly being embedded in software applications to provide natural language interfaces to features and functionality. In most cases these agents are powered by enterprise (100+ billion parameter) or frontier class large language models that require substantial computational resources run and depend on cloud hosted inference to handle the task of transforming natural language inputs into actionable software operations. This reliance on cloud-hosted inference introduces substantial network latency on top of LLM inference times, creates data privacy concerns, and, given the costs of running these models, can rapidly escalate expenses associated with supporting agentic features. This paper introduces a novel means of converting the NL-to-Action problem from a generative one into a classification-centric formulation via on-device operation caches. These caches allow an agentic system to handle frequently occurring classes of actions completely on-device -- reducing latency, enhancing privacy, and lowering operational costs. We show that for a classic NL-to-Formula task, generating Excel Formula in response to user requests, this approach reduces total inference cost by 56% when compared to cloud-only model-routing based inference and, on cache hits, reduces the latency to response latency by 5x. --- ### Leaky Students: Membership Inference against On-Policy Distillation Authors: Zhexi Lu, Mingzhi Zhu, Stacy Patterson, Lei Yu Published: 2026-09-27 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2609.33136v1 On-policy distillation (OPD) trains a student to match a teacher's next-token distributions on student-generated trajectories. However, privileged information supplied to the teacher for OPD training may contain sensitive data. Whether the student leaks private information about the records supplied to the teacher during distillation remains poorly understood. To the best of our knowledge, we present the first systematic study of membership inference in this setting. We find that fresh student trajectories expose sparse membership signals that fixed reference-answer losses often miss. These signals are mixed with probability changes caused by training on other records. We introduce Leaky, which samples fresh trajectories from the target model and compares its token log-probabilities with the maximum across matched reference models trained without the candidate records. It applies Leaky ReLU to the resulting gaps, preserving positive gaps and downweighting negative gaps as an approximate correction for incidental positive gaps in non-members. Across fifteen targets spanning mathematics, medical question answering, and code generation, Leaky outperforms all evaluated baselines and achieves mean AUROC 0.875, compared with 0.614 for the strongest baseline on each target in the main evaluation. On the same sampled trajectories, the strongest baseline achieves mean AUROC 0.826. These results show that students trained through OPD can expose the membership of records used for teacher supervision, even when fixed reference-answer losses provide little evidence of membership. --- ### Ceiling of a Task: When Can a Transformer Succeed Without Its Chain of Thought? Authors: Jiashu He, Jinxuan Fan, Xiao Xiao, Radu Marculescu, Alejandro Ribeiro Published: 2026-09-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.33134v1 Reasoning models generate long chains of thought before they answer, yet it is debated whether the content of these chains does real computational work or is largely decorative. We study this question by viewing a transformer as a shallow circuit. One forward pass through a fixed number of layers has constant depth, so any procedure that runs the model a constant number of times is a shallow circuit. We call the best accuracy that a shallow circuit can reach on a task the ceiling of the task, and a task is serial if its ceiling lies below one. We prove three results on serial tasks that hold for every transformer, no matter how it was trained. Necessity: replacing the chain by anything that does not depend on its content, such as filler tokens or a restatement of the question, drives the accuracy down to the ceiling, and on a maximally serial task down to chance. Depth: no shallow computation can write the chain of a model whose accuracy exceeds the ceiling, not even approximately. Locality: the answer is one shallow pass away from the finished chain, so all of the serial reasoning happens in the chain. On word problems of finite groups, whose ceilings are known, small transformers trained from scratch, with or without reinforcement learning, attain the predicted numbers: chain-trained models solve every input length and fall to chance when the chain is erased, chainless models collapse to the ceiling as the input length grows, and open-weight reasoning models given the same problem in words return to the baseline without their chain. On MATH-500 and AIME, erasing the chain costs open reasoning models 0.52 to 0.82 accuracy, a sentence shuffle is harmless, and a token shuffle is as harmful as erasing; the same holds for checkpoints trained by GRPO with a correct or a random reward. The ceiling of a task therefore answers when a transformer can succeed without its chain of thought. --- ### Quantum Monte Carlo Tree Search with Fixed Confidence Authors: Mingjie Hu, Jian-Qiang Hu, Enlu Zhou Published: 2026-09-27 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2609.33132v1 Recent advances in quantum computing are opening new opportunities for computationally intensive decision problems. This paper studies how quantum computing can improve Monte Carlo tree search (MCTS) in the fixed-confidence setting, where the goal is to identify a near-optimal move in a given game tree with high probability while minimizing query complexity. We first formulate MCTS under a quantum oracle model. We then develop a quantum MCTS algorithm (QMCTS) that combines threshold-based elimination on the search tree with quantum Monte Carlo estimation to reduce the cost of evaluating stochastic leaf values. We establish an instance-dependent lower bound on the query complexity and derive a corresponding upper bound for QMCTS. The lower-bound analysis introduces a new quantum phase-testing result that may also be useful beyond MCTS. We validate the theoretical results through simulation experiments and further demonstrate the feasibility of QMCTS on real quantum hardware. --- ### ILP-BO: Integer Linear Programming-Based Black-Box Optimization Authors: Hyakka Nakada, Shu Tanaka Published: 2026-09-27 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.33131v1 Black-box Optimization (BO) is a powerful framework for optimizing expensive objective functions or unknown functions with a limited number of evaluations. A central step of standard BO such as Bayesian optimization is the optimization of a surrogate-based acquisition criterion, which is commonly performed using nonlinear optimization or heuristic search. Therefore, conventional black-box optimization generally does not guarantee global optimality in candidate selection. In this study, we propose Integer Linear Programming-based Black-box Optimization (ILP-BO), a quasi-Bayesian optimization framework that transforms kernel-based surrogate optimization over discrete domains into an Integer Linear Programming (ILP) problem. The key idea is to represent nonlinear kernel functions exactly on finite discrete distance levels by introducing binary one-hot auxiliary variables. This transformation converts the nonlinear surrogate into a linear objective with linear constraints and binary variables. To incorporate exploration while preserving the linear structure, we further introduce a Hamming-distance margin that excludes neighborhoods around previously observed points. We derive the proposed formulation for several standard kernels and obtain an analytical upper bound on the Hamming-distance threshold based on the measure in the binary search space. The resulting candidate-selection problem can be solved by integer programming solvers with certificates of optimality. Thus, our methodology has the potential to serve as a highly transparent black-box optimization framework. Experiments on synthetic and discrete optimization benchmarks show that ILP-BO achieves competitive optimization performance compared with practical Bayesian optimization methods. --- ### Flow-Matching-Based Protein Structure Tokenizer Made Efficient and Easy Authors: Zhe Zhang, Yikai Zhang, Jiangtao Feng, Ya-Qin Zhang, Wei-Ying Ma, Hao Zhou Published: 2026-09-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.33129v1 As the bridge between protein modality and discrete modeling, protein structure tokenization still largely relies on heavily engineered training objectives tailored to specific downstream tasks and large training datasets, which hinders its transfer to broader application scenarios. To address this issue, we propose ProFiT, a lightweight flow matching tokenizer. With simple training strategies that encourage healthy codebook utilization, ProFiT can be trained efficiently and naturally learns semantically meaningful representations without any manual semantic alignment, while achieving reconstruction quality and generalization that match or surpass those of substantially larger tokenizers. We conduct extensive evaluations across a wide range of settings and demonstrate that ProFiT is a plug-and-play tokenizer adaptable to diverse downstream tasks. This study further reveals the significant potential of the flow matching tokenizer paradigm. Our code is publicly available at https://github.com/QDKStorm/ProFiT. --- ### Policy Plasticity Matters in Offline-to-Online Reinforcement Learning: Refitting Offline Policies for Online Adaptation Authors: Yuheng Huang, Yunpeng Qing, Yixiao Chi, Yilun Kong, Changqing Zou Published: 2026-09-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.33127v1 Offline-to-Online Reinforcement Learning (O2O RL) has emerged as a practical paradigm that pre-trains the policy using static offline datasets and subsequently adapts the policy through online interactions. Existing O2O methods primarily address the transition through value calibration, while generally treating the offline-trained policy as a given initialization. We instead study O2O adaptation from the perspective of network plasticity, asking whether the offline-trained policy remains sufficiently adaptable for online learning. Controlled experiments show that prolonged optimization on static offline data progressively reduces network plasticity even after offline performance has largely saturated, and that lower plasticity is associated with weaker subsequent online improvement. Motivated by these observations, we propose REstoring plasticity via Fresh Initialization and policy Transfer (REFIT), a lightweight model-level method for the O2O transition. Before online fine-tuning, REFIT distills the offline policy into a freshly initialized student while temporarily freezing a random subset of student units, transferring the learned offline behavior to a more plastic policy initialization. Extensive experiments on D4RL and OGBench demonstrate that REFIT consistently achieves higher aggregate performance than existing O2O plug-in methods across both Cal-QL and IQL backbones, while plasticity diagnostics and ablations provide further evidence of restored network plasticity. --- ### Save Your Saturated Data: Learning Beyond Reward Saturation in Group-Based RL Authors: Ziyuan Yang, Yike Wang, Shangbin Feng, Yulia Tsvetkov Published: 2026-09-27 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.33126v1 Group-relative reinforcement learning (RL) relies on reward variation among sampled responses to estimate informative relative advantages. As language models become increasingly capable, existing training data can become reward-saturated: all sampled responses to the same problem might receive equally high rewards, where the group-relative learning signals vanish and leave previously useful data obsolete. In this work, we investigate whether useful learning signals can be recovered from such saturated data. We study interventions at four levels of group-policy RL pipelines---data, rollout, reward, and advantage---and conduct extensive RL training on saturated reasoning data only. While standard GRPO on saturated data would almost always yield near-0 advantages and near-noise signals, diverse interventions successfully recycle and repurpose such data: among the proposed strategies, interventions at rollout generation are consistently most effective: nudging the policy to generate ``high-quality'', incorrect solutions introduces rollouts with poor rewards into saturated groups as negative samples, which turns out to improve GRPO by 6.4% to 9.0% across Qwen3-1.7B and 4B. Other interventions such as increasing rollout temperature or adding auxiliary rewards can also restore non-zero advantages, but yield less consistent gains. Further analyses show that effective negative rollouts require informative negative trajectories, that the method remains effective alongside unsaturated data, and that it supports iterative recycling of newly saturated examples. While increasingly stronger LLMs would render more data as saturated, our results demonstrate that don't waste your saturated data: with the right strategies they can be recycled into useful RL training signals in an increasingly data-scarce world. --- ### Train Together or Merge Later? Unifying VLA Experts via a Shared Action Interface Authors: Zhizhen Zhang, Yuxia Fu, Zijian Wang, Helen Huang, Yadan Luo Published: 2026-09-27 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.33125v1 Co-training offers a straightforward way to build a multi-task vision-language-action (VLA) policy, but can fall short of the performance achieved by training each task independently. The challenge is to retain these task-specific gains in a multi-task policy without joint post-training. Combining independently trained experts through model merging is a natural approach, yet strong individual experts do not necessarily yield a strong merged policy. We identify one source of this incompatibility: task-specific changes to the action interface, comprising action normalization and the action encoder and decoder. We propose PolicyWeave, combining merge-compatible post-training with context-guided sparse merging. During post-training, all experts retain the common base policy's action interface, while task adaptation is restricted to LoRA updates in the hidden layers of the action model. This makes the experts more compatible with existing model merging methods. However, merging all experts can still introduce interference from unrelated tasks at deployment. PolicyWeave scores each expert's LoRA updates using the initial visual-language context, determines the expert set through leave-one-layer-out ranking stability, and forms a sparse weighted merge of the selected updates that remains fixed for current task. We evaluate PolicyWeave with GR00T N1.5 on 18 RoboCasa365 tasks, using only 10% of the target-task demonstrations for supervised fine-tuning (SFT). Preserving the shared action interface raises the average success rate across four static merging methods from 17.0% to 52.8%. PolicyWeave achieves 64.7% success with these SFT experts and 74.1% after task-specific reinforcement learning (RL), compared with 60.7% for joint RL. Further evaluations on LIBERO-10 and an AgileX Piper arm support the deployment of independently learned skills in long-horizon and real-world manipulation. --- ### Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring Authors: Zhixiang Zhang, Zesen Liu, Wai Ip Lai, Hongxu chen, Dongdong She Published: 2026-09-27 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.33123v2 Self-evolving agent harnesses continually update persistent components such as memory, prompts, skills, and tools. We call this process harness evolution. However, such evolution could introduce unexpected safety risks. Existing work studies harness misevolution and validates candidate harnesses or attributed individual component updates, leaving safety analysis of cross-component update interactions largely unexamined. To address this gap, we study compositional safety failures in harness evolution, where interactions among individually safe and utility-preserving component updates can produce undesirable or unsafe agent behavior, revealing a safety risk intrinsic to harness evolution. Across three safety-related benchmarks, we identify 43 pairwise and 18 irreducible 3-way compositional safety failures. Conventional solution incurs combinatorial complexity in validating cross-component interactions, leaving the safety checking impractical as the harness evolves. To solve this, we introduced a typed hypergraph that represents component states as nodes and safety-relevant higher-order interactions as hyperedges. When the harness changes, the hypergraph updates only the interaction neighborhood of the changed states rather than reconstructing the global composition space. Building on that, we develop a hypergraph-guided runtime monitoring mechanism. Experiments show that our method effectively mitigates compositional safety risks while preserving task utility and reducing interaction-checking costs, and further reveal an empirical safety-utility-cost trade-off across different safety mechanisms. --- ### Classifying Dominant Temporal Orientation without Pretrained Text Embeddings: A Novel Morphosyntactic Inventory Vector Approach Authors: Jonathan Cleveland, Peter S. Bearman Published: 2026-09-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.33121v1 Computational methods have consistently struggled to determine the dominant temporal orientation of a sentence. This difficulty is especially pronounced when a sentence contains multiple embedded clauses with competing tense and aspectual information. To address this difficulty, we propose an alternative approach for identifying a sentence's past, present, or future global reference interval. Our method does not use any form of pretrained embeddings. We rather encode sentences using fixed-length inventory vectors that are comprised of part-of-speech counts, dependency relation counts, and explicit futurate pattern counts. We term this inventory vector of a sentence a "Morphosyntacton". The method does not use any padding, sequence models, or large language models. Evaluation on 1,799 syntactically complex English sentences, annotated as past, present or future, shows balanced and high accuracy multiclass classification, achieving an overall multi-class accuracy of 92%. --- ### Mycelium: A Generalizable Cross-Grid Multi-Task Model for Electrical Distribution Systems Authors: Zhengyang Wei, Shourya Bose, Helgi Hilmarsson, Elena Carnio, Dhruv Suri Published: 2026-09-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.33120v1 Electrical distribution grid operations require inference across heterogeneous networks from sparse, noisy, and incomplete time series measurements. In this work, we identify challenges and explore solutions towards a unified model that can perform diverse tasks grounded in the physics of the electric grid and generalize to unseen distribution networks. We define a unified grid ontology that represents variable sized distribution networks as heterogeneous graphs while preserving native topology, asset types, and electrical relationships across networks. We develop a physics based data simulation pipeline that combines reference and procedurally generated distribution networks with network reconfigurations, fault scenarios, and configurable sensing conditions. We present Mycelium, a heterogeneous graph transformer with structure aware communication edges and electrical reference features that encode network position and nominal phase orientation, together with task specific temporal readouts which generate per task outputs. We train Mycelium on reference as well as synthetic grids, and study its generalization on benchmark networks completely excluded from training and validation. Mycelium is observed to outperform task specific neural baselines on most reported benchmark metrics. Architectural ablations and the aforementioned studies reveal Mycelium's capability to learn representations of the underlying physics which serves to enhance cross-task performance, thereby addressing a significant challenge in unified grid models. --- ### MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning Authors: Lang Cao, Binghang Lu, Yuhao Shen, Yue Guo Published: 2026-09-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.33119v1 Medical question answering spans diverse specialties and modalities, and individual medical large language models (LLMs) exhibit distinct strengths across tasks and domains. This heterogeneity suggests that combining specialists may enable broader coverage of medical questions than relying on any single model. However, existing LLM routing methods primarily seek to balance answer quality and inference cost, leaving open how to exploit differences in specialist competence to improve medical reasoning. In this paper, we introduce MedRouter, an agentic system that uses an embedding-based multi-label router to select and query specialist LLMs, then passes their responses to a generator to produce the final answer. We further propose SCALE (Specialist Competence-Aware Learning), a two-stage training framework that first trains the Router with specialist correctness supervision and then optimizes its selections through reinforcement learning. The second stage uses a Performance Gain Reward (PGR) that measures how specialist information affects the generator's answer correctness relative to answering without that information. Experiments on eight text-based and multimodal medical QA benchmarks show that MedRouter outperforms the strongest routing baseline by 8% in average accuracy. Our analysis of specialist outputs further reveals distinct strengths and complementary question-level coverage, motivating learned routing to combine these capabilities for more comprehensive medical reasoning. --- ### ECG-Scroll: A Long-Horizon, Streaming Benchmark and Agent Environment for Interpretation of Ambulatory Electrocardiograms Authors: Haitao Li, Chenglin Li, Zhengyao Ding, Ziyu Li, Yiheng Mao, Zhengxing Huang Published: 2026-09-27 Categories: cs.LG, cs.AI, cs.CL, eess.SP arXiv: https://arxiv.org/abs/2609.33117v1 Multimodal large language models (MLLMs) can now interpret a standard ten-second, twelve-lead electrocardiogram (ECG) with clinically grounded, reward-verified reasoning. Real cardiac monitoring is different. Ambulatory (Holter) and telemetry recordings span hours to days and are read as they stream in, and their clinically decisive findings are paroxysmal, brief episodes buried in an otherwise unremarkable trace. Such a recording cannot be held in one context at diagnostic resolution, and its future has not yet happened, so a reader must work online, deciding what to measure now, committing evidence to memory as it passes, and reporting events as they occur. We recast long-duration ECG interpretation as a long-horizon, online (streaming, causal) sequential decision process and introduce ECG-Scroll. As a benchmark, long ambulatory recordings are streamed to an agent chunk by chunk, and it must localize, quantify, and promptly flag paroxysmal events without access to future signal; because the underlying signal is retained, every answer is checkable against objective ground truth, giving rule-based rather than judge-based rewards, and the streaming formulation adds a metric batch evaluation cannot express, the detection latency between an event's onset and the moment the agent records it. As an agent environment, it is a fixed, gym-style interaction layer that exercises three competencies single-glance ECG models never touch: Memory, Tool use through signal-grounded measurement rather than reading pixels, and Planning of what to measure now and when to commit. We release 390 whole-recording instances spanning 2,536 hours of two-lead ambulatory ECG and evaluate a signal-threshold rule agent alongside off-the-shelf LLM agents online, characterizing how they use memory, tools, and planning and where the benchmark's head-room lies. --- ### Modular Discovery of General Game-Playing Algorithms with Large Language Models Authors: Zun Li, John Schultz, Marc Lanctot, Daniel Hennes Published: 2026-09-27 Categories: cs.AI, cs.GT, cs.MA arXiv: https://arxiv.org/abs/2609.33115v1 General Game Playing across arbitrary games from rules alone remains challenging due to differing algorithmic requirements across game classes and strict decision-time constraints. Rather than hand-designing search heuristics for specific domains, can we leverage Large Language Models (LLMs) to discover general game-playing algorithms? Because language models can propose and refactor structured code, they provide an expressive proposal engine for exploring the space of algorithmic designs. We introduce a multi-agent LLM meta-learning system to co-evolve game-agnostic procedural search mechanisms in C++ alongside domain heuristics synthesized directly from game rules. Controlling the compute budget, we benchmark the discovered mechanisms across more than 400 diverse environments, including OpenSpiel training and held-out games, procedural simulation engines, and games with deep neural policy-value representations trained via PPO. Evaluated via AlphaRank stationary distributions and Soft Condorcet Optimization (SCO) against 15 established MCTS baselines, the discovered search mechanisms consistently achieve top-tier ratings and pairwise ballot majorities over most baselines across independent evolutionary runs, generalizing to unseen human-designed and procedurally synthesized games and remaining competitive with baselines on frozen neural network representations. --- ### Can Tabular Foundation Models Amortize Statistical Inference? Authors: Kai Ye, Shijin Gong, Hongyi Zhou, Valentina Zangirolami, Chengchun Shi Published: 2026-09-27 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2609.33114v1 For decades, statistical inference has largely been developed one problem at a time. Given a scientific target, such as a treatment effect or a regression function, statisticians design a problem-specific estimator together with a procedure for quantifying its uncertainty. This paper proposes a different paradigm. We focus on a classical problem in statistical inference, confidence interval construction, and develop TabCon, an amortized inference system built on a tabular foundation model that produces confidence intervals for new datasets through a simple forward pass. The key methodological ingredients of TabCon are a sparse mixture-of-experts architecture and reinforcement-learning-based post-training that calibrate the resulting confidence intervals to a desired coverage level. Across a wide range of benchmark datasets, TabCon attains near-nominal coverage while producing short confidence intervals. At inference time, it also offers considerably greater computational efficiency, running 50 times faster than the classical bootstrap procedure, even when the latter uses only 50 bootstrap samples. --- ### ParallelPilot: Supporting Coordination and Monitoring in Parallel AI Coding Authors: Tao Long, Weili Shi, Hussein Mozannar, Maya Murad, Rafah Hosn Published: 2026-09-27 Categories: cs.HC, cs.AI, cs.DC, cs.MA arXiv: https://arxiv.org/abs/2609.33113v1 As coding assistants become increasingly autonomous, developers run multiple sessions in parallel, shifting the challenge from code generation alone to coordinating and monitoring concurrent agent work. Through a formative study (N=14), we identified PILOT: five supervisory practices for Planning, Isolating, Logging, Observing, and Triaging parallel sessions. We present ParallelPilot, a design probe that instantiates PILOT through a planning interface, a run-logger, and an ambient dashboard alongside existing coding tools. In a counterbalanced within-subjects study (N=16), participants using ParallelPilot increased ticket throughput by 63% in short coding tasks and supervised an average of one more concurrent agent at peak, while their tracking effort and context switching dropped. ParallelPilot also clarified execution plans, task dependencies, and intervention cues, and 14 of 16 participants preferred it over their current setup. These gains were not accompanied by significant improvements in perceived control or perceived success in redirecting the agents. Our findings demonstrate the value of explicit supervision support and position PILOT as a scaffold for designing tools that help people supervise concurrent work within and beyond coding. We suggest that future coding assistants should pair high-level awareness with low-cost paths back to the implementation evidence developers need to judge and steer agent work. --- ### Simulation-Free Learning of GP-SDEs from Irregular Observations Authors: Zhidi Lin, Yuhao Liu, Ying Li, Edwin Fong, Petar Djurić Published: 2026-09-27 Categories: cs.LG, eess.SP, stat.ML arXiv: https://arxiv.org/abs/2609.33112v1 Gaussian process stochastic differential equations (GP-SDEs) provide a flexible Bayesian model for unknown continuous-time state dynamics with uncertainty quantification, but learning and inference from noisy and irregular observations remain computationally challenging. To address this issue, we propose GP-SDE Matching, a simulation-free variational framework for Bayesian GP drift learning and continuous-time state smoothing. We analytically marginalize the sparse GP posterior to derive a tractable drift-matching objective that accounts for both the posterior mean and uncertainty of the unknown drift. To handle irregular observations, we further introduce an irregular-time-aware variational state posterior that incorporates the actual observation times during both encoding and continuous-time marginal querying. Experiments on the stochastic Lorenz--63 system demonstrate substantially improved drift recovery and state reconstruction under irregular observations, while five system identification benchmarks show robust forecasting under increasing observation sparsity and competitive performance against existing latent-SDE and state-space methods. --- ### D-JEPA: Design-Recoverable JEPA Representation with Swappable Physics Decoders Authors: Nitin Nagesh Kulkarni, Aashwin Anand Mishra, Yin Yu, Peter Lyu Published: 2026-09-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.33110v1 Joint-Embedding Predictive Architectures (JEPAs) provide a framework for learning compact representations without directly reconstructing high-dimensional observations. However, in parameterized physical systems, learned representations can entangle geometry with operating conditions and task-specific physical responses, limiting their reuse across prediction tasks. We introduce D-JEPA (Design-recoverable JEPA), a geometry-centric JEPA that computes a compact representation from geometry alone and reuses it across operating conditions and physical response spaces through lightweight physics-specific decoders. An explicit design-recoverability objective encourages the geometry latent to preserve information about the underlying design variables, enabling the representation to support design analysis and optimization. We further identify a case-level collapse failure mode in which target representations become nearly invariant across distinct geometries despite low reconstruction error, and mitigate it using case-level variation constraints and auxiliary target reconstruction. Across four 3D aerodynamic, hydrodynamic, and structural benchmarks, D-JEPA maintains or improves full-field prediction accuracy while achieving near-perfect linear recoverability of design parameters. The frozen geometry representation can be reused at held-out operating conditions and transferred to a structural response task with fewer trainable parameters. Finally, the representation supports differentiable design optimization, with designs validated using high-fidelity CFD, preserving the predicted ranking of candidate designs. These results demonstrate that separating a reusable geometry representation from physics-specific prediction provides a practical representation for scientific surrogate modeling and design. --- ### Toward Comprehensive 3D Grounding: Orientation Grounding through Vision-Language Models Authors: Tuo Liang, Disheng Liu, Nengbo Wang, Vipin Chaudhary, Yu Yin Published: 2026-09-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.33109v1 Grounding is a core capability of spatial vision-language models, yet most existing work focuses only on where a referred object is. Many 3D tasks also require knowing how it is oriented. Although existing 3D VLMs may predict oriented boxes, box pose does not explicitly capture object-centric orientation or symmetry-induced ambiguities. We introduce orientation grounding, a referring grounding task that predicts an object's 6D orientation and axial symmetry from a language or box query in single-view or multi-view scenes. To support this task, we construct ReferOri, with 331K multi-view and 387K single-view orientation-grounding queries obtained through scalable reconstruction, consistency checking, and human verification. We further present OG-VLM, which adapts a 3D VLM with structured box/orientation outputs, sign and symmetry tokens, and geometry-aware auxiliary losses. Across single-view and multi-view benchmarks, OG-VLM substantially outperforms orientation-aware VLM baselines and surpasses object-level orientation foundation models on scene-level referring benchmarks, showing that explicit orientation grounding is a distinct and learnable capability beyond localization. Downstream results validate its benefit for orientation-related spatial reasoning. --- ### CARVE: Breaking Data Barriers in Chip Placement by Harnessing Reusable Expertise Authors: Jiefu Zhang, Haixiang Sun, Yang Xu, Vaneet Aggarwal, Zishen Wan Published: 2026-09-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.33106v1 Pretrained macro-placement policies can reduce repeated optimization across circuits, but deployment often exposes them to unfamiliar designs when the original training data are unavailable. Repeatedly fine-tuning a single serving model can overwrite earlier improvements, while simply saving checkpoints does not determine where they can be reliably reused. We introduce Continual Adaptation through the Reuse of Validated Expertise (CARVE), a framework that represents accumulated expertise as a frozen base policy, immutable specialists, and task-specific credentials obtained through local validation. For a new task, CARVE first checks existing specialists and trains a new specialist from the frozen base only when none qualifies. Under fixed task distributions and validation rules that control cumulative error, we establish expected-performance guarantees for repeated reuse. For bounded losses, we also derive matching worst-case bounds on the local samples needed for reliable reuse. In macro placement, a reuse-first follow-up reduces recorded training time by 58.5% (9.66 to 4.01 hours), while mean HPWL gain changes only from 8.41% to 7.86%. In a simulated receiving deployment, imported specialists are reused on six of seven new IBM circuits with no receiver-side training, achieving a 5.76% mean HPWL gain. Navigation studies provide complementary evidence on repair retention and repeated adaptation. --- ### VPTwin: Real-Sim-Real Video Prediction for Robotic Manipulation Planning Authors: Zhenghao Xiao, Minting Pan, Nantian He, Dongzhan Zhou, Yunbo Wang Published: 2026-09-27 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.33104v1 While action-conditioned video prediction provides an intuitive world model for robotics, purely data-driven predictors often suffer from compounding errors and physically implausible hallucinations in long-horizon rollouts, severely undermining downstream action planning. We propose VPTwin, a Real-Sim-Real video prediction framework that anchors real-world future prediction using real-synchronized simulation twins. For a target manipulation task, a VLM reconstructs an executable digital twin from a real demonstration episode. To accommodate the ill-posed estimation of unobserved physical properties, Isaac Sim simulates multiple forward dynamic rollouts across randomized physical configurations under candidate action trajectories. Using these rollouts as in-context references, VPTwin harmonizes both domains, using simulation dynamics to enforce physical plausibility while capturing unmodeled contact interactions from real video. Furthermore, we establish a predictive planning loop using VPTwin to visually verify VLM-proposed actions and guide reliable real-world execution. Evaluations show substantial reductions in physical hallucinations during video prediction and marked improvements in manipulation planning performance. --- ### Evolving Dexterous Robots from Scratch Authors: Zihan Guo, Shuzhe Zhang, Muhan Li, Peiyang Li, Sam Kriegman Published: 2026-09-27 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.33101v1 Little is known about how to manually design agents capable of dexterous manipulation. Some design principles have been inferred from close examination of how animals manipulate objects, but these structures and behaviors have so far resisted biomimicry and may not be optimal for artificial machines. Here we evolve freeform robots to pick up, hold, rotate, and use diverse objects. Unlike other approaches to optimizing robot hands, we do not presuppose the presence, articulation, or geometry of any part of the body. Although familiar prehensile forms such as tails, beaks, paws and claws may emerge spontaneously under certain conditions--and while such conditions could be of interest to evolutionary biologists--de novo manipulator design can also reveal whole new solutions, overlooked or unknown structures which may be better suited for the task at hand. We use contrastive learning to create a highly searchable genetic embedding of design space, an autoregressive developmental model to decode designs, evolutionary strategies to find good designs, and reinforcement learning to train each evolved design. Winning designs were automatically converted into a manufacturable blueprint, printed, assembled and tested in the real world in a zero-shot manner. The results represent the state-of-the-art in evolutionary robotics in terms of performance, diversity and complexity. --- ### Octree-based Video Representation Authors: Rungui Zhou, Chuanzhi Zhou, Yuk-Kit Hou, Peng-Shuai Wang Published: 2026-09-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.33100v1 Video models commonly use uniform grids even though visual complexity varies substantially across space and time. We introduce OctVideo, which approximates a video clip with an octree. This hierarchy recursively partitions a spatio-temporal volume into eight subvolumes, so that smooth regions remain coarse while detailed regions receive finer cells. Each leaf stores local RGB values and spatio-temporal gradients, supplemented by a lightweight learned residual. For reconstruction, a Conv1D VAE maps the serialized cells to a regular latent grid and selectively refines details during decoding. Our VAE achieves 36.12 dB PSNR with 38.2M parameters and 189.4 GFLOPs per clip on Kinetics-400 (K400). It also generalizes zero-shot to the high-resolution Densely Annotated VIdeo Segmentation (DAVIS) 2016 dataset with reconstruction quality comparable to the best evaluated models. On both datasets, it requires the fewest model FLOPs and achieves the fastest encoding and decoding among the evaluated models. OctVideo also supports video understanding, achieving competitive recognition performance with few input tokens when trained from scratch. By exploiting the redundancy already present in video signals and efficiently processing sparse structures, OctVideo provides an efficient representation for video. --- ### Query, Align, and Distill: Navigation-Aware Cross-Modal Interaction for Efficient Vision-and-Language Navigation Authors: Zhihao Chen, Yiyuan Ge, Ziyang Wang, Pu Cao, Lu Yang Published: 2026-09-27 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2609.33097v1 Recent large-scale Vision-and-Language Navigation (VLN) models deliver strong accuracy but remain costly to deploy due to their large parameter counts and computational requirements. We tackle efficient VLN in two steps. First, we build a high-performing teacher that makes navigation evidence selection explicit and compressible. The teacher introduces a small set of learnable query slots to extract global and local action-sufficient navigable evidence from panoramic observations via a Navigable Query Generator, then progressively grounds these evidence tokens to the instruction with an Instruction-Query Aligner for policy prediction. Second, using this explicit query bottleneck as a distillation interface, we train a compact student by transferring both where to attend and what to do. We distill the teacher's global and local navigable queries with a navigation-aware token-adaptive objective, then further match action distributions during fine-tuning. Experiments on standard VLN benchmarks demonstrate that our student nearly matches the teacher's navigation performance while reducing the number of parameters by 93.65% compared to the teacher. --- ### How Linear Attention Remembers Authors: Kichang Lee, JaeYeon Park, Songkuk Kim, JeongGil Ko Published: 2026-09-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.33093v1 Linear attention replaces the growing key--value (KV) cache of standard attention with a fixed-size recurrent state, substantially reducing memory growth with context length. This efficiency, however, changes how past information is stored: many tokens must share and repeatedly update the same memory. We study how this recurrent state functions as a memory system. Using an analytical decomposition together with controlled causal interventions in pretrained GLA and GDN models, we trace how recalled information is written, retained, and later accessed. We find that fact-specific information enters recurrent memory through concentrated, content-dependent writes and is later accessed through concentrated query-time read pathways. Multiple facts can remain selectively accessible within the same state, yet their internal representations exhibit cross-fact causal coupling rather than independent KV-like storage. As memory load increases, both recall and targeted editability degrade, whereas elapsed context alone has a substantially smaller effect within the tested regime. Causal interventions on subsequent writes further show that interference is shaped by their overlap with existing memory. Finally, in hybrid architectures that combine recurrent layers with full attention, the runtime memory directly supporting recall shifts predominantly to the full-attention KV state. Together, these results reveal how fixed-size recurrent memory supports selective recall despite shared storage, while exposing the interference and capacity limits that distinguish it from token-addressable KV memory. --- ### OneSign: Unifying Sign Language Understanding Tasks with One Model Authors: Shiwei Gan, Yafeng Yin, Xiao Liu, Desibieer Tuerdaken, Lei Xie, Sanglu Lu Published: 2026-09-27 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.33090v1 SLU encompasses a diverse set of tasks, including ISLR, CSLR, and SLT. Although these tasks share basic semantic and linguistic foundations, they are typically addressed with task-specific architectures and training pipelines, which hinders knowledge sharing and requires costly pretraining and finetuning for each task. In this paper, we focus on two aspects of SLU tasks: (1) training and inference pipelines are highly fragmented: most methods rely on pretraining on large-scale SL datasets followed by task- or dataset-specific finetuning, which leads to multiple specialized models rather than a single checkpoint. (2) current LLM-based methods may overlook the inherent modality discrepancy between sign and text tokens, simply concatenating them and processing both modalities with the same decoder layers. In this paper, we present OneSign, a unified framework that addresses multiple SLU tasks within a single model and a single checkpoint. OneSign reformulates ISLR, CSLR, and SLT under a single training paradigm. To accommodate the heterogeneous characteristics of sign and text representations, we introduce a Modality-Adaptive Mixture-of-Experts (MA-MoE) architecture, consisting of a shared expert and modality-specific experts for sign and text tokens. A modality router dynamically activates the corresponding experts, and their outputs are aggregated to form the final token representations. By enabling modality-dependent expert specialization while preserving a shared expert path, MA-MoE can effectively model the modality differences between continuous sign representations and discrete text tokens. Extensive experiments on multiple benchmarks demonstrate that OneSign achieves competitive or state-of-the-art performance on several benchmarks, highlighting its effectiveness as a unified SLU model. Datasets are available at : https://github.com/gswycf/OneSign. --- ### Geometry-Aware Operator Families for Structured Representation Learning Authors: Zuyuan Zhang, Fei Xu Yu, Tian Lan Published: 2026-09-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.33089v1 The geometry of latent representations governs which components should interact and how information should propagate, making geometry-aware operator design a fundamental ingredient of structured deep representation learning. However, existing neural architectures typically rely on generic operator templates or geometry-specific constructions, creating a need for a unified framework that can derive admissible operators directly from fixed structural information while remaining adaptive to changing contexts. We introduce \emph{Geometry-Induced Operator Families} (GIOF), a general framework that converts fixed geometry into a structured family of propagation operators and dynamically selects an appropriate member of this family according to the current context. GIOF first transforms geometry-derived interaction channels into reusable generator bases, then combines them through a context-dependent selector and adaptive propagation scale, and finally realizes the selected operator through stable continuous-time propagation and a bottleneck residual layer. We establish theoretical guarantees covering parameter compression, identifiability, stability, locality, compositional structure, and oversmoothing behavior, while controlled experiments validate these mechanisms and experiments on PEMS-BAY and METR-LA achieve the lowest mean MAE across all reported regional-outage settings, improving over the strongest retained baseline by 2.4\%--8.8\% at 30\% missing sensors. --- ### QSCP: Beyond Class-Name Prompts for Query-Guided Semantic Change Parsing Authors: Yuan Qian, Jie Ma Published: 2026-09-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.33088v1 Traditional change detection (CD) identifies changes between bi-temporal remote sensing images, while semantic change detection (SCD) assigns predefined land-cover classes. However, mapping all changes may not meet a user's specific needs. Referring change detection (RCD) enables selective retrieval through category prompts. However, existing category-prompted RCD uses the queried category to specify the destination of a change and returns only a binary mask of the corresponding regions. Users may instead request a particular transition and paired semantic maps to understand what changed into what. Such requests require explicit source and target reasoning beyond target-class localization. To address these needs, we propose query-guided semantic change parsing (QSCP), which supports category names, synonyms, and intent-bearing sentences and returns a query-specific mask with paired temporal semantic maps. QSCP parses requests into intents and semantic slots, composes bidirectional visual evidence, and predicts both temporal states with a query-conditioned decoder. On SECOND, QSCP outperforms RCDNet on synonym, sentence, and transition queries and improves end-to-end semantic prediction over evaluated semantic baselines. WHU-CDC experiments further assess cross-dataset transfer and consistency across equivalent expressions without target-domain training. Code is available at https://github.com/qianyuancs/QSCP --- ### Plug-and-Play Methods Provably Converge Even with Improperly Trained Denoisers: Convergence by Architectural Design Authors: Henry Pritchard, Rahul Parhi Published: 2026-09-27 Categories: math.OC, eess.SP, stat.ML arXiv: https://arxiv.org/abs/2609.33087v1 Plug-and-Play (PnP) methods replace proximal operators with learned denoisers, which produce state-of-the-art reconstruction quality, but sacrifice the variational interpretation and convergence guarantees of proximal methods. Learned Proximal Networks (LPNs) address this problem by designing the denoiser architecture so that it is exactly the proximal operator of a regularizer. In this work, we clarify the theoretical foundations of LPNs and extend the framework to a broader class of activation functions. We then study two practical mechanisms for controlling the learned prior: (i) averaging the LPN with the identity, a common heuristic in PnP methods, and (ii) directly scaling the implicit regularizer induced by the proximal operator. In particular, we characterize the regularizer induced by averaging and develop a convergent method for evaluating the scaled proximal operator. --- ### From Constitutions to Control: Interpretable Rewards for Aligning Language Models Authors: Johann D. Gaebler, Calvin Isley, Max Lamparth, Stephen Casper, Sharad Goel Published: 2026-09-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.33086v1 Current approaches to aligning language models often make it hard to know what behavior is being rewarded or to change that reward in a targeted way. In particular, standard preference-based methods collapse multiple considerations into aggregate human judgments, obscuring what drives the resulting reward, while principle-based methods specify high-level values without fully operationalizing them. To address this gap, we develop a rubric-based framework to transform a general-purpose constitution into an interpretable and tunable reward model, using constitution-guided AI feedback to estimate initial weights for the constituent rubric items. We then reweight those dimensions to construct modified rewards for training. Across experiments on political alignment and safety-helpfulness tradeoffs, reweighting individual dimensions predictably changes targeted behaviors largely independently while navigating tradeoffs between conflicting alignment objectives. We show that the same framework can mitigate label bias encoded in preference judgments -- including sycophancy and demographic bias -- by reducing their influence on the training reward. Our results demonstrate that constitution-derived, interpretable rewards can translate high-level alignment principles into more transparent and controllable model behavior. --- ### The Model Knows Another Way: Strategy Switching for Effective RLVR Exploration Authors: Jin Cui, Xinyue Long, Boran Zhao, Pengju Ren, Hao Dong Published: 2026-09-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.33085v1 Reinforcement learning with verifiable rewards (RLVR) is often limited by insufficient exploration: difficult problems can yield uniformly incorrect rollout groups and therefore little learning signal. We show that such failures need not reflect missing capability. Instead, finite sampling often concentrates on a problem-specific dominant reasoning strategy while leaving alternative strategies already supported by the model unexplored. Moreover, the accessibility of these strategies evolves during RL: some are internalized into autonomous behavior, while others become difficult to elicit before being absorbed. Motivated by these observations, we introduce Problem--Strategy Rollout Allocation (PSRA), which treats unguided and strategy-conditioned prompts as competing exploration arms and uses Bayesian sequential allocation to direct a fixed rollout budget toward arms most likely to yield informative, non-saturated groups. A preservation objective keeps useful strategy-conditioned routes accessible while successful guided behaviors are transferred to the unguided policy. Across Qwen2.5 models from 1.5B to 7B and two RL training corpora, PSRA consistently improves reasoning performance, reduces dead saturation, strengthens out-of-distribution transfer, and maintains larger gains under increased inference budgets. --- ### dKFD: Phase-Structured Evidence Allocation for Fixed-Budget Localized Event Understanding Authors: Aditya Bagri, Ashutosh Kumar, Chaitanya Lakhchaura, Avinash Anand, Zhengkui Wang, Rajiv Ratn Shah Published: 2026-09-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.33083v1 Sparse video understanding often requires selecting a small set of visual evidence under a fixed frame budget. Most sparse selectors allocate this budget globally, allowing all frames to compete with one another. For temporally localized events, this can be a poor inductive bias: useful evidence is often distributed across pre-event context, the event itself, and post-event consequences. We study fixed-budget evidence allocation for localized event videos and show that globally competitive Top-$K$ selectors can preserve recognition and grounding while producing unstable event evidence. On DoTA Video Anomaly Recognition, Global Top-$K$ obtains competitive recognition and temporal grounding, but low selector-event alignment at $K=12$ (Frame AUC $51.5 \pm 10.8$). We propose dKFD, a phase-structured differentiable selector that reserves evidence capacity across pre-event, event, and post-event phases after full-sequence temporal encoding. Under matched-budget multi-seed evaluation, dKFD improves Frame AUC by $+30.97$ over a matched Global Top-$K$ selector at $K=12$ ($p<0.01$), while yielding modest but statistically significant recognition gains and comparable temporal grounding. Mechanism ablations show that phase supervision is load-bearing: removing it reduces Frame AUC to $41.1 \pm 12.0$ even when phase-partitioned budgets are retained. Downstream diagnostics on VRU-Accident show consistent gains over learned Global Top-$K$ across VLM families, while dense captioning reveals a boundary condition where uniform sampling remains competitive. These results support phase-structured allocation as a controlled fixed-budget approach for event-centric sparse evidence selection, not as a universal video summarization strategy. --- ### SemReward-VL: Semantic Reward-Guided Video-Language Adaptation for Developmental Behavior Assessment Authors: De Jiang, Shuo Zhang, Kehong Yuan, Hongen Liao Published: 2026-09-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.33082v1 Developmental screening videos show how children perform specific behaviors, but clinical records usually contain outcomes rather than descriptions of what happened. We present SemReward-VL, which learns to describe item-specific behavior from these outcomes. A vision-language model generates a description, and a frozen language model scores its agreement with the clinical outcome, relevance to the item, abstention on unrelated video-item pairs, and clarity. Group relative policy optimization (GRPO) updates LoRA adapters using this semantic reward. On 13,379 videos covering 41 items, the method improves aggregate accuracy and the number of items with recall above 0.5. Errors remain in temporal direction, duration, and age-specific interpretations of behavior. --- ### Structure-Mapping-Guided Self-Explanation for Learning Mathematical Procedures Authors: Shinhaeng Lee, Christopher J. MacLellan, Daniel Weitekamp Published: 2026-09-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.33079v1 Worked examples are a powerful form of instruction, but learners must infer how the demonstrated steps were produced. A naive simulation of this self-explanation process can generate thousands of numerical explanations that reproduce one observed change without capturing its underlying procedure. We propose structure-mapping-guided self-explanation as a computational account of the cognitive biases that reduce search effort and make this inference tractable. The model represents mathematical expressions as typed relational structures and uses structure mapping to identify corresponding source and target regions. For each changed target value, the corresponding source region serves as an anchor: it guides abductive search toward structurally relevant values and operations before broader alternatives, yielding ordered, executable candidate procedures with inspectable source evidence. Across 70 mathematical transformations containing 120 changed numeric components, the model recovered every intended procedure. It returned the intended procedure before any other computation producing the same target value in 104 subproblems (86.7%), compared with a median of 32 (26.7%) across 100 unguided runs that tested candidate calculations in random order. Our proposed model also tested 93.8% fewer combinations of values and operations than unguided search before reaching the intended procedures. These results provide an efficient, interpretable account of how relational structure can guide procedural learning and a testable hypothesis about human self-explanation from worked examples. --- ### The limits of exactness: On the failure of automatic differentiation in physics-informed machine learning Authors: Ameya D. Jagtap Published: 2026-09-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.33078v1 Automatic differentiation (AD) lets neural networks compute derivatives of governing equations to machine precision, and this precision has made it the computational backbone of physics-informed machine learning. Yet exactness in the mathematical sense is not the same as fidelity to the physics. Here I argue that a derivative can be numerically perfect and still be the wrong derivative for the problem at hand, because AD, by construction, has no notion of the physical structure a solution must obey. Convection and its associated directionality, diffusion, and dispersion are only the most visible instances of a much longer list that spans all branches of computational science and engineering, including conservation, thermodynamic consistency, symmetry, symplectic structure, positivity, monotonicity, and boundedness. Recognizing this broader gap reframes how the field should build the next generation of PDE-driven neural surrogates. --- ### Parameter-Efficient 3D Segmentation of Liver and Liver tumors: Depthwise factorization Scales Better Than Dense Convolution with Spatial Dimensionality Authors: Adham M. Alkhadrawi, Mohammed A. B. Mahmoud Published: 2026-09-27 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.33077v1 Three-dimensional dense convolutional networks are the strongest performers on volumetric medical image segmentation, but their parameter counts scale poorly: moving a dense k x k convolution to k x k x k multiplies its weights by k. We observe that depthwise separable factorization does not share this penalty. Because the cubic kernel term applies only to the depthwise stage while the pointwise projection, which dominates the parameter count, is unchanged, the same architecture grows by 5 % from 2D to 3D where a dense convolutional U-Net grows by 200 %. We exploit this asymmetry to build a 3D U-Net with 536,990 parameters, 24x fewer than an identical dense 3D U-Net. On MSD Task03 Liver (the Medical Segmentation Decathlon liver task, derived from LiTS), evaluated per case under five-fold cross-validation over all 131 public volumes, the model reaches a tumor Dice of 0.577 (95% CI (0.518, 0.633)) and a liver Dice of 0.947 (95% CI (0.941, 0.952)). Its liver Dice exceeds previously reported performance. Its tumor Dice exceeds their low-resolution configuration (0.4701) by 0.107 and their 2D configuration (0.5394), at approximately one twenty-fourth of the parameters and roughly half the in-plane resolution. Trained under identical conditions on a common held-out split, it exceeds a dense 3D U-Net on liver by +0.031 Dice (paired p = 0.006) and on tumor by +0.041 (95 % CI (+0.005, +0.081), paired p = 0.056), suggesting the factorization also acts as a regularizer in the small-data regime characteristic of medical imaging. We further show, on both LiTS and a 2D endoscopy benchmark, that a large fraction of the network's learnable spatial filters can be replaced by fixed shifts at no cost in accuracy, but that replacing all of them is measurably worse, the placement of spatial capacity matters more than its total amount. --- ### NutriVision: Ingredient-Conditioned Fusion and Prediction for Single-Image Food Nutrition Estimation Authors: Aman Kumar, Avinash Anand, Chaitanya Lakhchaura, Ashutosh Kumar, Akshita Abrol, Timothy Liu, Zhengkui Wang, Rajiv Ratn Shah Published: 2026-09-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.33076v1 Nutrition estimation is a fundamental task in consumer diet tracking, clinical dietetics, chronic disease management, sports and hospital nutrition, and broader food computing systems. The existing approaches have progressed along two largely separate axes, vision models that rely on calibrated RGB-depth captures and ingredient-aware methods that use textual cues but use limited multimodal fusion. We introduce NutriVision, an end-to-end framework that leverages visual geometry and ingredient semantics to estimate calories, mass, fat content, carbohydrates, and protein from a single RGB image and an optional ingredient list. It obtains the unavailable depth modality using DepthAnything-V3 and encodes ingredient descriptions using CLIP. It integrates three complementary mechanisms: (1) an \emph{Ingredient-Conditioned Frequency-Aligned Fusion Module (IC-FAFM)}, which uses textual guidance to reweight and align RGB-depth frequency components; (2) an \emph{Ingredient-Aware Mask-based Prediction Head (IA-MPH)}, whose gating and channel masks are conditioned on food identity; and (3) modality-specific \emph{Internal Semantic Modeling (ISM)} blocks. On the Nutrition5k dataset, NutriVision achieves a mean PMAE of $\mathbf{13.60\pm0.10\%}$, outperforming our IGSMNet implementation by $0.89$ percentage points and OmniFood8k by $2.90$ percentage points (both $p<0.001$). The module-level ablations identify the ingredient-aware prediction head as the primary architectural contributor, improving mean PMAE by $1.50\pm0.17$ percentage points ($p<0.001$). These results demonstrate that ingredient-conditioned prediction and frequency-aware RGB-depth fusion provide measurable gains for single-image nutrient estimation. More broadly, NutriVision offers a practical route toward nutrition-assessment systems that exploit geometric and semantic cues without requiring specialized depth-sensing hardware --- ### QureRadEmbed: Structuring Radiological Similarity through Attribute and Reasoning Supervision Authors: Janhavi Prabhu, Sahil, Shivam Ashok Shukla, Manoj Tadepalli Published: 2026-09-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.33075v1 Radiological similarity depends on disease relationships and on fine details such as laterality, lobe, severity, size, and certainty. Broad biomedical similarity can overlook these qualifiers, particularly when several attributes vary together. We introduce QureRadEmbed, a 4B radiology-aware encoder trained with two complementary signals: RadSim supplies deterministic, attribute-decomposed ranking targets, while RadThought aligns reports with hierarchical evidence and reasoning descriptions. A three-stage curriculum combines these signals with report triplets, finding perturbations, and single- and cross-attribute contrasts. The final model achieves 0.996 mean ordering accuracy across ten controlled synthetic attributes and raises Spearman correlation with the designed joint-attribute targets from 0.501 to 0.976. On external findings-to-impression retrieval, Recall@1 reaches 10.5% on Open-I, 12.4% on testing XR, and 42.9% on testing CT, compared with 6.6%, 5.7%, and 31.4% for its backbone. Frozen embeddings support finding extraction with only 100 labeled testing-XR reports (macro-F1 0.481 versus 0.412 for the backbone). Whole-report comparison costs 8.8 seconds per 1,000 pairs in our benchmark, versus 2,755.1 seconds for the generative evaluator GREEN. Sentence-level comparison improves sensitivity to local discrepancies, although generative evaluation remains stronger on several expert-rated and subtle-error tasks. The results support reusable radiology-aware representations for search, structured report indexing, and efficient report comparison. --- ### KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation Authors: Changxin Ke, Rui Zhang, Zixiang Fang, Zhenghong Li, Yuanbo Wen, Jiashuo Shen, Shuo Wang, Jiaming Guo, Ling Li, Qi Guo, Yunji Chen Published: 2026-09-27 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2609.33074v1 High-performance GPU kernels are essential to modern machine learning systems, yet automatically generating kernels that are both correct and efficient remains challenging. Existing LLM-based approaches face two major limitations: the scarcity of high-quality training data aligned with the model's current capabilities, and the inherent trade-off between kernel correctness and performance. To address these challenges, we propose KernelZero, a co-evolution framework that continuously improves GPU kernel generation through two specialized models: a Proposer that generates Torch modules from API sets and a Coder that translates them into CUDA or Triton kernels. KernelZero uses a frontier-driven module generation mechanism to continuously produce capability-aligned training modules based on the Coder's current weaknesses. It further introduces Correctness-Aware Group Relative Policy Optimization (CA-GRPO), which optimizes performance only after correctness becomes sufficiently reliable. By alternating the optimization of the Proposer and Coder, KernelZero forms an automatic curriculum that enables targeted and training-efficient capability improvement. Empirically, KernelZero-7B surpasses Claude-4.5-Sonnet on CUDA and DeepSeek-V4-Pro on Triton. On KernelBench Level 1 and 2, it achieves CUDA pass@1 scores of 75.8% and 69.6%, respectively, with pass@10 reaching 100% and 97%. On Triton, it achieves pass@1 scores of 77.2% and 72.5%, respectively. --- ### Algorithmic Harms Associated with Generative Model-Augmented Recommendation Systems Authors: Christine Herlihy, Xumei Xi, Shloka Desai, Kevin Bannerman Hutchful, Pedro Silva Published: 2026-09-27 Categories: cs.LG, cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2609.33073v1 In this work, we consider algorithmic harms that may arise as generative models are incorporated into machine learning platforms. We argue that existing harm taxonomies and threat models require extension to (1) address novel causal drivers of well-studied representational and quality-of-service harms; and (2) anticipate and mitigate endogenous harms, such as sanitization, which may arise when system inputs are misaligned with the system designer's objectives, or the generative model's inductive priors. To this end, we introduce an expanded taxonomy of algorithmic harms associated with the use of generative models in non-conversational recommendation systems. In addition, we offer a causal analysis of how problematic subsets of the (input, output) joint distribution can arise, in an effort to inform harms detection and mitigation efforts. --- ### Zero-Storage Procedural Neural Synthesis via Boundary Dynamics: Formal Verification in Lean 4 and Bare-Metal Gauntlet Validation Authors: Volkan Dağlı, Zerrin Dağlı, Dağhan Dağlı Published: 2026-09-27 Categories: cs.LG, cs.AI, cs.CR, cs.LO arXiv: https://arxiv.org/abs/2609.33066v1 Contemporary neural inference architectures rely on dense floating-point weight matrices stored in high-bandwidth memory (VRAM), incurring severe memory-wall bottlenecks and preventing native execution inside deterministic virtual machines like the Ethereum Virtual Machine (EVM). Verifying termination and arithmetic invariants for recursive dynamical systems over continuous domains is generally undecidable in the Blum-Shub-Smale model. Here, we present the formal verification and bare-metal empirical validation of WERR (Waves & Errors) and Phase III Orbital Error Dynamics (OED), a non-tensor decision paradigm that procedurally synthesizes non-linear decision boundaries on demand from a 24-byte coordinate seed $Θ= (c_x, c_y, \text{zoom})$ along the boundary of the Mandelbrot set ($\partial\mathcal{M}$). By projecting the recurrence $z_{n+1} = z_n^2 + c$ onto the modular residue ring $\mathbb{Z}/9\mathbb{Z}$ and the fixed-point domain $\mathbb{Q}_{16.16}$, we establish ten machine-verified theorems in Lean 4 (v4.34.1) with Mathlib4 and zero unproven conjectures (sorry): proving $\mathcal{I}_3 = \{0,3,6\} \subset \mathbb{Z}/9\mathbb{Z}$ ideal closure, universal fuel-bounded halting ($\le 9$ and $\le 12$ steps), absence of $\mathbb{Q}_{16.16}$ square overflow below $2^{63}-1$, non-constant boundary escape sensitivity, and a parametric EVM gas bound ($\le 22,557 \le 24,000$ gas). Evaluated on a 40-core Dual Intel Xeon server, the vectorized 36-iteration CPU kernel processes 100,000 decisions in 6.49 s (15,397 decisions/s, 0 Bytes VRAM, 15.15x speedup), while a sigmoidal outlier gate suppresses 100.00% of adversarial spikes while preserving 89.60% of clean baseline signals. --- ### Reading Too Much into Context: Passive Exposure Can Steer LLM Decisions Authors: Yuxiang Zheng, Lin Tian, Marian-Andrei Rizoiu Published: 2026-09-27 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.33065v1 Large language model (LLM) assistants can now search the web and consult external sources while completing user requests. These sources can provide useful evidence, but they can also introduce additional content into the model's context. Can such passive exposure steer a decision even when the added content provides no reason to change it? We examine the stability of model decisions on the same tasks with and without such external content. Across all open-weight and closed-weight models we test, exposure systematically shifts decisions, with effects reaching nearly 50 percentage points in closed-weight models. The same pattern appears with real-world online opinions. The influence also extends beyond subjective preferences. Such exposure can steer models toward choices that violate explicit user requirements and increase their acceptance of false claims. In short, what enters an LLM's context can influence its decision even when it should not determine it. --- ### LLM sequential decision making under uncertainty in biochemical domains Authors: Mattias Akke, Soojung Yang, Jurgis Ruža, Sathya Edamadaka, Rafael Gómez-Bombarelli Published: 2026-09-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.33061v1 Large language models (LLMs) are increasingly used to drive scientific discovery. Understanding how LLMs make decisions from new data and memory of the literature is vital before trusting them to design experiments under tight experimental budgets. However, their decision strategies are invisible in the current performance scores used to evaluate research agents. Here, we benchmark five frontier LLMs in a Bayesian Optimization setting against published statistical baselines on seven combinatorial datasets spanning protein engineering, reaction optimization, molecular design, peptide self-assembly, and catalysis. Performance is paired with direct measurements of model beliefs and actions, enabling highly resolved behavior analysis. A prompt ablation that progressively strips context separates memorization from chemical reasoning and from bare categorical optimization. Prior chemical knowledge helps in expectation, but with high variance and occasionally even harms performance. No configuration tested decisively beats a mean statistical baseline across domains. Belief-movement and Martingale diagnostics, corrected here for a measurement-noise bias that mislabels rational agents as irrational, show that models overreact to incoming data rather than entrenching on their priors in the contexts studied here. Interestingly, while LLM actions are exploitative, models sincerely intend to explore and consistently act on that intent. This failure is a competence gap arising from context-stickiness. Removing in-context history restores exploration, indicating that priors and data must be decoupled to achieve effective LLM-driven discovery. --- ### Deep Learning Techniques for Phoneme Recognition in Italian Children' s Speech Authors: Nicola Barbaro, Cristina Gena, Francesco Petriglia, Andrea Meirone, Alessandro Mazzei, Arianna Viotti Published: 2026-09-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.33060v1 Speech therapists often face difficulties diagnosing impairments due to the lack of efficient tools for transcribing speech into the International Phonetic Alphabet (IPA). This work addresses this challenge with Broca, a Conformer-based deep learning system pretrained on 8 days of adult speech and fine-tuned on a 165-minute dataset of Italian child speech collected through a range of standardized diagnostic tests for children aged 3.5-6.5. Broca was optimized to handle phonetic variability in children's speech, including tone, accent, and speech errors, and achieved a state-of-the-art weighted Phoneme Error Rate of 13.36% on Italian speech. Remarkably, this performance was obtained using less than three hours of child-specific data, underscoring the model's efficiency and robustness in low-resource clinical settings. This work demonstrates that accurate, vocabulary-independent speech-to-IPA transcription can be achieved with minimal data, paving the way for more accessible, data-efficient tools to support speech assessment and diagnosis. --- ### Large Language Models Substantially Compress Well-Being Inequality but Largely Preserve Its Socioeconomic Structure Authors: Nattavudh Powdthavee Published: 2026-09-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.33055v1 Research using large language models (LLMs) to generate synthetic populations has repeatedly shown that model outputs compress the diversity of human experience. This has raised doubts about whether LLM-generated data can capture meaningful differences within populations. We show that such compression does not necessarily erase the social structure of human heterogeneity. Using 93,901 respondents from 66 countries and territories in Wave 7 of the World Values Survey, we ask six LLMs to predict respondents' life satisfaction from demographic, socioeconomic, and attitudinal profiles. All six models substantially understate the overall dispersion of life satisfaction. Yet after normalizing for these differences in scale, they largely reproduce the human income gradient in well-being inequality: lower-income groups remain relatively more heterogeneous than higher-income groups. The pattern is robust to country fixed effects, equal-country weighting, WVS survey weights, and observed demographic composition, and it extends directionally to employment, education, and perceived control. Fidelity is weaker for extreme outcomes and country-specific gradients. These results show that the amount of heterogeneity preserved by an LLM and the way that heterogeneity is distributed across social groups are distinct properties. LLM-generated populations can therefore substantially compress human variation while retaining meaningful information about where that variation is concentrated. --- ### BudgetVerify: Budget-Tiered Verification for Financial QA Authors: Janet Jenq, Hongda Shen Published: 2026-09-27 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.33052v1 Financial question answering often requires precise numerical extraction, unit handling, and arithmetic over tables and text, but applying expensive verification uniformly wastes test-time compute. We propose BudgetVerify, a budget-tiered generator-verifier framework that routes each generated answer to one of three verification tiers: no verification, lightweight check-and-revise, or higher-cost solve-first-then-compare verification. The router is trained from offline correctness and token-cost outcomes and, at test time, selects a verification tier using information available before verification, including the question, context statistics, the generated answer, and associated generator metadata. The selected tier either returns the generated answer directly or invokes the corresponding verifier. Across six commercial and open-weight base models, BudgetVerify consistently produces more efficient accuracy-cost Pareto frontiers than fixed verification policies by selectively allocating stronger verification only when it is useful. Although absolute performance varies across models, these efficiency gains and the resulting qualitative frontier shape are consistent across generator models. ---