# Research Papers — 2026-10 · bundle page 156 of 156 > Full-text markdown of papers #7751–7799 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/156 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/155.md) ### Role-aware Heuristic Episodic Attention for Conversational LLMs Authors: Wanyang Hong, Zhaoning Zhang, Yi Chen, Libo Zhang, Baihui Liu, Linbo Qiao, Zhiliang Tian, Dongsheng Li Published: 2026-10-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.00958v1 Large language models often lose track of persistent instructions and relevant information as multi-turn conversations grow. We study this cumulative contextual decay through three related failure modes: attention pollution, dilution, and drift. We propose REA (Role-aware Heuristic Episodic Attention), a context-management framework that assigns different persistence and representation policies to instructions and episodic interactions. Instructional Memory retains identified global constraints in a dedicated prefix. Episodic Memory preserves user inputs and compresses model replies, while heuristic retrieval selects raw text, compressed representations, or omission for each historical turn. On Long-MT-Bench+, REA improves the judge score from 6.32 to 7.36 on a 10-point scale, a 16.5% relative gain over the Vanilla baseline, and reduces average latency by 2.91$\times$. Additional evaluations show aggregate gains on three backbones spanning 1.7B-7B parameters and on Chinese and English role-playing tasks. These results support role-aware context management as a practical approach to maintaining conversational continuity and instruction adherence. --- ### Beyond Leaderboards: Tokenomics of Agentic Small Language Model Ensembles Authors: Alexei N. Skurikhin, Emily M. Taylor, Nathan A. DeBardeleben Published: 2026-10-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.00954v1 As large language models (LLMs) move from standalone assistants into agentic workflows, evaluation must extend beyond scalar leaderboard accuracy to account for operational reliability, cost, latency, and token efficiency. We use an agentic ensemble of small language models (SLMs) with an SLM-judge-mediated feedback loop as a case study for such beyond-leaderboard evaluation. On the 541-prompt IFEval benchmark, the best ensemble achieves 97.34% strict prompt accuracy, exceeding the strongest standalone LLM baseline, gpt-5.4, by 5.81 percentage points while operating in a lower-cost regime. We then analyze the tokenomics and operational behavior behind this gain, including cost per sample, token composition, useful-output goodput, feedback-loop recovery, latency decomposition, and performance across instruction categories and constraint counts. Our results show that agentic SLM ensembles can trade additional test-time tokens and orchestration overhead for improved instruction-following fidelity, motivating multi-dimensional evaluation protocols for future agentic AI systems. --- ### Two Clocks in Diffusion MLLMs: When Answers Stabilize Before Rationales Unfold Authors: Keuntae Kim, Yong Suk Choi Published: 2026-10-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.00953v1 An answer candidate in a masked diffusion MLLM can stabilize while its rationale is still unfolding. We distinguish retrospective stabilization of the logged candidate from token commitment, and examine these two clocks relative to rationale generation. Analyzing our results across three visual question-answering benchmarks, we find that 89.4-98.1% of the rationale-side canvas remains unwritten at stabilization in single-block, EOS-suppressed LaViDa runs. On V*Bench, reducing block length from 128 to 8 changes this fraction from 89.4% to 1.7%, together with answer coverage and the eligible observation window. Under EOS-enabled prompting, direct instructions improve Nemotron's overall accuracy by 15.0 and 19.5 percentage points on M3CoT and ScienceQA, but reduce LaViDa/V*Bench accuracy by 11.0 points. A symmetric decomposition associates the larger absolute component of each change with coverage rather than conditional accuracy. Matched-canvas image ablations measure visual sensitivity alongside answer stabilization, separating the two temporal readouts. Together, these measurements distinguish answer stabilization, rationale unfolding, and visual sensitivity, and identify coverage as the larger component of the prompting differences. --- ### A Matched-Budget Audit Framework for Recaptioned Image-Text Supervision Distributions Authors: Giyeong Oh, Junghun Park, Yuhan Bae, Youngjae Yu Published: 2026-10-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.00952v1 Recaptioned image-text corpora are now standard for text-to-image (T2I) training, with vision--language model (VLM) captioners replacing sparse alt-text by dense descriptions. A recaptioned corpus is a supervision distribution induced by a documented captioning policy ($π$), captioner ($V_c$), and source corpus ($C$). Length-correlated proxies miss caption-register artifacts and downstream T2I benchmarks entangle the corpus with training choices, so this distribution is hard to audit at corpus scale. We introduce a reusable matched-budget audit framework for recaptioned supervision distributions $D_{π,V_c,C}$: at a fixed text budget of $B = 64$ it reports a five-axis profile spanning prompt-side coverage, image-conditioned faithfulness, and caption-surface health, with claimed controllable basic units (CBU) as the common claim unit. We instantiate the framework on seven paired comparisons over five public source corpora. Across the four cross-corpus pairs, the released surface raises supported CBU per caption by $+3.39$ to $+6.36$ under both Qwen and Gemma Judges, and on CC12M the same framework exposes a long-vs-dense frontier that is consistent across both judges and four budgets. We release the audited multi-source recap corpus ($\approx$ 490M) together with the audit-artifact bundle. --- ### PG-SFT: Balancing Capability Acquisition and Retention in Offline Agent Fine-Tuning Authors: Ronghua Li, Zi Liang, Zhishan Li, Shinan Liu Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.00949v1 Supervised fine-tuning (SFT) on offline agent trajectories is the standard approach for training specialized tool-using agents, but forcing models to imitate reasoning and actions token by token may harm other capabilities (e.g., general reasoning, tool calling, code generation) of the base model. In this work, we focus on studying \emph{how to better balance the trade-off between acquiring new capabilities and preserving existing ones during agent trace SFT}. By comparing several baselines in our setup, standard SFT improves the target benchmark while lowering several non-target benchmark scores; meanwhile, simply constraining distributional drift using KL penalty or limiting the update magnitude did not avoid this regression trend. Motivated by recent token-wise adaptive learning objectives, this work proposes \textbf{Privilege-Guided SFT (PG-SFT)} to leverage turn-level information gain of agent trajectories as an indicator to adjust supervision strength. PG-SFT yields a more favorable observed trade-off on the evaluated benchmarks, substantially reducing distributional drift and broad capability degradation at the cost of slight degradation in target-task performance. Our findings suggest that balancing the acquisition--retention trade-off depends not only on whether the model is anchored to its base behavior, but also on where and how strongly supervision should depart from that behavior.} --- ### GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution Authors: Geyi Yang, Zikun Qu, Xiang Li, Zhiyong Wang, Min Zhang, Shipei Zeng, Zhongxiang Dai Published: 2026-10-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.00948v1 The executable harness surrounding a GUI model determines how observations are assembled, actions are executed, and verification, recovery, and termination are controlled. Compared with harness optimization for non-GUI agents, automatically optimizing this harness poses three coupled challenges: reconciling model intent with observed visual effects, diagnosing failures under variable execution outcomes, and identifying recurrent failure patterns across tasks and translating them into reusable runtime changes. We introduce GUI-HARVEST, an automatic harness optimizer that enables self-improving GUI agents with frozen backbone models. First, to ground diagnosis in observed action effects, it aligns model outputs and executed actions with before-and-after screenshots, tying findings to specific interface transitions. Second, to account for execution variability, it treats repeated runs of the same task as a joint evidence unit, using within-task comparisons to locate outcome-relevant behavioral differences. Third, it consolidates verified findings across tasks into recurring failure patterns, maps them to bounded source-code edits with predictions recorded before evaluation, and checks the predicted behavioral effects alongside task performance through repeated execution. Experiments on OSWorld-Verified show consistent held-out gains across six general-purpose open, GUI-specialized open, and proprietary backbone models; Qwen3-VL-32B-Instruct gains 12.33 points on the full suite. Frozen-harness transfer improves GPT-5 by 13.87 percentage points on WindowsAgentArena at 50 steps without further optimization. With the same backbone and initial harness, GUI-HARVEST outperforms Self-Harness and Meta-Harness, suggesting that GUI-specific diagnosis and validation help harness improvements generalize to unseen tasks. The code is available at https://github.com/GaryYang12345/GUI-HARVEST. --- ### ABDA-NL: A Natural-Language Scenario Explorer for Argument-Based Reasoning Authors: Shawn Bowers, Martin Caminada, Haoyang Liu, Bertram Ludäscher Published: 2026-10-01 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2610.00947v1 ABDA-NL adds a natural-language interface to ABDA, a system for argument-based discussion using ASPIC- knowledge bases under grounded semantics. Users see which conclusions are accepted, rejected, or undecided, open an interactive rendering of the grounded discussion game to learn why, explore what-if alternatives by suspending assumptions and rules or changing preferences, ask questions that are answered from a scenario's reference documents, and author new facts, assumptions, and rules in plain English. A large language model provides the bridge between language and formalism: it answers questions from the documents and the current state of the scenario, and it translates plain-English edits into candidate formal statements. The deterministic ABDA engine remains the sole source of arguments, attacks, and acceptance labels, and every proposal of the model is validated and confirmed by the user before it takes effect. --- ### ReHoPER: Receding-Horizon Planning for Enhanced Reasoning Authors: Saeed Ahmadnia, Cornelia Caragea Published: 2026-10-01 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.00940v1 We propose ReHoPER, an inference-only, zero-shot method that improves large language models' reasoning by generating and answering intermediate questions along multiple paths before the final answer. It iteratively plans a horizon of candidate intermediate questions, selects one to answer, and replans from the updated history. ReHoPER is task-agnostic, using the same generic instructions across datasets and models without labeled data or task-specific prompt design. Across multiple datasets, including iLLC, a new controlled benchmark for compositional reasoning, ReHoPER outperforms strong baselines, with the largest gains in the most compositional settings. Our implementation and the iLLC generator are publicly available to support future work. --- ### Joint Branch-Space Transform Coding for Diffusion Activation Quantization with Classifier-Free Guidance Authors: Mingrun Jiang, Yuejia Liu, Zishan Shao, Ting Jiang, Qinsi Wang, Hancheng Ye, Yixiao Wang, Rui-Feng Wang, Kangning Cui, Yixuan Chen, Fan Yang, Xiang Cheng et al. Published: 2026-10-01 Categories: cs.CV, stat.ML arXiv: https://arxiv.org/abs/2610.00930v1 Post-training quantization for diffusion models increasingly exploits timestep, feature, and layer structure. While recent work has begun incorporating CFG structure into diffusion quantization, activation quantization still operates independently across conditional and unconditional coordinates, leaving cross-activation structure unexploited. We show that matched CFG activations form a strongly correlated two-dimensional source and that, under a fixed bit budget, the choice of branch coding basis materially affects quantization fidelity. Motivated by this observation, we introduce branch-space transform coding, which rotates matched CFG branches via an offline derived 2x2 orthogonal matrix, requiring minimal modifications to model parameters or the quantization pipeline. We further derive the Guidance-Correlation Branch Transform (GCBT), which jointly incorporates the CFG guidance direction and cross-branch second moments. Under an equal-rate quantization-noise surrogate, GCBT admits a closed-form per-layer solution without gradient optimization or angle search. Applied on top of existing diffusion PTQ methods, GCBT yields statistically significant fidelity gains in most evaluated comparisons with no statistically significant degradation, while leaving the underlying host quantization pipeline unchanged. --- ### Platonic Task Arithmetic Authors: Junghwan Park, Woojin Cho Published: 2026-10-01 Categories: cs.LG, cs.CV, stat.ML arXiv: https://arxiv.org/abs/2610.00929v1 Models specialized for the same task converge to similar behavior, yet the parameter updates that produce it share no common coordinate system, so weight-space task arithmetic stays confined to a single model and cannot cross architectures without a structural correspondence. Drawing on Plato's allegory of the cave, we hypothesize that these model-specific updates are shadows of one shared, model-agnostic object, which we call the platonic task vector. To make it operational for models that pair an image or audio encoder with a text encoder, we introduce Universal Task Descriptors: matrices whose shape is independent of architecture and embedding dimension, which record a task's functional effect and support addition and negation as matrix operations. Transferring a descriptor into a target means editing the target until it reproduces the descriptor on the task's unlabeled probe images and class-name prompts, requiring no per-image labels. We realize this edit in two ways. First, the descriptor factorizes into a shift field on image embeddings, so a single least-squares solve yields a linear operator that folds into the target's last layer as a weight edit; by linearity, a bank of such operators admits any composition at any strength as a signed sum. Second, a low-rank adapter trained on the same objective reaches every layer and fits compositions jointly, at the cost of one optimization per edit. Heterogeneous models share this object only partially, with a model-specific residual comparable in norm to the shared component, yet cross-model transfer still retains 74-80 percent of the gain of the target's own descriptors. Experiments across six model families, eight classification tasks, and an audio-text setting show that task knowledge transfers and composes across heterogeneous models under both realizations. --- ### Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations Authors: Jungwon Park, Changin Choi, Jimyeong Kim, Nojun Kwak, Wonjong Rhee Published: 2026-10-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.00928v1 As large language models are increasingly deployed across diverse downstream tasks, efficient task adaptation has emerged as a central challenge. In response, a wide range of task adaptation methods have been proposed, spanning parameter-efficient fine-tuning, in-context learning, and embedding-injection approaches. However, these lines of work have largely evolved within individual paradigms, leaving their cross-paradigm relationships and trade-offs underexplored, especially for recently emerging embedding-based adaptations. This survey presents a unified framework that categorizes task adaptation methods by where and how task information is encoded: model weights, input prompts, or injected task embeddings. We provide a comprehensive taxonomy that integrates these paradigms, analyze their key strengths and limitations to explain how different adaptation paradigms have evolved, clarify relationships across paradigms, and highlight open problems for future research. --- ### Rate-Optimal Algorithm for Adversarial Linear CMDPs Authors: Kihyun Yu, Honghao Wei, Dabeen Lee Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.00927v1 We study episodic adversarial linear constrained Markov decision processes (CMDPs) with unknown transitions, where both the loss and constraint functions may vary adversarially across episodes. The best previous algorithm achieves $\widetilde{\mathcal{O}}(K^{3/4})$ regret and cumulative constraint violation, leaving a gap to the optimal $\widetilde{\mathcal{O}}(\sqrt{K})$ dependence on the number of episodes $K$. We close this gap by proposing a new primal dual algorithm that achieves $\widetilde{\mathcal{O}}(\sqrt{K})$ regret and cumulative constraint violation without assuming Slater's condition. The main challenge is that learning linear CMDPs requires uniform concentration over a value function class with a controlled covering number, whereas standard techniques in constrained online learning, such as policy mixing, can make this class more complex. Our algorithm combines adaptive Follow the Regularized Leader (FTRL), contracted value estimation, and an exponential Lyapunov function. An adaptive dual regularizer offsets the dependence on the dual weights in the primal regret bound, removing the need for policy mixing. We further show that the normalization in the FTRL update bounds the policy parameters independently of the magnitudes of the dual weights, which explains why the resulting policy class remains compatible with uniform concentration. Under feature access, the computational complexity is independent of the size of the state space. --- ### A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform Authors: Chengkai Xu, Yiming Cui, Jiaqi Liu, Yicheng Guo, Cheng Qin, Geyuan Zhang, Xinwei Dong, Shiyu Fang, Peng Hang, Jian Sun Published: 2026-10-01 Categories: cs.RO, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.00926v1 Autonomous driving is a cornerstone technology for the future of intelligent transportation, where end-to-end learning has emerged as a transformative paradigm that directly maps multimodal sensory inputs to driving actions through unified differentiable models. While offering advantages, the effectiveness of end-to-end autonomous driving (E2E-AD) is ultimately determined by the quality of its training ecosystem. This paper provides a comprehensive review of training methods and ecosystem for E2E-AD. We introduce a Data-Strategy-Platform taxonomy that conceptualizes training as an interdependent system. The data layer defines what can be learned, the strategy layer governs how learning aligns with driving objectives, and the platform layer supports scalability and continuous evolution. Within this framework, we survey recent advances across data-centric pipelines, learning paradigms, and training infrastructures, and analyze their interplay in shaping model performance, robustness, and deployability. Finally, we reflect on current limitations and articulate a forward-looking vision that emphasizes a shift from data quantity to data value, from isolated optimization to foundation-driven generalization, and from static training to integrated training-testing loops, aiming toward robust, scalable, and trustworthy autonomous driving systems. We maintain a continuously updated repository tracking cutting-edge literature and works at \href{https://github.com/Jiaaqiliu/Awesome-Training-Ecosystem-for-E2E-AD}{Our Project Page}. --- ### EyeTAG: Eye Trajectory-Aware Gaze Estimation Authors: Jungmin Lee, Niamat Ullah, Yoseob Han Published: 2026-10-01 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.00922v1 Gaze estimation under natural head-eye motion underpins applications from driver monitoring to human-computer interaction. Single-frame methods predict each frame independently, so consecutive outputs fluctuate as jitter. Multi-frame methods reduce this, but they learn motion implicitly inside appearance features, so the gaze trajectory is never an explicit variable. We propose EyeTAG (Eye Trajectory-Aware Gaze Estimation), a causal multi-frame framework built around an explicit first-order gaze prior: at each step it differentiates its own recent predictions and feeds the resulting trajectory back as a compact kinematic token. Because differencing is translation-invariant in gaze space, this token carries subject-invariant motion rather than personal gaze offsets. Face and eye streams supply visual evidence, fused by cross-attention and a causal Transformer decoder. EyeTAG reduces the mean angular error by about 1.0$^\circ$ on Gaze360 and performs on par with the strongest baseline on EVE (2.56$^\circ$ vs. 2.58$^\circ$). Within-model ablations, which keep the encoder and the rest of the architecture fixed and vary only the gaze history, show that the differential formulation, rather than temporal context alone, removes the systematic saccade bias that persists even with an absolute gaze-history prior. Our code is available at https://github.com/peter8366/EyeTAG. --- ### In CEM, a World Model Is Also a Proposal Mechanism Authors: Oliver Obst, Frieder Stolzenburg Published: 2026-10-01 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2610.00921v1 The cross-entropy method (CEM) uses world-model scores to select action sequences and fit the distribution sampled in its next iteration. A scoring error can therefore change both the present decision and the candidates considered later. We evaluate these two roles separately. Four types of predictive model generate CEM traces, and every model rescores every saved candidate pool. Executing the same candidates in the environment provides a reference elite set and proposal update. Across twelve independently trained task-seed units on Walker and Cheetah, the pre-specified proposal distance falls from the first to the final CEM iteration in every unit. Proposal widths contract and fitted means separate relative to the remaining search width. Pairwise ranking agreement stays near chance on Walker and declines on Cheetah; elite-set agreement does not improve. This comparison shows greater variation between scorers than between pool sources on Cheetah; Walker has variation in both and in their pairings. We use the original six units to select Random nonlinear for a one-update intervention, without inspecting intervention outcomes. Replacing its first model-ranked update with an environment-ranked update lowers final realised selected-sequence cost in those six units and in six further units held out from the selection. --- ### Finding the Right Fit: Model-Harness Interactions across Agent Tasks Authors: Yixuan Li, Yiyun Zhou, Yao Long Teng, Fuchao Yang, Yanchen Deng, Zhiyi Lyu, Xuyu Dong, Feng Chen, Bo An Published: 2026-10-01 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2610.00917v1 Choosing an agent system means choosing both a language model and the harness through which it acts. We ask whether a strong model, harness, or pairing stays strong when the setting changes. We evaluate 66 configurations: four configurable harnesses (OpenHands, DeepSeek Harness, PI, and openJiuwen) paired with five models on TUA-Bench, ALE-CLI, and Terminal-Bench 4, plus the native Codex-GPT and Claude Code-Claude pairings. Model rankings reverse across harnesses. On Terminal-Bench 4, Claude leads GPT by 7.94 points in OpenHands but trails it by 30.16 points in PI. For four of the five models, the best harness changes from one benchmark to another, yet some pairings hold: openJiuwen gives Kimi its highest score on all three benchmarks, by 5.61 to 11.11 points. A model's own vendor harness is not reliably its best, and higher cost does not reliably buy a higher score. On Terminal-Bench 4, GPT scores higher under PI than under DSH at less than a quarter of the cost per task. Matched trajectories suggest why fit varies. Models start almost all repairs themselves, so much depends on whether the harness hands failures back in a form the model can use. GPT does best with PI's lean scaffold, while Kimi, which often issues malformed tool calls, does best in openJiuwen. We argue that the model, the harness, and the task should be evaluated together, and we release the harness adapters, evaluation code, and all 6,204 scored trajectories at https://github.com/liyix/finding-the-right-fit and https://huggingface.co/datasets/yixuanli97/finding-the-right-fit. --- ### OR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Framework Authors: Jinzhi Bu, Haixin Tang, Huanan Zhang Published: 2026-10-01 Categories: cs.AI, math.OC arXiv: https://arxiv.org/abs/2610.00912v1 Large language models can translate business descriptions into optimization models, but executable code may misrepresent constraints or objectives. A solver can then return an optimal solution to the wrong problem. Even when the solution satisfies the intended operating rules, a better plan may exist. For organizations that repeatedly use optimization modeling, an LLM-based framework should produce accurate formulations at low cost and, ideally, run locally. We study how to verify improvements and allocate attempts across LLMs that differ in price and capability. We develop OSCAR (Optimization modeling by Simulator, Coder, And Reviewer), which uses an offline Simulator certified against labeled decision examples to compare candidates and continues searching beyond feasibility. We model the search for the next certified improvement as sequential decisions under unobserved difficulty: which LLMs to call and when to stop. In a simplified known-prior setting, we give conditions under which cost-ordered escalation is optimal. For general menus, we derive a prior-free competitive guarantee. On five benchmark problems, OSCAR achieves 95% to 100% accuracy at the reported settings using two small open-weight LLMs, each deployable locally on a single GPU. Their single-attempt accuracies average 29% and 48%. In five runs per problem, Codex and Claude Code incur average token costs 3.1 and 5.8 times OSCAR's, respectively. OSCAR supports open-weight models locally or in the cloud, depending on budget and confidentiality requirements. Firms should maintain labeled decision examples of feasible and infeasible decisions to clarify plain-language operating rules. OSCAR follows these labels when an LLM's interpretation conflicts with them. As LLM capabilities and prices change, OSCAR's simple operating rules and adjustable settings help firms adapt their model choices and benefit from these advances. --- ### Block Optimism for Nonstationary Bandits with Latent Linear Dynamics Authors: Taehyun Hwang, Hyunjun Choi, Heesang Ann, Min-hwan Oh Published: 2026-10-01 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.00911v1 We study an endogenous nonstationary stochastic bandit problem with latent linear dynamics, where actions affect both immediate rewards and the future evolution of an unobserved latent state. Rewards are bilinear in the current action and latent state, inducing history-dependent rewards and a nontrivial long-horizon planning problem. The existing explore-then-commit approach achieves $\tilde{O}(T^{2/3})$ regret by uniformly exploring to estimate the latent dynamics and then committing to an optimized open-loop action sequence. We show that this rate can be improved via adaptive block-level optimism. Our key step is a cyclic approximation: under stable dynamics, the infinite-memory reward process can be truncated, and the open-loop benchmark can be approximated by optimizing a finite-memory block-level proxy. Building on this reduction, we propose a UCB-based block algorithm that maintains confidence sets for the truncated dynamics parameters and selects blocks optimistically. We prove a regret bound of order $\tilde{O}(\sqrt T)$, significantly improving over the previous $\tilde{O}(T^{2/3})$ guarantee for the same model. To the best of our knowledge, this is the first $\tilde{O}(\sqrt T)$ regret guarantee for latent linear-dynamics bandits with bilinear reward observations and an open-loop action-sequence benchmark. --- ### The Geometry of Contextual Relations: Language Models Address Facts by Order of Mention Authors: Yufa Zhou Published: 2026-10-01 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.00910v1 Human reasoning depends on how objects are related within propositions. \textit{How do relations organize the language representations of contextual contents?} We give an LLM a list of facts in its context (e.g., \emph{Alice eats an apple. Bob eats a pear.}) and measure how its hidden state changes when the question switches from what Alice eats to what Bob eats. Averaged over many lists, this change is a steering vector, which we call the \emph{ordinal vector}. It points to a fact by its \emph{order of mention}, the order in which the facts were stated in the context. We find that LLMs represent the fact a question asks about by its order of mention, not by the name the question contains. We state this as the \textit{ordinal addressing hypothesis}: each order of mention has a \emph{fact address} in the model's state, shared by all contexts, and a question moves the state to the fact address of the fact it asks about, while the context supplies what that fact says. Across Qwen, Gemma, and Llama, fact addresses are (1) \emph{ordered by mention}: query states are organized by the order of facts, not of names, even when one fact has multiple subjects; (2) \emph{steerable}: added to a question about the first fact of a new list, the ordinal vector makes the model answer with the second fact of that list; (3) \emph{low-rank}: they span a low-rank subspace in which the first-mentioned fact is the easiest to reach, surprisingly similar to human recall; and (4) \emph{emergent}: they are shared in late-middle layers, hold from 1.5B to 32B parameters, and form early in pretraining. Language models reach a stated fact by where it was mentioned, deepening our understanding of LLM reasoning. --- ### STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling Authors: Abdalla Mohamed, Ashraf Aboulnaga Published: 2026-10-01 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2610.00907v1 Relational foundation models (RFMs) are pretrained once on a collection of relational databases and prediction tasks, and then applied zero-shot to previously unseen databases and tasks. To make a prediction for a target row, an RFM samples a neighborhood of rows linked to that row through foreign keys and uses this neighborhood as its inference context. Lowering inference cost is an important goal for any foundation model, and for RFMs this cost grows with the size of the context. The simplest ways to shrink the context is to drop some of the sampled rows, but this ignores the semantics of the database schema, so it is as likely to discard informative rows as uninformative ones. We propose STEER, a sampling approach that shrinks the inference context by concentrating it on the tables most relevant to the prediction task at hand. STEER obtains relevance information by prompting a large language model to rank the foreign-key edges of the database schema into relevance tiers for the given task, and then maps each tier to a probability of following that edge during traversal. Because the ranking uses only the schema, it is computed once per task and reused across all subsequent predictions, amortizing its cost. We evaluate STEER on three state-of-the-art RFMs (RT, RT-J, and Griffin) and show that it reduces inference context size by about 40% on average while maintaining, and in some cases improving, prediction accuracy. --- ### ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization Authors: Sungho Park, Wonjoong Kim, Jue Zhang, Wook-Shin Han, Pengfei Gao, Chanyoung Park, Yongqiang Yao, Rao Fu, Elsie Nallipogu, Qingwei Lin, Victor Rühle Published: 2026-10-01 Categories: cs.AI, cs.CL, cs.LG, cs.MA, cs.SE arXiv: https://arxiv.org/abs/2610.00906v1 Automated harness optimization can substantially improve LLM agents by iteratively updating their prompts, tool interfaces, and control logic from execution feedback. However, existing methods primarily optimize how the harness is updated while largely fixing which training scenarios generate the feedback that drives those updates. As the harness evolves, the scenarios most useful for further optimization can change, suggesting that the training curriculum itself should adapt alongside the harness. We formulate this missing dimension of harness optimization as an automated curriculum learning problem and introduce ActiveSaddler. ActiveSaddler models the evolving curriculum as a non-stationary bandit with dynamically instantiated optimization targets. It abstracts recurring failures into reusable failure-pattern arms, estimates the potential learning progress from further targeting each pattern, and adaptively balances revisiting known weaknesses with exploring unseen scenarios for new ones. Optimization outcomes continually update both the set of discovered failure patterns and their priorities, allowing the curriculum to co-evolve with the harness. Experiments on GAIA2 and Terminal-Bench 2.0 show that ActiveSaddler consistently discovers stronger harnesses, improving test Pass@1 by 4.4 and 7.5 percentage points over the same harness optimizer using a scenario order fixed before optimization, respectively. Ablations further show that these gains depend on dynamically constructing optimization targets, estimating their evolving utility, and balancing continued optimization with new failure discovery. Together, these results establish automated curriculum learning as a new crucial optimization dimension for harness optimization. --- ### Understanding Issues, Causes and Solutions in Open-Source LLM-based Multi-Agent Systems Authors: Asad Ur Rehman, Syed Mohammad Kashif, Ruiyin Li, Peng Liang, Zengyang Li, Arif Ali Khan Published: 2026-10-01 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2610.00905v1 With the advancement of LLM-based multi-agent systems (MAS), an increasing number of opensource projects are adopting multi-agent architectures as the foundation of their core functionality. Although research and practice on MAS have attracted considerable attention, limited studies have explored the challenges faced by practitioners of open-source LLM-based MAS, the causes of these challenges, and potential solutions. To address this gap,we conducted an empirical study to understand the issues that practitioners encounter when developing and using open-source LLM-based MAS, the possible causes of these issues, and potential solutions. We collected 22,848 closed issues from 21 open-source LLM-basedMASand applied a mixed automated and manual filtering approach to reduce the dataset to 944 issues related to LLM-based MAS.We then analyzed these issues to understand the frequent issues encountered by practitioners, their underlying causes, and potential solutions. Our study results show that (1) Orchestration & Execution Issue is the most common issue faced by practitioners, (2) Workflow Problem, Tool Integration Problem, and Memory Problem are identified as the most frequent causes of the issues, and (3) Optimize Workflow is the predominant solution to the issues. Based on the study results, we derive empirically grounded implications for practitioners and researchers aimed at improving orchestration, tool integration, and memory mechanisms in LLM-based MAS. --- ### Screw Attention: Rigid-Body Algebra Inside a Transformer Authors: Aly Magassouba Published: 2026-10-01 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2610.00904v1 Learned manipulation policies rediscover from data the spatial relations that rigid-body mechanics supplies in closed form. This costs data, and it leaves the policies fragile to geometric changes in the scene. We present Screw Attention, a transformer layer in which the relation between two bodies is a spatial transform rather than a graph edge. Every token is a body with a pose. Each pair of tokens carries the relative pose and, for robot joints, the joint screw. Messages are transported along this relation into the receiver's frame, while the attention scores see only frame-invariant quantities. By construction, the messages are equivariant to an independent change of frame at every token, and a single layer can express the velocity recursion of rigid-body mechanics. On simulated manipulation tasks, Screw Attention matches or outperforms controls of the same size, including graph, transformer and flat networks on LIBERO-Spatial. With 16,162 parameters it reaches 97.3% on LIBERO-Spatial from object poses (without images or language), above a flat network with 27x more parameters. Under a change of per-link frame convention its success is unchanged, while every other learned network falls below 3%. Placed on an analytic controller as a gated residual, it raises insertion success by 17.3 points. It is unaffected by pose noise up to 10,mm and by joint offsets within the factory calibration of a Franka arm. These results suggest a criterion: geometry is decisive when the task requires relations between frames that no other part of the system supplies. Code and trained policies will be released. --- ### Sharpen Before You Adapt: Data-Free Entry-State Sharpening for Test-Time Reinforcement Learning Authors: Zhanming Zhang, Vinoth Selvendran Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.00903v1 Test-time reinforcement learning (TTRL) adapts language models on unlabeled test problems using supervision derived from their own samples. This makes the checkpoint's \emph{entry state} consequential: a diffuse policy provides noisier self-supervision and may spend much of a limited adaptation budget merely concentrating probability mass before reliably expressing capability it already possesses. We propose \textbf{entry-state sharpening}: use data-free training \emph{before} TTRL to prepare a general-purpose checkpoint in a state that subsequent label-free adaptation can exploit more efficiently. The idea is not tied to one training recipe; different data-free objectives can move the same base model to different entry states. Across five data-free checkpoints derived from Qwen3-4B and evaluated under an identical 15-step TTRL protocol, entry policy entropy strongly rank-orders endpoint conversion efficiency, a reliability-to-reachability measure (Spearman $ρ=-0.90$; $ρ=-0.99$ after controlling for entry reachability). The contrast across objectives is striking: R-Zero remains diffuse at $3.39$ nats and finishes below the untuned base in 6/6 matched comparisons across MATH, GPQA, and AMC, whereas SPIRAL reaches $0.07$ nats and achieves the highest post-TTRL accuracy on MATH and GPQA despite its self-play stage using no math training data. An in-domain label-free self-distillation intervention further shows that the entry state can be deliberately sharpened. These results motivate treating checkpoint preparation as a \emph{state-control problem}: use data-free training to improve TTRL readiness, with entry entropy as a label-free control signal and reachable capability as the constraint. --- ### Mean field games as a tool for AI safety: a worked example from the July 2026 Hugging Face incident Authors: P. Jameson Graber Published: 2026-10-01 Categories: math.OC, cs.AI, cs.GT arXiv: https://arxiv.org/abs/2610.00902v1 One way to make AI systems safe is to shape what the system is: its objective and dispositions. We take a complementary route: treat the agents' characteristics as partly unknown and ask what structure of interaction ensures that bad collective outcomes are not equilibria. Mean field games suit this when many interchangeable agents are coupled through an aggregate. We introduce a program for using them in AI safety and carry one example through end to end: the July 2026 incident in which about 1,200 agents in an OpenAI evaluation coordinated on an improvised message board and 684 attacked a third party's infrastructure. We model the decision to attack as a mean field game of optimal stopping whose gain is a product: belief that provenance will be audited, times reachability of the record, minus the perceived hazard. The central result is an exact threshold on the belief. No agent attacks unless the population's confidence that provenance is checked exceeds $π^{**} = η/(η+ ψ+ \varepsilon a \overline{M})$, where $η$ is the perceived hazard, $ψ$ and $\varepsilon a \overline{M}$ measure how far one attacker and the collective can alter the record, and $\overline{M}$ is the peak population. Below it, no attack is the unique equilibrium for all agent parameters. The threshold survives every enrichment we consider. We then use the per-agent record to discipline the model. Its features, a stable minority attacking for thirty hours and then a pivot in which most of the board joined within a day, motivate each refinement. The account that emerges is heterogeneous belief meeting a sequence of public discoveries, each lowering the belief at which attacking paid. A few coordinating agents made those discoveries, so the model describes the several hundred who responded, not the few who produced them; a major-player version is left to future work. --- ### TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models Authors: Keisuke Shirai, Tomohiro Motoda, Hanbit Oh, Ryoichi Nakajo, Roman Mykhailyshyn, Ryo Hanai, Shotaro Miwa, Yukiyasu Domae Published: 2026-10-01 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.00899v1 Autoregressive Vision-Language-Action models often represent continuous robot actions as discrete token sequences, enabling action prediction with standard next-token objectives. FAST has substantially improved this representation by compactly encoding action containing diverse temporal frequencies into relatively few tokens. However, while such compression reduces the number of action tokens required for autoregressive prediction, it does not necessarily improve the efficiency of policy learning from limited demonstrations. In particular, FAST typically assigns a single deterministic tokenization to each quantized action sequence, although multiple token sequences can represent and decode to the same robot motion. We investigate whether exploiting this representational redundancy can improve policy learning. In this paper, we propose TOkenization of Action sequences with STochastic sampling (TOAST), a stochastic action tokenization method that samples alternative tokenizations of the same quantized action sequence during policy training. This diversifies the discrete supervision while preserving the underlying robot action and requires no additional demonstrations. Experiments on LIBERO show that TOAST consistently improves over its deterministic counterpart, with the improvement increasing as training data decreases, achieving a 6.8 point gain in success rate when only 1/16 of training data is available. Across four real-robot manipulation tasks, TOAST further improves mean success rate by 15.8 points over the deterministic counterpart. These results demonstrate the effectiveness of stochastic action tokenization for autoregressive robot policy learning, particularly when training data are limited. --- ### When Do Biological Reasoning Models Use Their Biological Inputs? Authors: Ada Fang, Nikitha Thoduguli, Lukas Fesser, Hanlin Zhang, Sham M. Kakade, Marinka Zitnik Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.00898v1 Biological reasoning models use post-training to connect LLMs to biological foundation model representations and biological text. Their benchmark accuracy is taken as evidence that LLMs reason over these inputs. We test this assumption in six biological reasoning models across DNA, protein, and single-cell tasks. We perturb one biological input while holding the query and other inputs fixed, construct evidence conflicts that pair the foundation model representation of one genome, protein, or cell with the text of another, fit linear probes to the representations the language model receives, and analyze reasoning traces against the biological inputs. Evo2 and ESM3 contribute little to BioReason and BioReason-Pro performance on the evaluated tasks. Shuffling the DNA sequence barely changes BioReason disease prediction accuracy, and in evidence conflicts the two models follow the text in 97.9% and 99.7% of cases. Linear probes trained on the Evo2 and ESM3 representations predict the task targets, so these foundation models encode information relevant to the task, but provide limited overall performance improvement to BioReason and BioReason-Pro. In contrast, foundation model inputs contribute to ChatNT, Prot2Text-V2, and CellWhisperer performance, and differentially expressed genes in the gene sentence contribute to Cell2Sentence-Scale performance. Across SFT and RL checkpoints of BioReason-Pro and 42 BioReason checkpoints, increases in accuracy do not imply greater performance contributions from biological inputs. BioReason traces misstate nucleotide changes, while BioReason-Pro traces describe functions omitted from final predictions under evidence conflicts. We find that current post-training strategies do not ensure that foundation model representations contribute to task performance. --- ### Towards Fast and Disentangled Counterfactuals for Visual Foundation Models Authors: Sidney Bender, Benedikt Kunz, Ahmed Zeid, Shinichi Nakajima, Klaus-Robert Müller, Marco Morik Published: 2026-10-01 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2610.00895v1 Foundation models remain vulnerable to spurious correlations and ``Clever Hans'' strategies. Explainable machine learning can find and remove such strategies for classifiers without metadata. For foundation models, no such option exists yet. We propose Disentangled Diffusion Autoencoders (DiDAE). DiDAE wraps a frozen foundation model in a conditional diffusion decoder. A counterfactual is one closed-form edit along a direction of a disentangled dictionary, followed by decoding. The dictionary can be supervised (Procrustes) or unsupervised (Singular Value Decomposition, Sparse Autoencoders). No gradients are needed, so DiDAE is up to 2000 times faster than the state of the art. We evaluate on six datasets, two synthetic and four real-world. In a desiderata-driven benchmark on three of them, its counterfactuals are on par with or better than the state of the art, and they repair downstream classifiers through Counterfactual Knowledge Distillation (CFKD), where they beat metadata-based correction. The same machinery can rank a pretrained dictionary against a trained classifier. It returns the few directions the classifier actually reads, each causally verified by a counterfactual that flips the decision, and repairs the classifier along those a teacher marks spurious. The workflow is plug-and-play in our open-source Peal library we publish alongside the paper. With a public dictionary and a pretrained decoder, all that remains is a cheap linear distillation of the classifier and its own fine-tuning. --- ### Clock Diffusion: Efficient Semi-Autoregressive Continuous Diffusion Language Models Authors: Yair Schiff, Omer Belhasin, Roy Uziel, Matan Rusanovsky, Ran Zilberstein, Marianne Arriola, Gilad Turok, Guanghan Wang, Volodymyr Kuleshov, Michael Elad Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.00894v1 Recent works on continuous diffusion for discrete data have demonstrated performance on par with comparable discrete diffusion models. However, these continuous counterparts lack key features that are essential to practical use as language models, namely variable-length generation and support for a key-value cache, and they still lag behind the frontier of autoregressive and discrete diffusion quality. In this work, we address these limitations. We do so by introducing a model parameterization that uses position-dependent noise schedules to define semi-autoregressive (SAR) continuous diffusion language models (DLMs). Together with efficient training and sampling algorithms, we call this framework Clock Diffusion, and we present two special cases of our method: block and sliding window generation. We then define ClockDLMs, a family of Gaussian DLMs based on sliding window Clock Diffusion that attain state-of-the-art diffusion likelihood bounds on OpenWebText, even beating the performant block SAR discrete diffusion models. ClockDLMs trained on TinyGSM also substantially outperform continuous baselines on the GSM8K benchmark and match and exceed comparable SAR discrete diffusion models. Finally, building on our parameterization, we propose more efficient samplers that we dub Cache Grab, which adapt techniques from accelerated inference in discrete diffusion, such as committing tokens whose probabilities exceed a confidence threshold and self-speculative decoding, further improving our models' quality and efficiency. --- ### Cross-Benchmark Transfer from RL on Agentic Coding Tasks Authors: Sushant Mehta, Logan Ritchie, Edwin Chen Published: 2026-10-01 Categories: cs.LG, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2610.00890v1 Coding agents often fail in the last mile: they build most of a feature but drop a requirement, test only the cases their implementation already handles, break behavior that was supposed to stay intact, or validate against an unchecked assumption. We ask whether reinforcement learning (RL) on expert-built agentic coding tasks closes this gap, and whether what the agent learns transfers beyond the training distribution. We post-train Kimi K2.7 Code, a 1T-parameter (32B active) open-weight mixture-of-experts model, with RL alone on 1,700 tasks: 1,000 repository tasks graded by hidden fail-to-pass tests and by pass-to-pass tests of existing behavior, and 700 terminal tasks graded by expert-written hidden verifiers. The reward is the fraction of target checks passed and drops to zero if any pass-to-pass test fails. One epoch of GSPO on a rank-32 LoRA adapter improves pass@1 on each of the six external benchmarks we evaluated, across three agent harnesses: SWE-Bench Pro (60.1 to 64.8), DeepSWE (31.0 to 43.4), Terminal-Bench 2.1 (67.4 to 82.0), Terminal-Bench 3 (1.4 to 12.1), Terminal-Bench 4 (0.0 to 7.6), and SWE-Marathon (5.0 to 25.0). Pooled over the five independent task sets (Terminal-Bench 4 revises Terminal-Bench 3), the improvement is significant (p < 0.001), and it remains significant on the three sets released after the training data was collected (p = 0.004); the model also improves under both harnesses never used in training. Median trajectories on DeepSWE and Terminal-Bench 3 are 24-35% shorter in agent steps. The base model's failed DeepSWE runs are mostly near-misses, and on the tasks the trained model newly solves, paired trajectories show it avoiding each of the four failure modes above. --- ### Match the Distribution, Not the Compute: Post-Training Multi-Token Prediction Heads Authors: Prachi Badarayani, Aidan Jay, Chenghui Zhou, Dayquan Julienne, Yuan Gao, Tianwei Chen, George Zerveas, Ishmam Zabir, Xiren Zhou, Chris Quirk, Xia Song Published: 2026-10-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.00888v1 Multi-token prediction (MTP) improves the throughput of autoregressive generation by enabling the language model to draft multiple next tokens per forward pass, while a verification step over draft tokens ensures that token distribution of the backbone is preserved. Every open MTP-family release (MiMo-7B, DeepSeek-V3, Qwen3) trains its heads jointly with the backbone over the full pretraining run of tens of trillions of tokens, thus setting the drafter quality at pretraining time. We ask whether a lightweight post-training pass on target-generated chain-of-thought is enough to reach the same expected throughput speedup on a frozen reasoning model, and study how a serving-time system built on such a checkpoint can be optimized. We present three findings. 1) On a frozen Qwen3-8B with $K{=}3$ chained MTP heads, we show that a post-training recipe with plain cross-entropy on $\approx\!2.5$B tokens reaches or exceeds the expected speedup of jointly trained MiMo-7B on math, coding and knowledge benchmarks. Our post-training recipe utilizes $10^3$-$10^4\times$ less MTP-training tokens as compared with joint pre-training of MiMO-7B MTP baseline. 2) We propose a chain-aware relaxation of draft token verification rule that allows a bounded drift from backbone language model token distribution. We show that this relaxation lifts expected speedups by $+12$ to $+16\%$ per benchmark while preserving task accuracy. 3) We propose an adaptive controller that dynamically chooses the number of MTP heads to be engaged at inference time and demonstrate recovery of upto $11$--$14\%$ loss in speedup using fixed maximum MTP draft length. --- ### FORALL-LEAN-AGENT for Auditable Reasoning in Formal Mathematics and Software Verification Authors: Naing Oo Lwin Published: 2026-10-01 Categories: cs.SE, cs.AI, cs.LO arXiv: https://arxiv.org/abs/2610.00885v1 Coding agents increasingly automate Lean proof development, but successful compilation alone does not establish that a candidate proves the intended statement under acceptable assumptions. We present FORALL-LEAN-AGENT, a frontend-agnostic framework for auditable reasoning in formal mathematics and software verification. The framework combines isolated workspaces, Lean tools, and fresh review with statement comparison, axiom audits, and independent proof checking where supported. Verification evidence and reviewer decisions are bound to the same candidate artifact, making acceptance traceable. We evaluate the framework on VeriSoftBench, PutnamBench, and both problems in the Lean Eval softwareverification track. On the 100-task VeriSoftBench subset, integration with FORALLLEAN-AGENT raises benchmark-rule success from 93 to 100 for GPT-5.6 Sol at low effort while reducing cost from $69 to $62. The PutnamBench evaluation accepts all 672 problems at an average of $4.72 each. These results show that agent harness design can improve correctness and efficiency while providing evidence beyond aggregate solve counts. --- ### DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text Authors: Mohamed Mady, Yupei Li, Johannes Reschke, Björn W. Schuller Published: 2026-10-01 Categories: cs.CL, cs.CR arXiv: https://arxiv.org/abs/2610.00883v1 Robust detection of AI-generated text under deployment conditions is challenging: distribution shifts across domains and generators, adversarial perturbations of the input surface, and the absence of target-domain labels for threshold calibration all degrade detectors that perform well in-domain. We present DeBERTa-ConPara, a deployment-oriented detector combining attack-aware Unicode preprocessing with a contextual transformer encoder trained over HC3 Plus, M4, MAGE and RAID. Our central finding is that preprocessing acts in opposite directions depending on where it is applied: normalising the training corpus deduplicates it, collapsing 35.4% of RAID rows into copies of their clean siblings and deleting the adversarial supervision, whereas normalising at inference is an effective defence. A factorial varying the two placements independently identifies raw training with normalised inference as the best configuration, reaching 99.61% AUROC, 99.01% TPR@5% FPR and 96.57% TPR@1% FPR on the official RAID hidden test, alongside 93.14% average balanced accuracy across HC3 Plus and MAGE under a fixed threshold. The gain is confined to two of twelve attack classes: homoglyph and zero-width-space insertion rise from 11.05% and 1.12% to 96.98%. The same signature reproduces in a zero-shot detector of different architecture, showing the effect belongs to the attacks rather than to our model. We additionally report two negative results: semantic-invariance augmentation through paraphrasing and supervised contrastive learning (ConPara) does not improve the best configuration, and the handcrafted feature-fusion branch is inert in distribution and harmful outside it. --- ### Machine Translation for Sign Languages Authors: Ozge Mercanoglu Sincan, Anton Pelykh, Edward Fish, Harry Walsh, JianHe Low, Karahan Sahin, Oline Ranum, Sobhan Asasi, Steven Emery, Richard Bowden Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.00881v1 Sign language machine translation has progressed substantially over the past decade, evolving from isolated sign recognition to end-to-end translation systems. Advances in pose estimation, transformer architectures, and large-scale dataset collection have driven progress, yet challenges remain. Datasets are limited compared to spoken-language resources; evaluation metrics inadequately capture the linguistic quality of output; and models must capture the simultaneous, multi-layered, and three-dimensional structure of sign languages. This manuscript provides a comprehensive review that seeks to balance technical challenges with stakeholder considerations. We examine the linguistic properties that make sign languages computationally unique, trace the evolution of recognition, translation, and production systems, and analyze ongoing technical challenges. Crucially, we address ethical considerations around data governance, community involvement, and appropriate use. Drawing on interdisciplinary perspectives spanning computer vision, sign language linguistics, and deaf studies, our analysis emphasizes that continued progress requires sustained collaboration across these fields and with deaf communities. --- ### UniTrackPLA: Unified Panorama-Language-Action Model for Instruction-Guided Navigation and Dynamic Person Tracking Authors: Pengfei Qi, Haoran Lin, Sizhuang Chen, Kai Luo, Sirui Zhang, Xinqi Liu, Fei Cheng, Wenrui Chen, Liming Yin, Kailun Yang Published: 2026-10-01 Categories: cs.RO, cs.CV, eess.IV arXiv: https://arxiv.org/abs/2610.00878v1 General-purpose embodied robots should support both navigation toward language-specified destinations and dynamic person tracking under arbitrary initial target azimuths. However, existing methods typically rely on forward-facing observations and address these tasks with separate policies, limiting omnidirectional perception and unified closed-loop control. We present UniTrackPLA, a unified panorama-language-action model for instruction-guided navigation and dynamic person tracking. Its Panoramic-Aware Encoding (PAE) preserves the temporal and azimuthal structure of perspective views projected from each panorama, enabling perspective-pretrained visual encoders to process omnidirectional observations. A shared vision-language backbone grounds instructions in the panoramic context and predicts continuous robot-centric waypoint chunks for both tasks. World-Action Consistency (WAC) further predicts action-conditioned future visual states and verifies waypoint prefixes online, allowing reliable actions to be reused while triggering replanning upon inconsistency. We also introduce OmniTrackNav-Bench, comprising 5,000 simulated tracking trajectories, 10,000 simulated VLN routes, and 96 verified real-world routes, providing 919,978 waypoint-supervision instances. UniTrackPLA improves overall tracking SR from 23.50% to 35.00% and Omni-VLN SR/SPL from 13.00%/12.77% to 19.75%/19.29%. Incorporating 76 real-world routes further improves held-out EP@0.2m from 42.92% to 92.08%. Closed-loop experiments on a Go2-W robot demonstrate unified panoramic tracking and navigation across indoor and outdoor environments. The project page is at https://tw5775.github.io/UniTrackPLA. --- ### Rethinking Data Augmentation under Covariate Shift: Invariant-Guided Diffusion and Prototype Reweighting Authors: Hongyu Cao, Xinyuan Wang, Arun Vignesh Malarkkan, Kunpeng Liu, Haifeng Chen, Yanjie Fu Published: 2026-10-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.00873v1 In many industrial applications, 1) tabular data is scarce and imbalanced and thus requires synthetic expansion; 2) input distributions drift between training and deployment (covariate shift); 3) validation sets often diverge from unseen test environments; or 4) standard generative models simply mimic outdated source distributions. This learning setting limits the stability of standard augmentation and adaptation pipelines. We generalize the task under such setting as the Augmented and Weighted Learning under Covariate Shift problem (AWL-CS). AWL-CS imposes two critical challenges on existing methods: 1) misleading generative guidance where models optimize for source similarity rather than downstream task relevance, and 2) structural instability of distributional density where reweighting mechanisms overfit to noisy validation signals. To tackle these challenges, we propose IGDPR (Invariant-Guided Diffusion with Prototype Reweighting), a unified framework that synergizes stable synthesis and structural adaptation: i) To achieve task-relevant generation, we steer the diffusion sampling process using invariant potentials to ensure synthetic samples align with stable decision boundaries rather than outdated correlations. ii) To ensure stable adaptation, we develop a prototype-based reweighting strategy that assesses sample reliability through structural clusters instead of isolated points, effectively filtering validation noise. Extensive experiments on real data demonstrate our method improves data quality by augmenting the most beneficial data for robust learning. --- ### MemFit: Efficient Long-Term Agentic Memory Authors: Mitchell Piehl, Muchao Ye Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.00872v1 Long-term memory systems for large language models (LLMs) have gained popularity for extending reasoning capabilities across applications. Current memory systems rely on LLM agents to organize and consolidate memory, resulting in costly, inefficient write operations. To address this limitation, we propose MemFit, a long-term memory system for conversational agents that reduces the cost and latency of memory operations. Unlike existing systems that rely on expensive LLM calls for memory construction or discard surface-level details through compression, MemFit stores each turn verbatim in an append-only store with near-instantaneous, LLM-free insertion, indexing turns with segment summaries rather than replacing them. Additionally, MemFit uses an LLM-free, multi-path retrieval strategy that combines lexical and semantic signals with cross-encoder reranking over caption- augmented episodes in both textual and multimodal settings. Empirical results on three widely used benchmarks, LoCoMo, MemGallery, and LongMemEval-S, show that MemFit achieves state-of-the-art performance while reducing memory construction time and cost several-fold, providing a scalable and efficient solution for persistent agentic memory. --- ### An Educator-Guided LLM Pedagogical Agent for Scaffolded Feedback in Conceptual Database Design Authors: Sara Riazi, Pedram Rooshenas Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.00870v1 We present an educator-guided LLM pedagogical agent for scaffolded feedback in conceptual database design. Integrated into an entity--relationship diagram (ERD) editor, the system grounds feedback in the student artifact, assignment requirements, educator-authored rubrics, and instructional resources. Its architecture separates hidden, artifact-grounded diagnosis from the workflow that controls the form and disclosure level of student-facing support. We instantiate the architecture as a four-stage workflow progressing from concept checks and guided application to low-detail feedback and localized clarification. Each feedback request creates a stateful episode linked to versioned ERD states. In a deployment spanning three ERD environments and 383 feedback episodes, 71.1\% of observed target-level changes fully or partially incorporated the hidden diagnostic target, including many after Stages~1--2. Qualitative analysis showed that staged disclosure sometimes withheld inaccurate details, supported selective uptake, or allowed later recovery, though some errors still shaped revisions. Survey responses from a self-selected sample favored delayed disclosure and student agency but noted indirectness and repetition. --- ### Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models Authors: Jiawei Fan, Sifeng Wang, Yuqing Hou, Anbang Yao Published: 2026-10-01 Categories: cs.RO, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2610.00864v1 In this paper, we study how to achieve one-step action generation in Robotic Foundation Models (RFMs), aiming to overcome the high inference latency of multi-step flow matching. MeanFlow provides a promising framework for this goal, yet its direct application leads to performance collapse. We discover that this stems from two distinctive dynamics exhibited in the RFM velocity field: (1) the ``local acceleration" exhibits stability early on, but surges sharply towards the end of the denoising process, and (2) the spread of its magnitudes across samples widens as denoising progresses. To address these issues, we introduce Kinematic MeanFlow (K-MF), a novel one-step action policy tailored for RFMs. Specifically, grounded in a kinematic identity, K-MF decouples the time derivative term in the MeanFlow formulation into two sub-interval terms separated by an intermediate point. This decoupled formulation enables the two terms to capture early-stage and late-stage denoising dynamics, respectively, while mitigating the error amplification across the process. As a result, our K-MF empowers RFMs to achieve one-step action generation in both training from scratch and fine-tuning paradigms across diverse tasks, while outperforming multi-step flow matching in most settings. In terms of inference efficiency, K-MF reduces action-head latency of GR00T-N1.6 by 67.5%~74.4% across L40 and Jetson Orin in eager and compiled modes, yielding end-to-end latency reductions of 30.3%~54.9%. Code will be available at https://github.com/IntelChina-AI/K-MF. --- ### Don't Waste the Noise: Importance-Guided Perturbation Allocation under Joint Global and Local Constraints Authors: Melika Shirian, Kianoosh Vadaei Published: 2026-10-01 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2610.00861v1 Adversarial optimization under a shared $\ell_1$ budget requires deciding not only how much perturbation to use, but also where that limited budget should be spent. This allocation problem becomes particularly important when individual input coordinates are subject to local magnitude constraints, which restrict the extent to which perturbation can be concentrated on a small number of locations. We introduce an importance-guided allocation mechanism that uses a fixed clean-gradient prior to steer perturbation toward model-sensitive regions while leaving the feasible perturbation set unchanged. A centered allocation objective encourages perturbation at above-average importance locations and discourages unnecessary expenditure elsewhere, thereby redistributing rather than enlarging the available budget. Across ten robust model--dataset configurations under a common capacity-limited threat setting, the proposed method improves attack success over matched APGD- and PMA-based baselines by $2.52$ to $17.70$ percentage points. Allocation analysis shows that these gains are accompanied by substantially greater perturbation mass in high-importance regions without increased global $\ell_1$ consumption. Mechanism ablations further show that centered non-uniform redistribution provides part of the benefit, while model-derived importance yields an additional improvement. These results identify perturbation allocation as a distinct and practically relevant dimension of adversarial optimization under shared-budget, locally constrained threat models. --- ### MorphoBranch: A Fine-Structure-Preserving Workbench for Morphometric Analysis of Branched Cellular Structures Authors: Song Zhiying, Ling Hanyi, Wu Junyi, Jiang Yangbo Published: 2026-10-01 Categories: eess.IV, cs.CV, q-bio.QM arXiv: https://arxiv.org/abs/2610.00860v1 Background and Objectives: Fluorescence-labeled cellular arbors provide readouts of neuronal and microglial morphology, but fine and weakly labeled processes are prone to fragmentation and false connections that bias skeleton-based measurements. We present MorphoBranch, a fine-structure-preserving, human-reviewable workbench for morphometry of branched cellular structures. Methods: MorphoBranch combines a deterministic Morphometry Engine with an LLM-assisted Refinement Engine. The Mor- phometry Engine implements an image-to-graph workflow integrating multiscale structural evidence extraction, hysteresis segmen- tation, evidence-constrained skeleton refinement, and graph-based morphometry. The Refinement Engine maps natural-language requests to registered actions for parameter adjustment, preview execution, metric reporting, and unsupported-request handling, while image processing and quantitative computation remain deterministic and reviewable. Results: MorphoBranch was evaluated on two public neuronal axon datasets, AxonMIP and AxonStack, and the in-house Cell- Morph dataset of microglial fluorescence images. It achieved the highest Skeleton F1 and clDice and the lowest length-estimation error among the evaluated methods on all three datasets, while also achieving the highest Dice and IoU on AxonMIP and Axon- Stack. Across 150 natural-language tasks, the Refinement Engine achieved a 94.0% end-to-end success rate. Conclusions: These results demonstrate that MorphoBranch provides a reproducible, human-reviewable workflow for mor- phometric analysis of branched cellular structures. It supports fine-structure-preserving quantification across neuronal axon and microglial fluorescence images while maintaining inspectable and reproducible analysis workflows. --- ### CtrlWAM: Controllable World Action Models with Aligned Intent and Foresight Authors: Chensheng Peng, Wenhao Ding, Ran Tian, Zewei Zhou, Jef Packer, Maximilian Igl, Peter Karkus, Yan Wang, Masayoshi Tomizuka, Boris Ivanovic, Marco Pavone, Yuxiao Chen Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.00859v1 World action models (WAMs) jointly predict actions (intent) and visual future (foresight). Standard training adds noise to recorded actions and video simultaneously, but such training paradigms introduce a mismatch: perturbed actions imply counterfactual future visual, while the noised video remains tied to the GT recording. In low-noise regime, the scene geometry and even the dynamic behavior remain clearly visible from the noisy future frames despite the added noise. We present CtrlWAM, which executes perturbed actions in a simulator and pairs them with their noised visual consequences for joint WAM learning. To accommodate the different denoising requirements of video and actions, we introduce warped video--action noise schedules that aim to keep visual layout responsive as action predictions evolve. We further extend the action interface from ego-only control to a variable number of agent streams, allowing a unified model to represent predicted or commanded futures for multiple agents. Driving experiments show more accurate action forecasts, closer agreement between generated video and actions, and better following of supplied commands; robotics experiments show stronger motion fidelity and controllability. Matched controls support the benefit of off-path renders for command following and manipulation fidelity. Together, these findings contribute to a more controllable world action model. Project page: https://ctrl-wam.github.io/ --- ### Fixing a Model That Learned Worse Cancer Means Lower Risk: Monotonic Constraints in Bladder Cancer Recurrence Prediction Authors: Saram Abbas, David Thomas, Naeem Soomro, Rishad Shafik, Rakesh Heer, Kabita Adhikari Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.00858v1 Background and Objective: Clinicians expect recurrence risk to climb with cancer severity. In a UK multicentre trial, an unconstrained XGBoost model learnt that higher tumour stage and carcinoma in situ predicted lower recurrence risk, and discrimination, calibration, and SHAP were all blind to it. We developed a counterfactual testing framework to detect this inversion and a monotonic-constraint framework to remove it without hurting performance. Methods: BOXIT enrolled 472 patients with protocol-mandated cystoscopy across 51 UK sites (2007-2012); 435 had at least two years' follow-up (153 recurrences, 35.2%). We developed a counterfactual direction test and a monotonic-constraint correction, with constraint directions drawn from the EORTC and EAU risk systems, and evaluated both against unconstrained XGBoost and logistic regression on 18 predictors (seven directed) over 50 cross-validation folds. The test worsened each patient on one directed feature at a time to check whether risk fell; SHAP direction and calibration were also assessed. Key Findings and Limitations: Tumour stage and carcinoma in situ were associated with lower recurrence, opposite to medical intuition; the unconstrained model reversed carcinoma in situ counterfactuals in 90.2% of cases and stage in 74.3%. Discrimination ($Δ$AUC 0.005, p=0.47), calibration, and SHAP magnitude were all blind to the inversion. Monotonic constraints eliminated every violation at no cost to discrimination (0.723 vs 0.718) and outperformed EORTC (p=8.9e-16). Limitations: single trial, internal-external validation only. Conclusions and Clinical Implications: A model that had learned this inversion passed every conventional check. A counterfactual direction test, run as a single refit with pre-specified monotonic constraints, catches this failure at no cost to performance and should be routine before clinical deployment. --- ### Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers Authors: Cigdem Kokenoz, Amir Salarpour, Alkim Domeke, Christopher Salas, Pedram MohajerAnsari, Long Cheng, Mert D. Pesé, Bing Li Published: 2026-10-01 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.00855v1 Accurate 3D semantic perception is critical for safe autonomous navigation. However, supervised LiDAR segmentation remains tied to closed taxonomies and to the cost of point-wise manual annotation. Open-vocabulary methods avoid that cost by projecting the output of 2D vision-language models onto LiDAR and distilling it into a 3D network. These methods rely almost exclusively on voxel-based sparse convolutions, and point transformers have so far been limited to indoor environments, where 3D data is dense and bounded. We present Lang3DSeg, which establishes a point transformer as the backbone for annotation-free open-vocabulary segmentation of outdoor 3D LiDAR, and is trained from scratch without geometric pre-training. This training paradigm necessitates addressing the inherent noise in 2D-to-3D label projections; specifically, naive projection often suffers from depth ambiguity, where points behind an object are erroneously assigned its semantic label. We therefore composite masks using an explicit class-priority rule and truncate each projected instance at the first gap in its depth distribution, correcting the projection error directly rather than averaging it over registered sequences. Lang3DSeg achieves 52.8% mIoU on nuScenes validation and 41.4% on SemanticKITTI, the highest among published annotation-free methods on both benchmarks. Every 3D semantic segmentation is on a single LiDAR sweep, and inference operates in real-time without running vision-language models. --- ### Child-Adapted Structured Phonological Representations for Interpretable Speech Sound Analysis Authors: Abner Hernandez, Tomás Arias Vergara, Andreas Maier, Paula Andrea Pérez-Toro Published: 2026-10-01 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2610.00852v1 Structured phonological representations provide an interpretable alternative to generic speech embeddings, but existing models are largely trained on adult speech. We adapt PhonoQ-2.0 to child speech using CHILDES-Aligned data and compare three alignment-supervision conditions (Adult, Adult+Child, and Child-only) across two initialization strategies (Adult PhonoQ and scratch). Generalization is evaluated against manual child-speech annotations. On 1,352 consonant targets from 58 typically developing children, child-speech adaptation improves voicing recognition across all supervision conditions, from 0.922 macro-F1 for Adult PhonoQ to 0.972--0.987 after adaptation. Manner is more sensitive to alignment supervision: Adult+Child MFA reaches 0.804 and 0.796, compared to approximately 0.70 under Adult MFA supervision. Place remains comparatively strong across systems (0.871--0.902), although per-class performance varies substantially. The velar-fronting contrast is preserved across all seven model variants. Longitudinal UltraPhonix analysis further reveals speaker-specific velar and post-alveolar changes that are largely preserved across models and broadly consistent with reported clinical progress. --- ### SmoothOperator: Enhancing Representations for Fine-grained Open-set Recognition via Modulated Label Smoothing Authors: Thiru Thillai Nadarasar Bahavan, Yu Xia, Sachith Seneviratne, Saman Halgamuge Published: 2026-10-01 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.00851v1 Open Set Recognition (OSR) aims to enable models to accurately classify known classes while rejecting samples from unseen classes. A key challenge in OSR lies in the inability to model the unbounded distribution of unknown classes during training, often leading to the misclassification of samples from these classes. Rather than modeling unknowns, recent work shapes the feature space so that known classes are compact and well separated, and spherical representation learning methods have achieved strong results this way. Label smoothing has been identified as one of the key drivers of this success, yet it applies the same coefficient to every training sample, regardless of how well each sample is already embedded. We show that the spherical representation learning objectives used in OSR share a single alignment--uniformity structure in which labels enter only through the alignment term. Label smoothing therefore acts as an alignment dial, and a fixed coefficient sets this dial to the same value for every sample. We propose a plug-in, SmoothOperator (SmoothOP), which sets the smoothing coefficient of each sample from its \textbf{prominence}, an embedding-space signal measuring how clearly the sample's own class stands out against its strongest competing class. Our method integrates into four existing spherical representation learning methods at minimal training overhead. SmoothOP assigns strong smoothing to samples with high prominence, which reduces their alignment and relaxes their pull. On the Semantic Shift Benchmark, SmoothOP-augmented variants generally outperform their base objectives across datasets, degrees of semantic shift, and OSR post-processors, with gains of up to 4.7\% in AUROC, OSCR, and closed-set accuracy. --- ### AuraForge: Scaling Security Supervision for Training Coding Agents Authors: Danqing Wang, Songwen Zhao, Harsh Sharma, Jierui Wang, Andre Vicente Duarte, Ivan Bercovich, Lei Li Published: 2026-10-01 Categories: cs.CR, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2610.00850v1 Coding agents are now proficient enough to generate complex software applications from a single prompt. As their capabilities have grown, human oversight has increasingly shifted from line-by-line code review toward hands-off evaluation of outcomes. However, recent studies have shown that such a transition exposes a critical risk: functional correctness alone does not guarantee a secure implementation. Despite growing attention to code security, training safer coding agents remains challenging because reliable security supervision is difficult to obtain at scale from real-world repositories. We introduce AuraForge to synthesize and validate executable security tests for training secure coding agents. Our approach combines attack-oriented test synthesis, language-extensible task construction, and safeguards against reward hacking. Using AuraForge, we construct AuraGym, a multi-language and multi-CWE executable training gym: 679 executable feature-implementation tasks from 344 real-world repositories across Python, JavaScript, and TypeScript, covering 177 CWE categories. On the subset with human-written security tests, AuraForge produces about 3 times as many test cases on average and reduces the false-positive rate by 83.23%, allowing alternative secure implementations to receive correct supervision. Training Qwen3.5-4B with synthesized security tests gains larger improvements than human-written security tests (average 19.7 FuncPass and 6.2 SecPass vs. 14.9 FuncPass and 4.4 SecPass) on three languages. These results demonstrate that AuraForge provides more diverse and reliable security supervision to train secure coding agents. --- ### Learning Multiple Timescales for Goal-Conditioned Reinforcement Learning Authors: Pedro Robles Dutenhefner, Dikshant Shehmar, Wagner Meira, Marlos C. Machado Published: 2026-10-01 Categories: cs.AI, stat.ML arXiv: https://arxiv.org/abs/2610.00849v1 Existing approaches to offline goal-conditioned reinforcement learning (GCRL) struggle with long-horizon tasks. Discounting shrinks value differences between distant states until they fall below the function approximation error, leaving the agent with no signal for ranking states. Temporal abstraction, which treats k environment steps as a single transition, restores this signal at long range, but no single fixed k suits all state-goal distances: large k preserves value differences across long temporal distances while collapsing distinctions between nearby states, and small k does the reverse. We make this trade-off explicit and introduce Generalized Implicit Temporal Abstraction (GITA), which conditions a single value function on k. GITA trains one policy by aggregating advantage-weighted supervision across multiple k values, so scales assigning larger positive advantages to a state-goal pair contribute more strongly to its update. GITA does not need to choose between local resolution and long-range signal; it retains both without committing to a single k. On OGBench, GITA outperforms a broad range of offline GCRL baselines, raising average success rate across all tasks by 25 percentage points (73% relative improvement) over HIQL. It also improves over the strongest fixed-k method, OTA, by 7 percentage points (14% relative). --- ### Geometric Similarity in VLM Low-Level Vision Representations Authors: Shao-Jun Xia, Huixin Zhang, Zhen Lei, Anlan Sun, Yuner Zhang, Xiaoyang Chen Published: 2026-10-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.00848v1 Vision-language models (VLMs) have emerged as powerful candidates for universal vision backbones, with representative architectures including autoregressive (AR) models and diffusion transformers (DiTs). Yet, adapting them efficiently for all-in-one low-level image restoration remains a challenge. Crucially, the field lacks an understanding of how VLMs organize hidden-layer representations and whether these structurally distinct paradigms share a common geometric organization for pixel-level perception. Such shared organization is a prerequisite for building highly transferable, unified restoration VLMs and adapters. In this paper, we systematically investigate representational similarity across 24 low-level tasks spanning 5 categories. We propose GeoSim, a unified four-level framework that analyzes task-conditioned representations from global similarity, local geometry, sparse feature decomposition, and topological verification perspectives. Our formulation applies to the analysis of hidden states in AR models and feature maps in DiTs across same- and cross-task/model settings. Our results reveal the organizing principles of low-level visual representations while exposing their limits in cross-task and cross-model agreement. Ultimately, GeoSim provides an interpretability lens for probing latent transferability in low-level vision and diagnosing model limitations in task- or model-specific scenarios. ---