# Research Papers — 2026-08 · bundle page 87 of 240 > Full-text markdown of papers #4301–4350 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/87 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/86.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/88.md) ### RoMAN-Flow: Taming Autoregressive Normalizing Flows for Offline Reinforcement Learning in Robotic Manipulation Authors: Shaoxuan Wang, Guangting Zheng, Rui Huang, Zhipeng Tang, Sha Zhang, Jiajun Deng, Yanyong Zhang Published: 2026-08-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.20208v1 Offline reinforcement learning improves robotic policies using previously collected data without further environment interaction. Yet prevalent diffusion- and flow-matching robot policies lack tractable likelihoods, limiting their use in likelihood-based offline RL post-training. AR-NFs offer both expressive action modeling and exact likelihood evaluation, but their sequential sampling incurs substantial sampling overhead during policy optimization and deployment. We present RoMAN-Flow (Robotic Manipulation with Autoregressive Normalizing Flows), an offline reinforcement learning framework that makes AR-NF policies practical for robotic manipulation by addressing this sampling bottleneck in both stages. During policy optimization, RoMAN-Flow employs a sampling-free, advantage-weighted likelihood objective that assigns higher likelihood to high-advantage actions from the offline dataset without sampling from the autoregressive policy. For efficient deployment, it distills the optimized autoregressive policy into a one-step action generator, enabling low-latency action prediction. Experiments across multiple simulated manipulation benchmarks and real-world robotic platforms demonstrate that RoMAN-Flow achieves competitive policy performance while substantially reducing inference latency. Code is available at https://github.com/konnyaku28/RoMAN-Flow. --- ### ContractScrub: A benchmark for final review of legal contracts Authors: Yejin Bang, Kirsty Fielding, Brandan Oliver, Brian Birke, Nabeel Seedat, Andrew M. Bean Published: 2026-08-20 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.20204v1 Legal work, with its heavy reliance on processing large amounts of text, is often considered one of the domains most exposed to the use of LLMs. Contract ``scrubbing,'' the final review of transactional agreements for errors and inconsistencies, is a particularly suitable task for automation, because it is routine, painstaking work requiring detailed attention to long documents. Scrubbing also seems to align naturally with the general capabilities expected of frontier LLMs around long-context reasoning, consistency checking, and named entity recognition (NER). Despite the economic value and potential for automation, no formal evaluations of LLMs performing contract scrubbing have been conducted. We introduce ContractScrub, the first benchmark designed to evaluate contract scrubbing capabilities, comprising contracts hand-crafted by experienced lawyers over diverse error categories such as misuse of defined terms, incorrect references, and inconsistent language. Frontier models perform surprisingly poorly with only one model reaching 0.75 macro average recall despite strong performance on seemingly related general benchmarks, demonstrating the practical limits of current models and the importance of narrowly targeted, domain-specific benchmarks for measuring real-world impact. --- ### MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use Authors: Mengru Wang, Haozhe Luo, Zhenqian Xu, Zhixiang Cui, Haoming Xu, Qu Yang, Jizhan Fang, Junfeng Fang, Ningyu Zhang Published: 2026-08-20 Categories: cs.AI, cs.CL, cs.CY, cs.DB, cs.LG arXiv: https://arxiv.org/abs/2608.20202v1 Memory has become a key component of large language models, enabling them to retain information and learn from long-term interactions. However, existing memory benchmarks mainly evaluate whether information is correctly extracted, stored, and retrieved, while largely overlooking how retrieved memories reshape model reasoning and affect performance on the current task. We identify memory-induced cognitive traps: even faithfully recorded and semantically relevant memories can distort model reasoning or beliefs and degrade current task performance. To systematically evaluate these failure modes, we introduce MemTrapBench, which covers two forms of cognitive traps: Reasoning Fixation and Belief Distortion. Experiments across two model families and five representative memory frameworks show that MemTrapBench is challenging: all evaluated memory strategies underperform the no-memory setting, with even the strongest methods suffering drops of more than 10%. To mitigate these cognitive traps, we propose AdaptiveMem, a simple yet effective inference-time method that instructs LLMs to avoid memory traps. AdaptiveMem mitigates cognitive traps on MemTrapBench while preserving or improving performance on standard memory benchmarks across diverse memory frameworks. --- ### The Third Restructuring of Software Form: From the Three-Tier Architecture to Storage, Models, and Agents Authors: Wei Lin, Tao Zhou, Zhaofei Xie, Changgui Hong Published: 2026-08-20 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.20201v1 Software form has undergone two paradigm shifts since its inception: Software 1.0, in which instructions determine behavior, and Software 2.0, in which data determines behavior (machine learning). This paper argues that a third shift - Software 3.0, in which context and reasoning determine behavior - is now underway, and contends that its terminal form converges to three elements: a generalized database (the unified abstraction of all persistent state and memory), a large model (the intelligence core that performs reasoning and generation), and an agent (the execution loop connecting the first two). The core argument is as follows: in the traditional three-tier architecture, the user-interface layer will be absorbed by the model's ability to generate interfaces on demand, the business-logic layer will be re-partitioned along "expressibility x criticality" into model reasoning and storage constraints (with residual deterministic logic retained as tools), and only the data layer will be elevated into the sole persistent infrastructure. We formalize this convergence thesis, present a minimal reference architecture, report evidence from real prototypes and a live model, and systematically analyze both the conditions under which it holds and the boundaries where it fails - determinism, cost, security, and verifiability delimit the thesis's domain of applicability. We argue that the thesis holds in task domains that are expressible, verifiable, externally stateful, and tool-complete, and that it will reshape the roles of developers, the database industry, and the software-engineering discipline. --- ### From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentation Authors: Zhijun Gao, Jing Chen Published: 2026-08-20 Categories: cs.SE, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.20195v1 Technical documentation is written for human developers, but an increasing share of software changes is now authored by autonomous coding agents. Which documents they consult, when, and what follows remain unknown. We conduct a behaviour-grounded study of agent-documentation interaction across two public datasets: 557 agentic coding sessions from SWE-chat, yielding 94,813 development events including 3,033 documentation interactions; and 33,097 agentic pull requests from AIDev, with 690,260 classified file-level change records. Four findings challenge current documentation practice. First, agents' documentation work is dominated by agent-facing artefacts: instruction files and working notes account for 60.5% of all documentation interactions, versus 10.6% for classical technical documentation and 1.3% for API references. Second, the link between consultation and code editing is unresolved: the adjacent transition probability is 0.002 and the unadjusted three-event lift 1.05, whereas a stage-adjusted model places it above unity (OR 1.33 (1.09, 1.62)); documentation creation is elevated unadjusted (lift 1.67) but its adjusted interval includes unity. Third, no explicit documentation-based validation sequence was observed, and consultation is associated with less immediate testing (lift 0.23, cluster CI 0.08-0.45; adjusted OR 0.39 (0.25, 0.60)). Fourth, consultation is self-initiated (70.2%) far more often than failure-driven (7.5%), and documentation trails code: among multi-commit pull requests changing both, code is touched first 4.7x more often. From these traces we derive a descriptive model of agent-documentation interaction as a two-lobed cycle rather than a linear journey, and show that two widely assumed properties of "agent-friendly" documentation - actionability and verifiability - lack consistent behavioural support. We release our pipeline, coding scheme, and event-level data. --- ### Multi-Method Causal Evidence Synthesis: Ranking Candidate Drivers by Convergent Cross-Method Evidence from Observational Data Authors: Manish Gupta, Dipanjan De Published: 2026-08-20 Categories: stat.ME, cs.AI arXiv: https://arxiv.org/abs/2608.20187v1 Practitioners inferring causality from observational data usually rely on a single method and treat its output as causal truth. Recent tools select an optimal method for a dataset, and recent ensembles aggregate multiple causal-discovery algorithms into one graph, but little work pools evidence across different mathematical traditions, including non-causal ones. We present Multi-Method Causal Evidence Synthesis (MCES), a framework that ranks which candidate drivers in an observational system are most likely relevant to a set of outcomes, and with what strength of evidence. MCES runs eleven methods across eight mathematical traditions on observational panel data and pools their outputs into a Convergent Evidence Score (CES), a linear opinion pool. CES quantifies convergence of evidence across analytical lenses: the degree to which methods with different assumptions point to the same driver-outcome relationship. It does not claim causal identification in the interventionist sense; it supports hypothesis prioritization, not a transferable probability of causation. MCES first applies Structural-Behavioral Decomposition to remove definitional (algebraic) relationships, then runs all methods, normalizes outputs to (0,1), and pools them. We distinguish MCES from method selection, structural ensembles, prediction ensembles, and literature synthesis. Using synthetic data with embedded ground truth, the Sachs protein-signaling benchmark, six Bayesian-network structure benchmarks, and two further synthetic domains, we show MCES ranks true edges near the top (Precision@5 = 1.0, Precision@10 = 0.96 on the primary scenario), with a low empirical rate of null pairs reaching Moderate-or-higher convergence. Our central point is not that the pool beats every individual method, but that no single method is uniformly best across the evaluated scenarios, so MCES offers a method-agnostic default. --- ### Decoding silent reading from non-invasive EEG Authors: Ingo Marquardt, Anthilia Alchanat, Priyanka Jain Published: 2026-08-20 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2608.20186v1 Non-invasive decoding of inner speech faces a fundamental data problem: a corpus pairing brain activity with a person's spontaneous inner monologue cannot be collected, and the available proxy paradigms (cued repetitive and retrospectively reported generative inner speech) are slow to acquire, poorly time-locked, and subject compliance is unverifiable. We therefore treat silent reading as a scalable proxy task and ask how much lexical and semantic information a contrastive decoder can extract from it. We report an open-vocabulary analysis of approximately 240,000 word presentations recorded from a single densely-sampled participant across 393 runs (ca. 49 h) of 19-channel dry-electrode EEG. Words from continuous narrative text were presented in rapid serial visual presentation, with typography randomised on every trial to partially decorrelate word identity from low-level visual form. A convolutional EEG encoder, optionally followed by a causal transformer, was trained with a CLIP-style contrastive objective to align short EEG windows with hidden-state embeddings of the presented word taken from a large language model. Decoding, evaluated as word-grouped top-10 retrieval against permutation baselines, was reliably above chance, extended to mid-frequency and rare words, and scaled log-linearly with training-data volume with no sign of saturation. Removing occipital and posterior-temporal electrodes reduced the word-level gain by roughly one third but left context tracking unchanged. Control analyses separate word-level decoding from narrative context tracking and from a non-neural positional prior introduced by the transformer's positional embedding. These results establish that open-vocabulary word-level information is recoverable from EEG during silent reading, and that decoding is data-limited rather than saturated. --- ### Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models Authors: Grégoire Sergeant-Perthuis, Elias Tsigaridas, Jules Tsukahara Published: 2026-08-20 Categories: cs.LG, cs.SC, math.AG, stat.ML arXiv: https://arxiv.org/abs/2608.20183v1 Classical information criteria such as the Bayesian Information Criterion (BIC) rely on regularity assumptions that break down for singular models, leading to incorrect model selection in settings such as deep learning. The Widely Applicable Bayesian Information Criterion (WBIC) relies on local learning coefficients $λ$, which in the analytic case coincides with local Real Log Canonical Thresholds (RLCT) of the Kullback-Leibler divergence of the model, to capture correct marginal likelihood asymptotics. Exact computation of the learning coefficients has been limited to special cases, and only sampling-based estimation methods are generally applicable. We present the first deterministic algorithm that computes local RLCTs exactly for any two-dimensional model whose Kullback-Leibler distance is contact equivalent to a polynomial, derive a bound on its complexity, and demonstrate its effectiveness for a broad class of models, with applications including polynomial neural networks. Beyond providing ground truth to calibrate sampling-based estimators, exact computation reveals algebraic structure in learning coefficients that sampling cannot and out-speeds it in the shallow regime. --- ### A Standardized Framework for Machine Learning in Power System Protection Authors: Julian Oelhaf, Georg Kordowich, Paula Andrea Pérez-Toro, Christian Bergler, Johann Jäger, Andreas Maier, Siming Bayer Published: 2026-08-20 Categories: cs.LG, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2608.20181v1 Studies of machine-learning-based power-system protection increasingly report near-perfect scores, yet the meaning of those scores depends strongly on the evaluation setting. Protection task, physical scope, measurements, timing, targets, preprocessing, and validation often vary jointly and remain incompletely specified. This paper proposes a standardization-oriented framework that treats evaluation design as part of the scientific contribution. It defines seven required study dimensions: protection objective, physical scope, observability, timing and decision windows, targets and sample validity, validation protocol, and evaluation outputs. The framework is instantiated in a bounded case study on the public PROTECT-90 electromagnetic-transient benchmark, comprising 9022 simulated episodes from a 90 kV double-line topology, for onset-conditioned fault classification and localization. Under centralized sensing, simulation-metadata-aligned 20 ms windows, and episode-grouped validation, a multi-layer perceptron (MLP) achieved a five-fold mean macro-averaged F1 score of 0.991 +/- 0.001 for classification and a localization mean absolute error of 10.20 +/- 0.25% of line length (mean +/- std across episode-grouped folds). Extending the decision horizon to 50 ms preserved this task-dependent performance asymmetry, while reduced observability approximately doubled the MLP localization error but had little effect on classification. A synchronized two-ended conventional locator outperformed the learning locators under its richer clean information set, and measurement degradation showed that clean predictive performance did not determine robustness. The framework turns evaluation assumptions into explicit, reproducible evidence and provides a basis for more comparable, auditable evaluation and future certification-oriented assessment of machine-learning protection functions. --- ### Ask Self, Ask Others: Relation Is All You Need Authors: Yuting Ge, Pengju Yang, Mingkai Nie Published: 2026-08-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.20172v2 Attention dominates token mixing, but it collapses relation formation and flow allocation into a single score-to-flow step. We introduce Relation, which separates them by first organizing pairwise evidence into explicit Self and Exchange relations and deriving information flow afterward. Relation first decides whether a token should rely on itself or draw from its history, and if it draws from history, where to look. This relational organization gives rise to Full Relation, FlashRelation, Linear Relation, and Hybrid Relation. Across matched decoder-only models, Full Relation achieves lower mean final-validation NLL than MHA and reaches the paired MHA final training loss with 4.5-7.3% fewer tokens. Structural diagnostics further show that Relation learns a distinct depth organization: the first layer acts as a current-token anchor and a high-rank router, while later layers shift strongly toward history. In a fixed-context reference benchmark, FlashRelation is 4.17-5.28x faster than the materialized Full Relation implementation. Across scale-matched production workloads, it reaches 89.7-92.9% of PyTorch FlashAttention throughput while executing the exact Full Relation operator. Hybrid Relation demonstrates that Full and Linear Relation layers can be composed within a single decoder. These results support a relation-first view of token mixing: ask Self, ask Others, then let Flow follow Relation. --- ### Ask Self, Ask Others: Relation Is All You Need Authors: Yuting Ge, Pengju Yang, Mingkai Nie Published: 2026-08-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.20172v1 Attention directly derives normalized information flow from pairwise scores. We introduce Relation, an alternative token-mixing primitive that first organizes pairwise evidence into explicit Self and Exchange relations and derives information flow afterward. This relational organization gives rise to Full Relation, FlashRelation, Linear Relation, Hybrid Relation, and a KV-style Relation Cache. Across matched decoder-only models at approximately 10M, 30M, and 100M parameters, Full Relation achieves lower final validation NLL than MHA at all three scales. In a fixed-context reference benchmark, FlashRelation is 3.60-4.41x faster than the materialized Full Relation implementation. Across scale-matched production workloads, it reaches 76.4-84.9% of PyTorch FlashAttention throughput while executing the Full Relation operator. Hybrid Relation uses 75% Linear Relation layers and achieves strong language-modeling quality. These results support a relation-first view of token mixing: ask Self, ask Others, then let Flow follow Relation. --- ### Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection Authors: Atsuyuki Miyai, Kiyoharu Aizawa, Toshihiko Yamasaki Published: 2026-08-20 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.20169v2 We present a novel approach to efficient LLM harness optimization through adaptive validation task selection. Harness optimization iteratively rewrites the harness code based on validation performance, enabling substantial performance gains without updating the underlying model weights. Existing approaches, however, evaluate a fixed validation set in full at every iteration, incurring substantial evaluation costs even on tasks that become less discriminative as the harness evolves. We propose $\textbf{Task-CoEvolve}$, which co-evolves the validation tasks with the harness by addressing two challenges: selecting informative tasks and estimating full-set performance from partial evaluations. Task-CoEvolve builds on the observation that tasks on which candidate harnesses disagree are more informative for distinguishing among them than tasks that are consistently solved or failed. It uses variance-weighted sampling based on past outcomes to focus evaluation on tasks near the capability frontier, with the sampling distribution adapting as the harness evolves. It then estimates full-set scores from the sampled tasks by accounting for their sampling probabilities, enabling consistent comparisons across iterations despite evaluating different subsets. Experiments on online text classification and Terminal-Bench 2.1 show that Task-CoEvolve consistently outperforms subset-based baselines and matches the final performance of full-set search while reducing the number of evaluations during optimization by 80%. Code will be released at https://github.com/Agent4Science-UTokyo/Task-CoEvolve. --- ### Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection Authors: Atsuyuki Miyai, Kiyoharu Aizawa, Toshihiko Yamasaki Published: 2026-08-20 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.20169v1 We present a novel approach to efficient LLM agent harness optimization through adaptive validation task selection. Harness optimization iteratively rewrites the harness code based on validation performance, enabling substantial performance gains without updating the underlying model weights. Existing approaches, however, evaluate a fixed validation set in full at every iteration, incurring substantial evaluation costs even on tasks that become less discriminative as the harness evolves. We propose $\textbf{Task-CoEvolve}$, which co-evolves the validation tasks with the harness by addressing two challenges: selecting informative tasks and estimating full-set performance from partial evaluations. Task-CoEvolve builds on the observation that tasks on which candidate harnesses disagree are more informative for distinguishing among them than tasks that are consistently solved or failed. It uses variance-weighted sampling based on past outcomes to focus evaluation on tasks near the agent's capability frontier, with the sampling distribution adapting as the harness evolves. It then estimates full-set scores from the sampled tasks by accounting for their sampling probabilities, enabling consistent comparisons across iterations despite evaluating different subsets. Experiments on online text classification and Terminal-Bench 2.1 show that Task-CoEvolve consistently outperforms fixed-subset baselines and matches the final performance of full-set search while reducing the number of evaluations during optimization by 80%. Code will be released at https://github.com/Agent4Science-UTokyo/Task-CoEvolve. --- ### DARS: Dual-Level Credit Assignment RL with Structured Reasoning for Instruction-Based Image Editing Authors: Haoxiang Cao, Jiajiong Cao, Xuanpu Zhang, Changqian Yu, Chaoqun Wang Published: 2026-08-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.20161v1 Instruction-based image editing uses a planner-renderer pipeline: a vision-language model (VLM) first converts the instruction into an edit plan, and a diffusion model then executes that plan. Training such systems with only final-image rewards is inefficient because a poor edit does not reveal whether additional optimization should place more emphasis on the planner or the renderer, and even planner-dominant cases remain difficult to localize within a free-form reasoning trace. We present DARS, a reinforcement learning framework for dual-level credit assignment in this two-stage setting. Across modules, multi-plan multi-render rollouts estimate between-plan and within-plan reward variability for soft module routing, while rollout mean rewards provide hardness estimates for an adaptive curriculum. Within the planner, a four-field structured reasoning output enables a prefix-gated reward and token-level advantage reweighting, turning outcome-level feedback into localized supervision. Experiments on five benchmarks show that DARS outperforms a Joint~RL baseline with the same backbone, data, reward model, and rollout budget, with the largest gains on reasoning-intensive edits. --- ### G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding Authors: Marko Haralović, Akash Ramakrishnan, Estefania Talavera Martinez Published: 2026-08-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.20157v1 Egocentric action understanding is often addressed using large video models pretrained on extensive exocentric datasets. However, many first-person actions depend on a small number of hand-object interactions involving only a few relevant entities. We propose G3Ego, a graph-based framework for egocentric action understanding that uses gaze as a structural cue to identify action-relevant entities in the scene. From sparsely sampled frames, G3Ego constructs action scene graphs from vision-language descriptions, grounded objects, and hand cues, and then prunes irrelevant entities using the camera wearer's gaze. The resulting graph embeddings are temporally aggregated for action recognition and anticipation. Unlike prior work that uses gaze primarily as an auxiliary modality or attention signal, G3Ego incorporates gaze directly into graph construction, producing efficient and interpretable representations focused on action-relevant interactions. Experiments on EGTEA Gaze+ and MECCANO show that G3Ego achieves competitive performance compared with video-based approaches and consistently improves Macro-F1 under class-imbalanced evaluation, while avoiding reliance on computationally expensive video pretraining. These results demonstrate the effectiveness of gaze-guided graph representations for egocentric action understanding. --- ### Artificial Intelligence for Workflow Analysis in Colorectal Surgery: A Multicentric, Cross-Procedural Development and Generalization Study Authors: Pietro Mascagni, Julia Alekseenko, Pooja P Jain, Marta Goglia, Andrea Balla, Ludovica Baldari, Gianfranco Silecchia, Claudio Fiorillo, Vincenzo Tondolo, Salvador Morales-Conde, Luigi Boni, Sergio Alfieri et al. Published: 2026-08-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.20154v1 Minimally invasive colorectal surgeries (MIS-CRS) are characterised by significant variability and inconsistent outcomes. ColoWorkflow, a tool for the video-based assessment (VBA) of MIS-CRS workflow, was recently validated. However, manual VBA is time-consuming, limiting implementation. This study presents AI-ColoWorkflow, a deep learning model for automated surgical workflow analysis across MIS-CRS. Operative videos of MIS-CRS were collected from 4 centres and a publicly available dataset. Phases and steps were manually annotated according to ColoWorkflow. A deep learning model combining a fine-tuned DINOv3 vision transformer for per-frame visual feature extraction with a hierarchical multi-stage temporal convolutional network was jointly optimized for phase and step recognition. The model trained on pooled multicentric data, namely AI-ColoWorkflow was compared against centre-specific and procedure-specific models on a held-out test set. The following metrics were used for evaluation: macro F1 score, balanced accuracy, precision, and recall. AI-ColoWorkflow achieved a macro F1 of 73.01% $\pm$ 10.27 (balanced accuracy 73.43%) for phase recognition and 39.82% $\pm$ 7.06 (balanced accuracy 38.65%) for step recognition. The global model outperformed centre- and procedure-specific models in most experiments except procedure-specific step recognition. In the generalization analysis, mean F1 was 48.42% for phase recognition. AI-ColoWorkflow can reliably recognize MIS-CRS phases. A single model trained on pooled, multicentric, multi-procedural data generalises at least as well as and often better than centre- or procedure-specific models for phase recognition in MIS-CRS, while procedure-specific step models retain advantages for certain procedure types, motivating hybrid training strategies for future surgical AI development. --- ### FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models Authors: Dingzirui Wang, Xuanliang Zhang, Keyan Xu, Qingfu Zhu, Wanxiang Che Published: 2026-08-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.20153v3 Large language models (LLMs) have shown growing potential for automated theoretical computer science (TCS) research, yet existing benchmarks remain far from realistic research settings. We introduce \ourbenchmark, an expert-validated benchmark for evaluating LLMs on frontier, end-to-end TCS research. \ourbenchmark contains $143$ instances drawn from papers accepted to STOC, FOCS, SODA, and COLT in 2025-2026, preserving paper-specific definitions, assumptions, and proof dependencies, with expert-verified Lean formalizations and proofs. Evaluations of leading LLMs reveal that current models remain far from reliably completing the full research pipeline. In particular, autoformalization is the sharpest bottleneck: the best model achieves only $11.5$ on translating natural-language claims into formal theorem statements, compared with $28.6$ Pass@8 when proving human-provided formal statements. Building on \ourbenchmark, we further develop an automated TCS research framework that generates, formalizes, filters, and proves new claims. Of $64$ generated claims, only $6$ ultimately pass expert evaluation and proof verification, indicating that beyond formalization, limited research taste remains another major barrier to autonomous TCS research. --- ### FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models Authors: Dingzirui Wang, Xuanliang Zhang, Keyan Xu, Qingfu Zhu, Wanxiang Che Published: 2026-08-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.20153v1 Large language models (LLMs) have shown growing potential for automated theoretical computer science (TCS) research, yet existing benchmarks remain far from realistic research settings. We introduce \ourbenchmark, an expert-validated benchmark for evaluating LLMs on frontier, end-to-end TCS research. \ourbenchmark contains $175$ instances drawn from papers accepted to STOC, FOCS, SODA, and COLT in 2025-2026, preserving paper-specific definitions, assumptions, and proof dependencies, with expert-verified Lean formalizations and proofs. Evaluations of leading LLMs reveal that current models remain far from reliably completing the full research pipeline. In particular, autoformalization is the sharpest bottleneck: the best model achieves only $11.5$ on translating natural-language claims into formal theorem statements, compared with $28.6$ Pass@8 when proving human-provided formal statements. Building on \ourbenchmark, we further develop an automated TCS research framework that generates, formalizes, filters, and proves new claims. Of $64$ generated claims, only $6$ ultimately pass expert evaluation and proof verification, indicating that beyond formalization, limited research taste remains another major barrier to autonomous TCS research. --- ### Petri Net Description of Biological Neural Circuits for Fast Hardware Prototyping Authors: Carlo daCunha, Rodrigo Pena, Marcos Turqueti Published: 2026-08-20 Categories: cs.NE arXiv: https://arxiv.org/abs/2608.20147v1 Current approaches to simulating biological neural circuits, whether on general-purpose hardware or dedicated neuromorphic platforms, remain constrained by fixed-timestep numerical integration, hardware-imposed precision limits, and an inability to guarantee timing correctness for event-driven spiking dynamics under real-time constraints. Here, we propose a Petri net description of biological neural circuits that overcomes these limitations by modeling neurons, synapses, and spike events as a T-timed Petri net with formally verifiable timing semantics, enabling deadline-guaranteed real-time execution and analytically tractable correspondence to continuous-time leak-integrate-and-fire dynamics, independent of the underlying integration timestep. To test the model, we present the results of three simulated microcircuits: feedback inhibition, lateral inhibition, and hierarchical feature detector. The Petri neuron reproduces the expected dynamical signatures of each circuit while providing formally bounded timing guarantees throughout, with worst-case response times matching analytical predictions across all three cases. --- ### PelviNeXt: A Modality-Agnostic Hybrid Network for Pelvic Imaging in Women's Health Authors: Siam Tahsin Bhuiyan, Rashedur Rahman, Sefatul Wasi, Halima Khatun, Ashraful Islam, AKM Mahbubur Rahman, Saadia Binte Alam, M Ashraful Amin Published: 2026-08-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.20144v1 Women's health remains substantially under-resourced in medical imaging research, with pelvic pathologies such as polycystic ovary syndrome (PCOS) and pelvic fracture both suffering from a scarcity of public, well-annotated benchmark data despite their clinical importance. We introduce PelviNeXt, a modality-agnostic hybrid architecture combining a dense convolutional feature extractor, hierarchical channel-spatial attention (H-CBAM), a multi-scale fusion module (MSFM), and talking-heads multi-head self-attention (TH-MHSA), applied without modification to both pelvic ultrasound and X-ray inputs. While benchmarking PelviNeXt on PCOSGen, the only gynaecologist-annotated public PCOS ultrasound dataset, we identified extensive exact and near-duplicate contamination within and across the dataset. We audit this contamination via perceptual hashing, publicly release a deduplicated version of the dataset, and establish the first integrity-audited evaluation protocol and baseline for PCOSGen under 5-fold cross-validation. On the only publicly available pelvic fracture X-ray dataset (PXR150), PelviNeXt exceeds previously reported state-of-the-art results across accuracy, recall, specificity, and AUROC. Ablation studies confirm that each architectural component contributes to performance on both tasks. Our results demonstrate that a single architecture, applied without task-specific modification, can serve as a reliable foundation for pelvic imaging across modalities in data-scarce, under-researched areas of women's health. --- ### DPC-Net: Dual-Prior Collaborative Network for All-in-One Image Restoration Authors: Zhaokun He, Kangbiao Shi, Axi Niu, Jian Jin, Peng Wu, Wei Dong, Qingsen Yan Published: 2026-08-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.20141v1 All-in-One Image Restoration (AiOIR) aims to handle diverse degradations within a unified model. However, existing methods often overlook image semantics in degradation modeling and lack low-level visual priors during reconstruction, leading to structural distortions and semantic inconsistencies. To address these issues, we propose a novel Dual-Prior Collaborative Network (DPC-Net), which achieves high-quality restoration by jointly exploiting degradation-semantic coupled priors and low-level visual priors. Specifically, degraded images are fed into a Degradation-Aware Network (DAN) to extract degradation-semantic coupled features. To this end, a Vision-Language Model (VLM) supervises DAN by constraining its features distribution, introducing image semantics into the encoding of degradation patterns. A Degradation-Semantic Modulation Module (DSMM) further translates this guidance into degradation-semantic coupling and propagates coupled representations to the decoder. During decoding, knowledge bases provide low-level visual priors, and the Dual-Prior Collaborative Reconstruction Module (DPCR) integrates dual-prior information to guide degradation removal while preserving structure and semantics, producing high-fidelity restored images. Extensive experiments on multiple restoration benchmarks demonstrate that DPC-Net achieves superior performance against state-of-the-art AiOIR methods. --- ### Feature Evolution and Migration during Vision Transformer Training Authors: Joonas Järve, Halil Ibrahim Aysel, Tarun Khajuria, Meelis Kull Published: 2026-08-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.20134v1 We present a novel view on feature evolution in Vision Transformers (ViTs) by visualizing the training process over two dimensions -- network depth (layer) and training time (epochs). We employ Sparse Autoencoders (SAEs) to extract candidate sparse features from CLS-token representations and compare their activation profiles across epoch--layer pairs. This allows us to study feature-level dynamics that are not directly visible from representation-level similarity measures. Furthermore, we demonstrate how this framework of feature evolution allows us to describe feature migration, the change in the layer where a feature is most detectable during training. Our experiments show that migration is concentrated early in training, occurs more often toward earlier layers than toward deeper layers, and declines as feature organization stabilizes. We further find that deeper layers stabilize earlier and more strongly than shallow layers. The results show that our approach can be employed as a tool for understanding how ViTs learn and evolve. --- ### Multi-Agent Orchestration with the Common-Sense Reasoning Capabilities of LLMs for Autonomous Driving Authors: Mehdi Azarafza, Faezeh Pasandideh, Ali Ehteshami Bejnordi, Stefan Henkler, Achim Rettberg Published: 2026-08-20 Categories: cs.MA, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2608.20129v2 Autonomous vehicles require robust perception and decision-making capabilities to operate in diverse and unseen scenarios. While reinforcement learning and rule-based methods can provide effective control and safety mechanisms, their performance may degrade in situations requiring contextual reasoning. Large Language Models (LLMs) have demonstrated strong capabilities in understanding multimodal information and generating contextual reasoning, however, their use for direct vehicle control can introduce latency and hallucination risks. To address these limitations, a hybrid framework is proposed. This system uses an orchestrator to coordinate PPO-trained reinforcement learning and PID control, with LLM common-sense reasoning applied throughout the framework. LLM reasoning is further employed iteratively to refine the RL reward function for dynamic driving environments. The proposed framework is evaluated in highly randomized CARLA scenarios under diverse environmental and traffic conditions. The results demonstrate the potential of integrating LLM-based reasoning with conventional autonomous driving methods while retaining structured control and safety mechanism. --- ### Multi-Agent Orchestration with the Common-Sense Reasoning Capabilities of LLMs for Autonomous Driving Authors: Mehdi Azarafza, Faezeh Pasandideh, Ali Ehteshami Bejnordi, Stefan Henkler, Achim Rettberg Published: 2026-08-20 Categories: cs.MA, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2608.20129v1 Autonomous vehicles require robust perception and decision-making capabilities to operate in diverse and unseen scenarios. While reinforcement learning and rule-based methods can provide effective control and safety mechanisms, their performance may degrade in situations requiring contextual reasoning. Large Language Models (LLMs) have demonstrated strong capabilities in understanding multimodal information and generating contextual reasoning, however, their use for direct vehicle control can introduce latency and hallucination risks. To address these limitations, a hybrid framework is proposed. This system uses an orchestrator to coordinate PPO-trained reinforcement learning and PID control, with LLM common-sense reasoning applied throughout the framework. LLM reasoning is further employed iteratively to refine the RL reward function for dynamic driving environments. The proposed framework is evaluated in highly randomized CARLA scenarios under diverse environmental and traffic conditions. The results demonstrate the potential of integrating LLM-based reasoning with conventional autonomous driving methods while retaining structured control and safety mechanism. --- ### ID-VTG: Image-Disambiguated Video Temporal Grounding Authors: Minghang Zheng, Jingli Wei, Hongyi Yang, Yang Liu Published: 2026-08-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.20127v1 Video Temporal Grounding (VTG) faces significant challenges when natural language queries must distinguish between multiple events involving visually similar entities, particularly when relying on fine-grained visual attributes that are difficult to describe accurately in words alone. To address this, we introduce Image-Disambiguated Video Temporal Grounding (ID-VTG), a task that leverages multimodal queries combining a reference image and a text description to precisely localize segments where a specific instance performs a described action. To facilitate research, we construct two benchmarks: IDVTG-Gym, focusing on fine-grained, compositionally ordered gymnastics actions with athletes in similar uniforms; and IDVTG-InternVid, an open-world dataset featuring diverse entities (e.g., humans, animals, fictional characters) and significant temporal distractors. Methodologically, we propose the Visually-Guided Disambiguation Aggregation (VGD-Agg) framework based on a dual-branch fast-slow architecture. The fast branch efficiently generates preliminary event proposals, while the slow branch performs fine-grained frame-level matching between video frames and the reference image. We enhance discriminability via two learnable tokens: a Compare Token, which represents hard negatives to probe for the presence of the target instance (as referred to by the query image), and a Depress Value, which represents text-irrelevant events. Proposals that the Compare Token identifies as lacking the target instance are pushed toward the Depress Value, thus easing disambiguation via the text query. Extensive experiments validate our approach, which achieves state-of-the-art results on the proposed benchmarks. Code is available at https://github.com/oceanflowlab/ID-VTG. --- ### Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo Authors: Lohithsai Yadala Chanchu, Hany Abdulsamad, Christian A. Naesseth Published: 2026-08-20 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.20123v1 We study inference-time control for text generation in discrete diffusion language models, where the goal is to steer sampling toward sequence-level rewards without retraining. Prior work in this domain has focused on particle-based methods such as best-of-$n$ sampling and bootstrap sequential Monte Carlo, which may suffer from overoptimism and weight degeneracy, respectively. We address these limitations using \emph{nested} sequential Monte Carlo methods. We formulate nested SMC (NSMC) and fully-adapted nested SMC (FA-NSMC) for Feynman--Kac steering, identifying and correcting errors in prior formulations that lead to biased final estimates. We evaluate these methods on toxicity and fluency steering tasks, showing that NSMC and FA-NSMC consistently outperform best-of-$n$ and bootstrap SMC. --- ### ArmorOCR: Grounded Adversarial Visual Perception via Observation-Transferred Self-Distillation Authors: Linhan Cao, Siyuan Li, Jun Lan, Liangbo He, Guannan Li, Xiaolei Huang, Jun Jia, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Wei Sun Published: 2026-08-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.20122v1 Large multimodal models (LMMs) have demonstrated strong OCR recognition capabilities, yet remain vulnerable to adversarial visual text that is readable to humans but challenging for models to localize and recognize. Existing OCR benchmarks mainly focus on natural or document-style text, while adversarial OCR evaluations remain limited in scale, task coverage, or region-aware evaluation. In this paper, we formulate adversarial OCR as a \textbf{grounded OCR perception} task and introduce \textbf{AdvSpot}, the first benchmark for grounded adversarial OCR evaluation. AdvSpot comprises 390 images with region-level annotations, spanning 5 primary categories and 13 fine-grained adversarial OCR types. To address this challenge, we propose \textbf{ArmorOCR}, a two-stage training framework for robust adversarial OCR perception. ArmorOCR first acquires missing adversarial OCR perception from privileged transformed observations through On-Policy Self-Distillation (OPSD), and then refines grounded OCR perception through Group Relative Policy Optimization (GRPO) with task-conditioned rewards for localization, recognition, full spotting, and visual question answering (VQA). Experiments on our AdvSpot, other adversarial OCR benchmarks, and general OCR benchmarks demonstrate that ArmorOCR consistently improves adversarial OCR perception while preserving competitive general OCR capability. --- ### Privacy-Preserving Detection of Rare Disease-Associated Cell Subsets via Secure Multi-Party Computation Authors: Ş. Selcan Magara, Esther Havemann, Debora Jutz, Ali Burak Ünal, Mete Akgün Published: 2026-08-20 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.20118v1 The detection of rare disease-associated cell subsets from high-dimensional single-cell measurements is critical for understanding diseases such as leukaemia and viral infections. CellCnn, a convolutional neural network (CNN) designed for this task, has demonstrated the ability to identify phenotype-associated cell populations at frequencies as low as 0.01\%. Training such models reliably requires patient cohorts that are larger and more diverse than any single institution can typically assemble, and the underlying single-cell data is too sensitive to share across institutional boundaries under existing privacy regulations. We propose a secure multi-party computation (MPC) framework that enables the training and inference of CellCnn entirely on secret-shared data. This ensures that neither the participants nor the computing servers ever observe raw patient data or intermediate values. Evaluated on benchmark single-cell datasets for cytomegalovirus infection (CMV) and acute myeloid leukaemia (AML), our implementation preserves accuracy close to its plaintext counterpart while outperforming the prior privacy-preserving baseline. In contrast to earlier privacy-preserving approaches that removed components such as ReLU activations and bias terms, our method retains these key parts of the CellCnn architecture and supports accurate analysis without exposing raw patient data. --- ### SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events Authors: Hugo Porta, Emanuele Dalsasso, Chang Xu, Theo Gnassounou, Devis Tuia Published: 2026-08-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.20117v1 The emergence of large-scale Weather and Climate (W&C) datasets offers new opportunities for modeling extreme Earth events (ExEE) and their impacts using deep learning. However, their adoption in operational settings remains limited by the lack of models' interpretability. While for conventional text and image modalities, tools such as Sparse Autoencoders (SAEs) have proven effective for extracting human-understandable concepts, their use for the analysis of ExEE remains challenging due to the nature of W&C data. To address this, we introduce (i) a geographic location-based modulation of the inputs of SAE to capture the local semantic meaning of environmental patterns, and (ii) an ensemble of rule-based SAE-Xplainers to interpret the resulting high-dimensional features derived from complex, multi-modal environmental predictors. We evaluate our method on three ExEE types: the prediction of fires, and the detection of tropical cyclones and atmospheric rivers. We show that SAE input modulation improves both reconstruction performance and feature utilization, and that our SAE-Xplainers enable faithful interpretation of complex climatic patterns by unfolding them into human-understandable rules that are consistent with the scientific literature, while also supporting the identification of feature absorption. --- ### When Text and Numbers Disagree: Evidence Arbitration in Large Language Models Authors: Mattia Carletti, Edward Phillips, Fredrik K. Gustafsson, Patitapaban Palo, Lei Clifton, Danielle Belgrave, Xiao Gu, David A. Clifton Published: 2026-08-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.20116v1 Large language models (LLMs) are increasingly used in settings where textual summaries, numerical observations, and external tool outputs may provide conflicting evidence. We study how LLMs arbitrate between such sources when they support opposing decisions. To do so, we introduce a controlled synthetic benchmark in which latent risk trajectories generate both numerical time series and natural language summaries, allowing us to construct conflicts where exactly one evidence source is aligned with the ground-truth label. This design lets us independently manipulate modality, temporal recency, source reliability, and evidence provenance. Across open-weight instruction-tuned models, we find that arbitration behaviour is systematic rather than random: models exhibit distinct text-versus-number preferences, follow temporal recency more consistently than explicit reliability cues, and can over-rely on external forecasts even when they conflict with direct contextual evidence. These results suggest that current LLMs often rely on heuristic arbitration strategies when integrating heterogeneous evidence, highlighting a failure mode for tool-augmented decision systems. --- ### DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation Authors: Siyuan Ma, Boshi Zhang, Yutian Zhang, Qinglian Wu, Jiaqi Zhai, Dong Wei, Qiaojun Yu Published: 2026-08-20 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2608.20114v2 Mobile manipulation requires a robot to predict how locomotion and arm motion jointly alter future observations and control. Existing world-action models, developed largely for fixed-base platforms, do not explicitly distinguish camera ego-motion from base and arm actions. Here we introduce DECOWAM, a whole-body world-action model that separates these factors through dedicated conditional interfaces. DECOWAM freezes an adapted FastWAM backbone and trains residual adapters, an action-equivalent future bottleneck distilled from privileged observations, adversarially separated base and arm latents, and base-velocity conditioning for video prediction. We further introduce ARMDOG, a real-robot dataset that synchronizes video, whole-body state and action, and language. On a fixed replay protocol, DECOWAM improved both future-video and action prediction over FastWAM, reducing action MSE by 21.7% with 25.95M trainable adaptation parameters. Across 79 closed-loop trials per method, it achieved the highest observed whole-body coordination and base-displacement robustness among the compared systems, while task completion remained comparable to the strongest baseline. These results show that embodiment-aware factorization can support parameter-efficient joint visual prediction and whole-body control under moving viewpoints. --- ### DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation Authors: Siyuan Ma, Boshi Zhang, Yutian Zhang, Qinglian Wu, Jiaqi Zhai, Dong Wei, Qiaojun Yu Published: 2026-08-20 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2608.20114v1 Mobile manipulation requires a robot to predict how locomotion and arm motion jointly alter future observations and control. Existing world-action models, developed largely for fixed-base platforms, do not explicitly distinguish camera ego-motion from base and arm actions. Here we introduce DECOWAM, a whole-body world-action model that separates these factors through dedicated conditional interfaces. DECOWAM freezes an adapted FastWAM backbone and trains residual adapters, an action-equivalent future bottleneck distilled from privileged observations, adversarially separated base and arm latents, and base-velocity conditioning for video prediction. We further introduce ARMDOG, a real-robot dataset that synchronizes video, whole-body state and action, and language. On a fixed replay protocol, DECOWAM improved both future-video and action prediction over FastWAM, reducing action MSE by 21.7% with 25.95M trainable adaptation parameters. Across 79 closed-loop trials per method, it achieved the highest observed whole-body coordination and base-displacement robustness among the compared systems, while task completion remained comparable to the strongest baseline. These results show that embodiment-aware factorization can support parameter-efficient joint visual prediction and whole-body control under moving viewpoints. --- ### Flow Matching-Based PET Image Reconstruction Authors: Fumio Hashimoto, Ziqian Huang, Tatsuya Yokota, Kuang Gong Published: 2026-08-20 Categories: eess.IV, cs.CV, physics.med-ph arXiv: https://arxiv.org/abs/2608.20112v1 Generative models have shown strong potential for positron emission tomography (PET) image reconstruction. Although diffusion model-based reconstruction methods have demonstrated promising performance, they often require many reverse sampling steps with data-consistency updates incorporated into the sampling process. Flow matching offers an attractive alternative because it can directly estimate clean images from intermediate states, allowing data-consistency refinement to be separated from flow propagation. In this work, we proposed flow matching-based PET image reconstruction methods. We first established PET-FlowDPS by incorporating Poisson likelihood guidance with an expectation-maximization (EM)-based preconditioner into the FlowDPS framework. We then proposed a model-based PET reconstruction method that used a pretrained flow matching model as a prior, in which the flow-based prior, PET data refinement, and stochastic propagation were interpreted within an approximate Bayesian framework. Experimental results using ($^{\text{18}}\text{F}$)FDG brain PET datasets showed that the proposed method achieved better bias-variance trade-offs across different dose levels compared with other reference methods. These results demonstrated the potential of flow matching as a generative prior for quantitative PET image reconstruction. --- ### BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal Authors: Yigit Ekin, Enes Sanli, Aykut Erdem, Erkut Erdem, Aysegul Dundar Published: 2026-08-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.20107v1 Recent advances in generative video models have significantly improved visual realism in video object removal, yet evaluation protocols still focus on masked region fidelity, treating removal as local inpainting. In real scenes, object removal is a causal intervention: eliminating an object also requires removing its induced physical effects, such as shadows, reflections, illumination changes, translucency, and dynamic traces. Existing benchmarks lack aligned clean references or remain limited to simplified synthetic settings, preventing systematic evaluation of causal consistency. We introduce BeyondMasks, a paired benchmark for causally consistent video object removal, consisting of temporally aligned synthetic and real world video pairs with clean background references. The dataset spans diverse photometric, geometric, volumetric, and dynamic interactions, and supports both mask based and instruction driven editing. We further propose CORE, a structured vision language model based evaluation protocol that jointly measures object disappearance and after effect consistency, aligning more closely with human judgments than existing metrics. Benchmarking state of the art methods reveals systematic failures in removing secondary physical effects despite high masked region fidelity, exposing a gap between visual plausibility and causal correctness. BeyondMasks reframes video object removal as causal scene consistency rather than local reconstruction and provides a unified framework for its evaluation. --- ### OenoBench: A Wine-Domain Benchmark for Knowledge-Grounded Evaluation of Large Language Models Authors: Nikita Khudov Published: 2026-08-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.20106v1 We introduce OenoBench, a wine-domain knowledge benchmark of 3,266 multiple-choice questions across six pillars (regions, grape varieties, viticulture, winemaking, producers, business) and four difficulty tiers. The corpus is built from 38,104 atomic, source-anchored facts extracted by 35 provenance-verified scrapers from government registries (INAO, TTB, OIV), peer-reviewed journals, and Wikipedia/Wikidata. Our methodological contribution is an LLM-driven pipeline in which language models reformat verified facts and audit the result, but never serve as the source of truth: every claim traces to a URL, every question is generated by one of five strategies across five generator families, and every question is scored by a nine-agent audit calibrated against a human gold sheet via Cohen's $κ$. Evaluating sixteen frontier configurations, we find: (i) overall accuracy spans 53%-84%, led by o3 at 83.6%; (ii) reasoning-mode lift concentrates in DeepSeek R1 (+6.8pp) and is absent in Claude Opus and Gemini Pro; (iii) Anthropic shows +9pp self preference on its own questions while Google shows -8pp inverse preference; (iv) frontier open-weight models share the cost-vs-accuracy Pareto frontier with proprietary reasoning models; and (v) every config gains around 33pp on closed-book solvable items, revealing a parametric-recall ceiling that only the contextual slice avoids. We release corpus, audit findings, human-review app, and construction code under CC-BY-SA-4.0. --- ### Structured Affinity for Unsupervised Visual Class-Incremental Memory in Deep Artificial Immune Networks Authors: Siphesihle Sithungu Published: 2026-08-20 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.20104v1 Artificial immune networks (AINs) are naturally memory-forming systems, but conventional visual AINs often rely on flattened vector affinity that ignores spatial structure. This paper studies whether structured, gradient-free immune affinity can make Deep AINs viable as replay-free visual class-incremental representation-memory learners. Visual B-cells are formalized as structured templates, including shifted-template affinity, zero-normalized cross-correlation (ZNCC) filters, and feature-map binding profiles. A repertoire is treated both as memory and as a representation-inducing basis, while depth is obtained by passing binding-profile response maps to subsequent immune layers. The resulting Deep AIN exhibits adaptive latent coordinate reorganization: as new classes arrive, the binding-profile space evolves while retaining recoverable structure for earlier classes. Experiments on sklearn digits, MNIST, Fashion-MNIST, and KMNIST show that preserving response maps is critical. Scalar binding-profile variants underperform, whereas feature-map Deep AINs learn class-discriminative visual memory without replay, label-driven immune updates, or backpropagation through the immune layers. On sklearn digits, downstream probes fitted on the learned binding profiles reach 0.939 final balanced accuracy with logistic regression and 0.902 with 1-nearest-neighbour after all ten classes are encountered, with initial-class retention of 0.978. Adaptive layer-wise scale calibration further improves the two-layer feature-map Deep AIN to 0.978 balanced accuracy. With the same calibration rule, Fashion-MNIST reaches 0.814 and KMNIST reaches 0.853. These probes are external validation tools, not components of the AIN. The results identify structured affinity, response-map preservation, adaptive latent reorganization, and layer-wise scale calibration as key mechanisms for replay-free visual immune memory. --- ### Reward-Guided Autoregressive Graph Generation for Efficient Multi-Agent Communication Topology Design Authors: Poomphob Suwannapichat, Boonyarit Changaival, Caesar Wu, Pascal Bouvry Published: 2026-08-20 Categories: cs.MA, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.20099v1 LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption. Recent work on automatic topology design, ARG-Designer, has reframed this problem as autoregressive graph generation. However, its training objective provides no explicit incentive for the model to generate sparse and efficient topologies. We address this limitation by introducing a Reward-Guided Autoregressive Graph Generation (RGA-Designer) inspired by Reinforcement Learning from Human Feedback (RLHF). We train a reward model that jointly captures task correctness and structural compactness, and then fine-tune the pretrained graph generator using the reward model as feedback. Our method preserves task accuracy at the level of ARG-Designer while reducing token consumption by an average of 20.5%. --- ### HandMvNet: Real-Time 3D Hand Pose Estimation Using Multi-View Cross-Attention Fusion Authors: Muhammad Asad Ali, Nadia Robertini, Didier Stricker Published: 2026-08-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.20093v2 In this work, we present HandMvNet, one of the first real-time method designed to estimate 3D hand motion and shape from multi-view camera images. Unlike previous monocular approaches, which suffer from scale-depth ambiguities, our method ensures consistent and accurate absolute hand poses and shapes. This is achieved through a multi-view attention-fusion mechanism that effectively integrates features from multiple viewpoints. In contrast to previous multi-view methods, our approach eliminates the need for camera parameters as input to learn 3D geometry. HandMvNet also achieves a substantial reduction in inference time while delivering competitive results compared to the state-of-the-art methods, making it suitable for real-time applications. Evaluated on publicly available datasets, HandMvNet qualitatively and quantitatively outperforms previous methods under identical settings. Code is available at github.com/pyxploiter/handmvnet. --- ### HandMvNet: Real-Time 3D Hand Pose Estimation Using Multi-View Cross-Attention Fusion Authors: Muhammad Asad Ali, Nadia Robertini, Didier Stricker Published: 2026-08-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.20093v1 In this work, we present HandMvNet, one of the first real-time method designed to estimate 3D hand motion and shape from multi-view camera images. Unlike previous monocular approaches, which suffer from scale-depth ambiguities, our method ensures consistent and accurate absolute hand poses and shapes. This is achieved through a multi-view attention-fusion mechanism that effectively integrates features from multiple viewpoints. In contrast to previous multi-view methods, our approach eliminates the need for camera parameters as input to learn 3D geometry. HandMvNet also achieves a substantial reduction in inference time while delivering competitive results compared to the state-of-the-art methods, making it suitable for real-time applications. Evaluated on publicly available datasets, HandMvNet qualitatively and quantitatively outperforms previous methods under identical settings. Code is available at github.com/pyxploiter/handmvnet. --- ### Towards Professional Tennis Styles for Humanoid Robots with Adaptive Motion Planning and Tracking Authors: Tao Huang, Ruofei Liu, Xuchen Tang, Xinyin Zhang, Junli Ren, Huayi Wang, Feiyu Jia, Yukai Qi, Kangning Yin, Weishuai Zeng, Lipeng Chen, Xi Li et al. Published: 2026-08-20 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.20087v1 Humanoid robots have recently demonstrated promising capabilities in real-world ball sports. However, achieving professional motion styles while maintaining strong task performance remains challenging. In this work, we propose AdaPT, an Adaptive Motion Planning and Tracking framework that learns professional tennis serving and rally styles directly from broadcast videos. This hierarchical design is motivated by the key insight that the planner generates stylistic kinematic motions, while the tracker executes them with minimal interference with planning. Despite its effectiveness in simulation, a substantial sim-to-real gap emerges: tracking performance inevitably degrades on real robots, and this degradation is partially overlooked by autoregressive planning and further compounded by noisy perception. To address these issues, our adaptation mechanism improves tracking robustness by learning to track randomized execution speeds, while conditioning the planner on a learned motion-speed adapter to mitigate compounding errors. Real-world experiments on the Unitree G1 demonstrate the effectiveness of our adaptation mechanism in bridging the sim-to-real gap. We further deploy AdaPT policies on the full-size Dobot Atom humanoid robot (1.7m) and demonstrate in-the-wild serving without motion capture. Beyond these results, our real-world experiments reveal both algorithmic and engineering insights for future humanoid ball-sports systems. Videos and code are available on our \href{https://humanoidtennis.github.io/AdaPT/}{project website}. --- ### Evidence-Gated Task and Motion Planning with Vision-Language Models Authors: Tsunehiko Tanaka, Matthew Stephenson, Alistair Macvicar, Edgar Simo-Serra Published: 2026-08-20 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.20084v1 Robots executing long-horizon manipulation tasks from natural-language instructions must reason about both semantic task structure and geometric feasibility. However, under partial observability, the availability of goal-relevant objects may be uncertain. In such cases, approaches that combine Vision-Language Models (VLMs) with Task and Motion Planning (TAMP) may generate subgoals that rely on the VLM's prior knowledge without observational support, leading to execution failures or unintended outcomes. We propose Evidence Acquisition and Feasibility Gating (EAFG), a framework that acquires visual evidence through VLM-generated exploratory subgoals and TAMP-based execution. EAFG then applies a feasibility gate to decide whether to proceed with task planning, acquire further evidence, or halt. Our experiments show that, in cooking tasks with ambiguous object use, EAFG improves recipe completion by discovering task-relevant objects before planning. For instructions requiring an absent object, EAFG promotes appropriate halt decisions and reduces repeated attempts to manipulate that object. --- ### SABET-QA: Temporal Knowledge Graph Question Answering Authors: Brahim Touayouch, Mirette Moawad, Dmitry Akulov Published: 2026-08-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.20083v1 Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet existing embedding-based methods struggle with multi-step queries due to single-pass reasoning pipelines. We propose SABET-QA, a framework that iteratively refines reasoning states across multiple hops via a bidirectional entity-temporal scoring mechanism and a slot-aware contextualization module that aligns question semantics with temporal KG embeddings. A differentiable working memory enables progressive hypothesis refinement, while auxiliary temporal boundaries serve as coarse supervision when available. Experiments on CronQuestions, Complex-CronQuestions, MultiTQ, and TimeQuestions demonstrate consistent improvements over strong baselines, particularly on complex multi-step temporal queries. --- ### V-REX: Efficient Specialist VLM Training for Veterinary X-Rays Authors: Tim Elsner, Nicole McNally, Andre Dourson, Michael Fitzke Published: 2026-08-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.20069v1 While generalist VLMs are expensive to train, creating domain experts is widely assumed to require fine-tuning increasingly large foundation models. We show that, in veterinary radiology, this assumption is misguided. By rethinking the entire VLM pipeline - from text tokenisation and pre-training to grounding and inference - we demonstrate that careful engineering can yield models that outperform much larger foundation models from scratch, without relying on any other data. Our approach introduces new strategies for generative pre-training and grounding that improve training efficiency, increasing data utilisation and downstream performance. Using only a fraction of the parameters, data, and compute of contemporary generalist models, we develop the first VLM capable of generating diagnostic reports for veterinary radiographs, surpassing open foundation models on this task by significant margin. --- ### Orthogonal JEPA: Factorized Predictive States for Latent World Models Authors: Taoyong Cui, Pheng Ann Heng, Wanli Ouyang Published: 2026-08-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.20065v2 World models construct latent states that support prediction, planning, and reasoning about an underlying system. Joint-embedding predictive architectures (JEPAs) offer a direct way to learn such states by predicting targets in representation space instead of reconstructing every detail of the observation. Standard JEPAs, however, organize all predictable content through one target embedding and one prediction pathway. In complex systems, this monolithic state can allocate redundant capacity to dominant signals while providing weak or conflicting gradients to less dominant predictive structure. We introduce \method, a latent world-modeling framework based on orthogonal predictive factorization. Learned basis matrices analyze each target state into multiple components, and a dedicated prediction branch estimates each component from a shared context representation. Predictive regression preserves the factor magnitudes required for state synthesis, an orthogonality objective discourages repeated directions, factor-activity regularization maintains variation in projected targets, and online variance regularization discourages coordinate-wise encoder collapse. Predicted components are synthesized into a complete latent state that can be used by a readout, decoder, planner, or autoregressive rollout. The same predictive-state mechanism applies when the target is temporally future, spatially hidden, or another partial observation of the same system. Experiments on controlled vision, single-cell transcriptomics, longitudinal health records, continuous control, and molecular dynamics evaluate representation quality, forecasting, planning, and long-horizon stability. --- ### Orthogonal JEPA: Factorized Predictive States for Latent World Models Authors: Taoyong Cui, Pheng Ann Heng, Wanli Ouyang Published: 2026-08-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.20065v1 World models construct latent states that support prediction, planning, and reasoning about an underlying system. Joint-embedding predictive architectures (JEPAs) offer a direct way to learn such states by predicting targets in representation space instead of reconstructing every detail of the observation. Standard JEPAs, however, organize all predictable content through one target embedding and one prediction pathway. In complex systems, this monolithic state can allocate redundant capacity to dominant signals while providing weak or conflicting gradients to less dominant predictive structure. We introduce \method, a latent world-modeling framework based on orthogonal predictive factorization. Learned basis matrices analyze each target state into multiple components, and a dedicated prediction branch estimates each component from a shared context representation. Predictive regression preserves the factor magnitudes required for state synthesis, an orthogonality objective discourages repeated directions, factor-activity regularization maintains variation in projected targets, and online variance regularization discourages coordinate-wise encoder collapse. Predicted components are synthesized into a complete latent state that can be used by a readout, decoder, planner, or autoregressive rollout. The same predictive-state mechanism applies when the target is temporally future, spatially hidden, or another partial observation of the same system. Experiments on controlled vision, single-cell transcriptomics, longitudinal health records, continuous control, and molecular dynamics evaluate representation quality, forecasting, planning, and long-horizon stability. --- ### Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts Authors: Nayeon Kim, Hojin Lee, Yunju Bak, Jaesun Park, Boseop Kim Published: 2026-08-20 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.20061v1 Mixture-of-Experts (MoE) architectures significantly expand model capacity without a proportional increase in computational cost. However, optimizing their hyperparameters---particularly the learning rate---at extreme scales of both model size and token budget via sweeping remains computationally prohibitive. In this paper, we propose a compute-efficient, two-step hyperparameter transfer framework that estimates optimal learning rates for training large MoE models by transferring them across scaling model widths, and subsequently extrapolating to trillion-token horizons. First, we formulate a Maximal Update Parameterization ($μ$P) adaptation for MoE architectures utilizing Multi-head Latent Attention (MLA) and the Muon optimizer, demonstrating that optimal learning rates transfer consistently across width-scaled models. Second, we extend this transferability along the token dimension by establishing a predictive scaling law. By applying linear regression to the optimal values derived from small proxy models on limited budgets, we successfully extrapolate the ideal learning rate to massive training horizons (e.g., 10 trillion tokens) with high fidelity ($R^2=0.95$). Consequently, this indicates that proxy training on small models is sufficient to determine the optimal learning rate for the extensive training of large-scale MoEs. We apply the proposed methodology to pretrain our foundation model (155B total, 17B active parameters) from scratch, and the stable training and evaluation results validate that optimal configurations for full-scale target models can be accurately predicted with minimal ablation costs. --- ### Gravity-aware partially calibrated absolute pose estimation from affine- or rotation-covariant features Authors: Marcus Valtonen Örnhag, Alberto Jaenal, Stefan Adalbjörnsson Published: 2026-08-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.20056v1 Inertial measurement units (IMUs) are now standard in most consumer devices, such as smartphones, drones, and extended reality (XR) headsets. By fusing visual and inertial data, localization systems gain significantly in speed and robustness compared to vision-only or IMU-only approaches. However, traditional pose estimation methods fail to utilize the local geometric information embedded in feature descriptors like SIFT. Recent work has proved the advantages of leveraging this information for relative and absolute pose estimation, but its application to partially calibrated absolute pose estimation remains unexplored. In this paper, we derive novel constraints for joint estimation of absolute pose and focal length, making use of a gravity vector obtained from IMU data and the feature-induced local geometry, which we use to construct two efficient solvers: UP1PfAC, that operates given a single affine correspondence and UP2PfORI, which requires two orientation-covariant features. Unlike traditional, semi-calibrated absolute pose methods requiring four point correspondences, our solvers benefit from fewer samples and lower computational cost, simplifying robust estimation in modern RANSAC-like frameworks. We evaluate the proposed solvers against the state-of-the-art on large-scale public datasets and demonstrate that our method achieves fast and accurate localization and focal length estimation. --- ### EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models Authors: Yiting Qu, Ziqing Yang, Chi Cui, Ye Leng, Junjie Chu, Yang Zhang Published: 2026-08-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.20055v1 Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet whether these hidden CoTs can be directly extracted from black-box models remains largely unexplored. In this work, we systematically study whether hidden CoTs can be extracted near-verbatim from black-box LRMs through API interactions. We identify a previously overlooked reasoning replay surface between tool calls and develop EchoCoT, a multi-step attack that iteratively extracts hidden CoTs using API-returned fidelity signals. We further develop an LLM-based optimization framework that automatically searches for an effective universal injection trajectory across various datasets. We evaluate EchoCoT on three open-source and five frontier proprietary LRMs. On open-source LRMs, EchoCoT achieves up to 66.4\% near-verbatim extraction success, with the extracted trace length within 10\% of the target and at least 90\% of tokens exactly matching the target CoT. The same injection trajectory also generalizes to unseen datasets, achieving up to 80\% extraction success under the same criterion. For tested frontier proprietary LRMs, a substantial fraction of extracted CoTs closely align with provider-reported reasoning lengths and available CoT summaries. EchoCoT can also extract very long CoTs: on Gemini-2.5, it extracts 33,463 tokens from a 32,948-token target. These results establish hidden-CoT extraction as a practical security risk and highlight the need to better protect hidden CoT assets. --- ### What You Can't See Is What You Learn: Slot-Selective Evidence Masking Favors Compositional Generalization in Shared-Genome Language-Model Societies Authors: Narcis Marincat Published: 2026-08-20 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2608.20054v3 Multi-module neural systems often expose every module to the full input. We test whether a slot-selective evidence-masking regime -- restricting each module to its own evidence span -- changes which solutions gradient-based training discovers. Four-cell societies share one frozen pretrained language model and one low-rank adapter, communicating only through two model-width continuous vectors in a fixed relay. On a prospectively sealed natural-language function-composition task, we train ten matched restricted/global pairs identical except for the attention mask. Restricted-visibility societies outperform their globally visible twins by at least 20 percentage points at both depths in 9 of 10 pairs, with median paired advantages of 0.7648 and 0.6050. Cutting communication reduces every restricted society to chance, and in a post hoc collision-stratified analysis the depth-three advantage remains 0.558 on programs whose complete affine map never appeared in training. In six post hoc-selected restricted societies, packet interventions on correctly answered held-out episodes are consistent with approximately value-indexed relay states; the sole high-performing global model also requires communication, but its same-value packets are not interchangeable across episodes. Thus restricted visibility is not necessary for composition. Under the tested seeds, streams, task world, and training budget, the masking regime strongly shifted which solutions training discovered: a post hoc mask crossover finds both arms mask-native. Because the restricted mask both blocks foreign evidence and implicitly identifies each cell's assigned slot, attribution to evidence visibility alone awaits a role-marked control. The preregistered battery nevertheless formally fails because restricted-arm median depth-three accuracy is 0.6988, below the 0.70 floor; an earlier qualification cohort yielded 0/10 complete passes. --- ### What You Can't See Is What You Learn: Restricted Evidence Visibility Favors Compositional Generalization in Shared-Genome Language-Model Societies Authors: Narcis Marincat Published: 2026-08-20 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2608.20054v1 Multi-module systems often expose every module to the full input. We test whether restricting evidence visibility changes which solutions gradient-based training discovers. Four-cell societies share one frozen pretrained language model and one low-rank adapter, communicating only through two model-width continuous vectors in a fixed relay. On a prospectively sealed natural-language function-composition task, we train ten matched restricted/global pairs sharing initialization bytes, training order, token layout, parameters, and computation; only the attention mask differs. Restricted societies outperform their globally visible twins by at least 20 points at both depths in 9 of 10 pairs, with median paired advantages of 0.7648 and 0.6050. Cutting communication reduces every restricted society to chance, and the depth-three advantage remains 0.558 on programs whose composite function never appeared in training. Across six audited restricted societies, same-value packet transplants preserve behavior at 0.94-1.00 across all tested interfaces; destructive interventions collapse performance; and counterfactual packets redirect outputs toward the mathematically predicted answer. The sole high-performing global model also requires communication, but its same-value packets are not interchangeable across episodes. Restricted visibility is thus not necessary for composition; under this protocol it substantially increases the probability of a generalizing relay and favors a reusable, value-indexed interface. The complete preregistered battery nevertheless formally fails because restricted-arm median depth-three accuracy is 0.6988, below the 0.70 floor. An earlier qualification cohort likewise yielded 0/10 complete passes: one model met every task-performance gate, but all ten failed ordinary-language preservation, confining the system to explicitly task-gated use. ---