# Research Papers — 2026-08 · bundle page 73 of 240 > Full-text markdown of papers #3601–3650 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/73 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/72.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/74.md) ### Beyond Accuracy and Surface Fluency: Risk-Sensitive Evaluation of LLMs for Legal Clause Generation Authors: Devansh Singh, Sundaraparipurnan Narayanan Published: 2026-08-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.22127v1 Large language models (LLMs) are increasingly used to draft contractual language, yet conventional accuracy or preference-based evaluations are poorly matched to legal drafting. A clause may be fluent and stylistically polished while still omitting an essential carve-out, allocating risk in an unenforceable way, assuming an inapplicable jurisdiction, or exposing a party to regulatory liability. This paper presents a empirical study design and framework for evaluating LLM-generated contract clauses. The study evaluates four models - Claude Haiku 4.5, Gemini 2.5 Flash Lite, GPT 5.4 Nano, and Qwen 3.5 Flash, across 22 contract clause categories and 34 legally-motivated failure modes. We combine two evaluation frameworks: CLAUSE, which classifies prompts by legal function and failure target, and LENS-CRAFT, which scores outputs across nine legal-quality dimensions. Instead of averaging dimension scores, the study applies a Max Severity Principle so that a single legally decisive defect remains visible. The paper provides the evaluation protocol, taxonomy, analysis plan, and a results structure for reporting empirical findings. We argue that legal AI evaluation should move beyond aggregate accuracy toward clause-specific, failure-mode-driven, and risk-sensitive assessment. --- ### Improving Generalization and Robustness in Offline Reinforcement Learning via Boundary-Aware Data Augmentation Authors: Gong Gao, Weidong Zhao, Xianhui Liu Published: 2026-08-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.20300v1 Current offline reinforcement learning (ORL) algorithms tend to overfit the training dataset and exhibit poor in-distribution generalization and robustness performance when deployed to real environments, thus compromising their effectiveness. Existing methods typically enhance in-distribution generalization and robustness by leveraging regularization techniques widely used in computer vision. However, due to the high sensitivity of low-level physical signals to distributional shifts, these methods still suffer from notable limitations in in-distribution generalization and robustness, making it difficult to achieve stable performance in complex environments. To address this issue, we theoretically analyze the error bounds of the behavior policy and action-value function trained with random episode interpolation, revealing that the error scales positively correlated with the distance between states. Based on this insight, we propose a method called $\bf{B}$oundary-$\bf{A}$ware $\bf{D}$ata $\bf{A}$ugmentation (BADA), which leverages neighboring states to construct interpolation boundaries, enabling the generation of synthetic data that more faithfully preserves the original data distribution. We first conduct qualitative studies in a toy environment, showing that BADA generates mixed samples that preserve desirable policy smoothness while accurately reconstructing multimodal value distributions. Extensive experiments on limited offline datasets further demonstrate that BADA attains state-of-the-art performance across diverse benchmarks. --- ### A Hybrid Gaze-Motor Imagery BCI Framework for Effective Decision Communication Authors: Gowtham Reddy N, KongFatt Wong-Lin, Yogesh Kumar Meena Published: 2026-08-22 Categories: cs.HC, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2609.20273v1 Non-invasive brain-computer interfaces (BCIs) and eye-tracking technologies offer promising communication pathways; however, motor imagery (MI)-based BCIs often suffer from low discriminability and high inter-subject variability. To mitigate these issues, this study investigates the impact of visual fixation on neural response stability in both standalone MI and hybrid MI-eye tracking systems. We then propose a novel asynchronous hybrid paradigm that streamlines user intent by utilising eye-tracking for direct selection, followed by MI-based confirmation, significantly reducing the operational steps required by conventional systems. The paradigm was evaluated with 15 healthy participants using a 16-channel EEG system. Results show that MI-related information is predominantly localised within motor cortex regions, with limited-channel configurations (SVM: 0.58) achieving performance comparable to full-montage setups (SVM: 0.54). The hybrid MI paradigm further outperforms conventional MI, achieving up to 100% accuracy with greater robustness across all channel configurations. Our findings indicate that visual fixation enhances neural response stability, while integrating eye-tracking with MI enables the development of reliable, scalable multi-command BCI systems suitable for real-world applications. --- ### Open-Set Cattle Muzzle Identification: A Leakage-Controlled Benchmark and Evaluation Protocol Authors: Lalit BC, Dharmendra Singh Chaudhary, Shovit Nepal Published: 2026-08-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28663v1 Reliable individual cattle identification supports disease surveillance, vaccination records, breeding management, and livestock insurance. Although the bovine muzzle provides a stable, non-contact biometric, existing muzzle-recognition systems largely assume a closed set of enrolled animals, limiting their practical deployment. We reformulate cattle muzzle biometrics as an open-set, gallery-based identification problem that can reject previously unseen animals and support incremental enrollment without model retraining. We introduce a leakage-controlled evaluation protocol based on identity-disjoint splits, per-fold retraining, held-out threshold calibration, verified duplicate removal, and bootstrap confidence intervals. We evaluate the framework using two contrasting embedding configurations: a hybrid CNN-ViT metric-learning model and the MegaDescriptor-L foundation model. Under oracle threshold selection, the hybrid model achieves detection-and-identification rates of 98.3%, 96.4%, and 93.6% at target false-acceptance rates of 10^(-1), 10^(-2), and 10^(-3), respectively, while MegaDescriptor-L achieves 99.3%, 98.1%, and 96.1%. However, deployable threshold calibration reveals a substantial difference between oracle and calibrated performance: the hybrid model achieves a false-acceptance rate of 1.03% at a 1% target, whereas MegaDescriptor-L reaches 2.44%. Incremental enrollment further achieves Rank-1 accuracy above 91% with a single reference image and up to 97.3% with eight reference images, without retraining the model or degrading the existing gallery. These results demonstrate that threshold calibration, leakage control, and embedding quality are critical for reliable open-set cattle identification and provide a practical evaluation framework for deployment-oriented animal biometric systems. --- ### FRAC-MAS: A Safe and Explainable Multi-Agent System for Fracture Diagnosis Authors: Hardik Iyer, Tirath Bhathawala, Mihir Panchal, Ying-Jung Chen, Kiran Bhowmick, Pankaj Sonawane, Meera Narvekar Published: 2026-08-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28662v1 Fracture detection and its clinical interpretability see notable improvements when deep vision models are integrated with agentic AI architectures. While deep learning models achieve high diagnostic performance, their black-box nature limits clinical adoption. We propose FRAC-MAS, an agentic AI system for automated, explainable, and safe bone fracture detection. The framework combines a stacked ensemble of four vision models with conformal prediction to produce statistically grounded differential diagnoses, while a multi-agent workflow performs independent verification, retrieves clinical guidelines, and generates patient-friendly reports. A pipeline-depth ablation study confirms that our multi-agent critic triages 86.6% of cases into a high-confidence auto-confirmed cohort while escalating uncertain cases, outperforming a single-agent baseline. Patient preference studies against Llama, MedGemma, and Gemini further demonstrate significantly more comprehensible clinical reports. These results suggest that integrating multi-agent critics with conformal guarantees enables safer radiology triage while preserving clinician oversight. More broadly, FRAC-MAS demonstrates how cooperative agentic architectures can serve as auditable, human-in-the-loop decision support systems for safety-critical healthcare. Our code is available at https://github.com/hardik1712/FRAC-MAS, and the website is available at https://frac-mas.vercel.app. --- ### Effectiveness of IoT and Deep Learning for Detection and Severity Assessment of Postelectrotermes militaris in Tea Plantations Authors: D. K. C. Senevirathna, A. A. E. Nanayakkara, H. M. C. K. Kulathunga, J. K. D. P. Nadula, R. M. Mapatuna, Malithi Nawarathne, Jaliya L. Wijayaraja, P. D. Senanayake, Samitha Vidhanaarachchi, Kalpani Manathunga Published: 2026-08-22 Categories: cs.AI, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2608.27480v1 Tea plantations are vulnerable to Postelectrotermes militaris, commonly known as the Upcountry Live Wood Termite (ULWT), which can cause substantial damage when infestations remain undetected. This study proposes an IoT-enabled acoustic monitoring framework integrated with deep learning for early detection and severity assessment of ULWT infestations in tea plantations. Research Method: Audio signals were captured non-invasively from tea trunks using a high-sensitivity microphone connected to a Raspberry Pi-based IoT device, with geographic coordinates recorded for spatial tracking. After trimming, resampling, and segmentation, 2,000 ten-second samples were obtained, comprising 1,000 healthy and 1,000 infested samples, and divided into 1,600 training, 200 validation, and 200 test samples. The dataset used in this study is publicly available on Kaggle (Senevirathna et al. 2026). Fourier-derived spectrograms trained a CNN for infestation classification and probability estimation. A weighted severity model combined CNN probability, mean acoustic amplitude, and nearby infested plants within 5 m, with geospatial mapping used to visualize infestation distribution. Findings and Values: Field trials in a ULWT-affected tea plantation in Pundaluoya demonstrated feasibility under realistic environmental noise. On the held-out test set, the CNN achieved 81.5% accuracy, 80.6% precision, 83.0% recall, 81.8% F1-score, and 0.819 ROC-AUC. Beyond binary infestation detection, the framework introduced quantitative severity assessment using infestation probability, acoustic amplitude, and nearby infested plants. The resulting severity and geospatial outputs can support plantation managers in identifying high-risk areas, prioritizing field inspections, and implementing more timely and targeted control measures. --- ### When the Canonical Completion Is Wrong: Formalizing and Measuring the Jump in Large Language Models Authors: Dai Shi, Xiaoyu Li, José Miguel Hernández-Lobato Published: 2026-08-22 Categories: cs.CL, cs.AI, cs.LG, cs.LO arXiv: https://arxiv.org/abs/2608.26187v3 Whether large language models (LLMs) can perform the abductive leap from evidence to a new system of axioms, commonly referred to as a jump, has recently attracted considerable debate. A prominent position holds that LLMs are structurally incapable of such jumps, while recent studies challenge both its mechanism and empirical evidence. One of the main reasons why the debate remains open is the difficulty of defining the jump precisely enough to test it. In this paper, we attempt to develop a formal account of the jump in four steps and measure the second. These steps ask what the default completion of partial data is, when the constraints exclude it, whether the new structure agrees with later observations, and how successive jumps compound. We define a \emph{jump instance} as a finite extension problem whose constraints exclude the canonical completions given by the Kan extensions and leave one correct completion up to renaming. In this setting, a model with a canonical default performs the second step by producing the correct completion under the constraints. We evaluate fourteen models across three certified families. The canonical completion returns once in $13{,}300$ constrained answers across all runs. Several calibrated models also give the correct completion reliably, including three API models that solve $159$ of $162$ primary chain trials, suggesting that they can jump at this step. We further formalize the third and fourth steps, whose empirical evaluation remains future work. We hope our work paves the path for formalizing and measuring the full jump in the future. The code of the paper is available at https://github.com/EEthanShi/kan-jump-test. --- ### Investigating the Influence of Prompt and Response Languages on LLM Content Generation Authors: Thi Thanh Nhan Nguyen, Mai Khoi Tieu, Michael A. Riegler, Pål Halvorsen, Thu Nguyen Published: 2026-08-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.26186v1 This study examines how prompt and response language influence the behavior of large language models. Using five models, we evaluated answers to 68 non translation questions across four language conditions: English to English, English to Norwegian, Norwegian to Norwegian, and Norwegian to English. After removing refused items, the dataset contains 1348 responses. We measure length differences with Cohen d, semantic fidelity with LabSE cosine similarity, and cross lingual keyword overlap with both raw and soft Jaccard. Prompt language has a strong effect on response length. With English output, Norwegian prompts shorten responses by about thirty seven percent. With Norwegian output, English prompts shorten responses by about forty one percent. The largest cross lingual contrast shows a reduction in word count but a smaller reduction in tokens, reflecting tokenizer differences. Despite variation in length, semantic similarity remains high, and soft Jaccard reveals substantial conceptual overlap that raw Jaccard does not capture. Effect sizes vary across models, indicating heterogeneity. Prompt language is not neutral and systematically shapes output length and lexical realization, with implications for multilingual prompt design. --- ### Can You Say This for Me? Speaking Up by Proxy in Co-Located Discussion Authors: Yue Shen, Rehema Abulikemu, Ryan P. McMahan, Yan Chen Published: 2026-08-22 Categories: cs.AI, cs.ET, cs.HC arXiv: https://arxiv.org/abs/2608.26185v1 Equal participation in co-located discussion is important for effective collaboration, yet people often hold back when they anticipate negative interpersonal or professional consequences, especially when raising a point requires voicing it themselves. We present SecondVoice, a mixed-reality system that enables people to speak up through an embodied virtual proxy. By separating what is said from who says it, SecondVoice brings hesitant points into the live spoken discussion without putting the speaker on the spot. Using a private overlay, users specify their intent through a structured specification process rather than composing a full utterance. The system reformulates the input and voices it into the conversation through the proxy. We characterize a design space of participation channels under social risk. In a preliminary within-subject study (N = 16), we compare the complete SecondVoice system with an anonymous text-board channel across two group discussion tasks. Half of participants reported using SecondVoice for a point they did not say aloud, compared with 18.8% for the text board. Proxy-delivered points entered the spoken floor and were followed by multi-turn group engagement, which we did not observe after text-board posts. Participants described the channel as situationally valuable but identified tradeoffs around timing, ownership, and trust in reformulation. --- ### TutorTrace: A Dataset and Taxonomy for Classifying Learner Behavioral States during AI-Assisted Programming Education Authors: David Barron, Xiaohang Tang, Rezky Dwisantika, Minsun Kim, David H. Smith, Jiaming Cui, Yan Chen Published: 2026-08-22 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.26184v1 AI programming tutors provide scalable support, yet lack the behavioral context human tutors rely on to adapt support to learners' needs. We present TutorTrace, a dataset and behavioral abstraction pipeline that makes learners' behavioral context visible and computable in real time from low-level IDE telemetry. Across four deployments in two introductory Python courses (N=480), TutorTrace captures approximately 180K telemetry events, 13,633 behavioral segments, and 27 continuously computed metrics. From this foundation, we derive a taxonomy of learner activity before the first AI query, between consecutive queries, and across the full session, enabling systems to respond not just to what learners say, but to what they have done leading up to the help-seeking moment. In a preliminary classroom evaluation, behavior-aware prompts were associated with a decrease in intervals between queries with no independent work from 50.0% to 20.7%. As an additional demonstration of downstream utility, we evaluate TutorTrace on two held-out prediction tasks: whether a learner will query within the next 60 seconds (AUROC=.726) and whether an upcoming query reflects guided or dependent help-seeking (AUROC=.717). Together, these findings show how behavioral context can enable adaptive AI tutoring at scale. --- ### When May an Agent Stop? Evidence-Carrying Termination for Tool-Using LLMs Authors: Jason Liu Published: 2026-08-22 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.23623v1 Tool-using agents must decide when to stop. Existing systems already gate terminal success, certify execution traces, or enforce runtime polici es, but do not test this particular receipt-, scope-, and closed-replay design at the COMPLETE boundary across controlled termination faults. W e instantiate and evaluate Evidence-Carrying Termination (ECT): an agent may return COMPLETE only when a typed certificate binds every required answer claim to valid, in-scope trace evidence and a deterministic replay reconstructs the claimed value. A locked static study crosses 48 ful ly synthetic tasks in six tool-use families with clean execution and eight faults. ECT produced 0/288 unsafe completions versus 252/288 for the inspected termination-critic core (difference -87.50 pp, 95% task-cluster interval (-87.50, -87.50) pp). A fresh, prespecified and frozen 576- trajectory study then compares ECT with the critic core, its faithful controller, and a full-trace LLM critic. On 22 primary held-out task clus ters, ECT produced 0/66 premature unsupported terminations versus 40/66 for the controller (difference -60.61 pp, 95% interval (-78.79, -40.91) pp), while supported completion was 97/132 versus 92/132 (difference 3.79 pp, interval (0.00, 9.09) pp), satisfying a -10-point noninferiority margin. ECT executed successful recovery in 18/66 trajectories, of which 17 subsequently completed with support; all three closed-loop gates p assed. ECT certifies support in a recorded trace under declared assumptions, not external truth, safety, or alignment. --- ### LLM Agents Perform Controlled Experiments Using Simulation Models Authors: Yuchen Xia, Michael Weyrich, Nasser Jazdi, Johannes Stümpfle, Johannes Sigel, Akshay Narla, Gavin K. Reynolds, Anna Jawor-Baczynska, Pol Llopart Published: 2026-08-22 Categories: cs.AI, cs.CL, cs.MA, cs.SE arXiv: https://arxiv.org/abs/2608.23622v1 Large language models (LLMs) have shown strong capabilities in reasoning, planning, and tool use, but many scientific and engineering tasks require more than plausible text and code generation. They require understanding how a system responds to intervention, which in practice depends on controlled experimentation. In this work, we propose a multi-agent framework that enables LLM agents to conduct controlled experiments with scientific simulation models for pharmaceutical process design. Given a user query and a baseline configuration, the system constructs a structured task representation, designs experiments, executes comparative simulation, interprets the resulting outcomes, and synthesizes evidence-based recommendations for process parameter optimization. By coupling language models with high-fidelity simulation models in an interactive agent framework, the proposed system supports reasoning through intervention, comparison, and observation. As a result, it produces more specific and actionable outputs than language-only reasoning. In an industrial application setting, this advantage is reflected in higher output specificity as well as improved user-rated correctness and helpfulness. Ablation studies and visualized case analyses further demonstrate the effectiveness and practical utility of simulation-integrated experimental reasoning. --- ### Identifying Latent Declarative Representations of Code for Assisting Repository Migration Authors: Shraddha Surana, Ashwin Srinivasan, Michael Bain Published: 2026-08-22 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.23619v1 Legacy software repositories embed decades of domain knowledge in undocumented code, making understanding and modernization difficult. We treat a program as the implementation of an unobserved, declarative description of its computation and investigate whether making this latent declarative representation explicit improves repository-scale porting. ADFD-Migrate approximates the latent representation with an annotated data-flow diagram (ADFD) of processes, data stores, external entities, flows, and behavioral contracts. An LLM infers the source ADFD from bounded repository context, guided by static-analysis coverage checks. Dependency-aware chunking orders bounded process groups for target-language generation. Differences between the source ADFD and a statically recovered target ADFD then guide regeneration. We evaluate ADFD-Migrate on f2x50, a new benchmark of 50~Fortran repositories spanning 1.5k--1.6M lines of code and three complexity tiers, and assess the resulting ports along two dimensions: porting soundness, measured by source-oracle behavioral agreement, and porting completeness, measured by a composite migration outcome index. Against 382 curated Fortran-oracle probes, the generated Python passes 327 (85.6\%), with 40 repositories passing every attempted probe. ADFD-Migrate exposes all 382 planned behaviors as runnable targets, compared with 99 and 98 for direct and repository-context translation and 69 and 30 for the static-profile and dependency-chunking ablations. It also achieves a 93.1\% mean migration outcome index and a 17--59 percentage-point outcome-index advantage over direct translation on 47 repositories. These results suggest that an inspectable semantic bottleneck can improve the coverage and integration of repository-scale migration while enabling lower-cost generation for many repositories. --- ### Rebuild Dossier: Mechanically-Enforced Specs for Agentic App Rebuilds, and What Model-Tier Failures Reveal Authors: Parker Fawcett Published: 2026-08-22 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.23616v3 An AI agent's rebuild is only as good as the process that produced it. Prior work found that once a model is strong enough, a multi-agent rebuild pipeline loses to the simplest approach: giving the model the original code and one instruction (AgentModernize). We present rebuild-dossier, an open-source tool that locks an application's real interface - its exact inputs and outputs - before any code is written, then enforces one-test-at-a-time building through automated checks, not written instructions alone. Three results shape this evaluation, with differing amounts of evidence. First, in a small comparison, the compliant agent failed a held-back test while the rule-breaking agent passed everything - proof that a passing suite doesn't certify correctness when tests can be gamed. Second, we tested whether this beats simply giving the weaker model the source and one instruction: tied on a small app, but lost outright on a larger one where the automated check wasn't even running - pointing to the check mechanism, not interface-locking, which held up separately. Third, every claim here is checked at three levels - the agent's own report, an automated log, and the actual files produced - catching real errors, including a bug in our own logging code, that a single level would have missed. These risks reproduce on a different model and toolchain: a stronger model followed our process three times running, something the weaker model never managed. The tool is public, MIT licensed, and reproduces end to end against our own applications. --- ### Learning Reduced-Order Dynamics with Singularity via Latent-Augmented Neural Ordinary Differential Equations Authors: Xiaorui Wang, Yu Zhou, Wenjie Mei, Dongzhe Zheng, Yang Bai, Masaaki Nagahara Published: 2026-08-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.22142v1 This paper addresses the issue of self-intersecting trajectories (in phase space) in industrial reduced-order modeling and proposes the Latent-Augmented Neural Ordinary Differential Equations (LA-NODEs) framework. From the perspective of artificial intelligence, the proposed method augments conventional neural ordinary differential equations to enhance model expressiveness, enabling the representation of conflicting vector fields that may arise in reduced-order systems, thereby improving learning accuracy. Through theoretical analysis, the underlying mechanism of the framework is established, and a condition for determining the minimum required augmentation dimension is derived. From the perspective of engineering applications, the effectiveness of the proposed method is validated on the reduced-order system of two representative industrial models, namely an interior permanent magnet synchronous motor (IPMSM) drive and a distributed energy system (DES). Experimental results demonstrate that the proposed method can recover system features that are difficult to capture using conventional approaches and achieve superior performance in terms of prediction accuracy and modeling fidelity, thereby providing an effective approach for high-precision data-driven modeling of complex industrial systems. --- ### MEMONDEMAND: A Memory Management System for Large-Scale Enterprise Data Authors: Xinyuan Song, Bowen Zhu, Hasibul Haque, Liang Zhao Published: 2026-08-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.22141v1 Enterprise repositories are large, heteroge- neous, and continuously updated, making re- trieval difficult when efficient access, source- faithful evidence, and cross-query adaptation must be supported together. Enterprise mem- ory extends retrieval beyond the model con- text, but existing systems do not jointly address collection-specific hierarchy construction, low- cost routing, detailed evidence loading, and workload-aware memory updates at this scale. We introduce MEMONDEMAND, short for On- Demand Memory, a memory management sys- tem with three coordinated mechanisms: a dy- namic multi-level hierarchy that determines the abstraction structure and depth for each col- lection, dual memory at every hierarchy level that separates distilled routing from detailed evidence, and on-demand memory promotion that updates node priority under a bounded active-state budget. On EnterpriseRAG-Bench, MEMONDEMAND outperforms the strongest published LB#1 result at every evaluated scale from 10M tokens through the complete 618M- token collection, with gains of 12.23% at 10M and 4.66% at 618M. Results on FinanceBench, HotpotQA, and FRAMES further show strong performance across financial, multi-hop, and fact-retrieval settings. Together, these results establish MEMONDEMAND as an accurate, ef- ficient, and scalable memory solution for very large enterprise repositories across data scales, domains, and evidence requirements. Our code is available at https://github.com/ xfab-xinyuansong/MemOnDemand.git. --- ### Lexical Perturbations Disrupt LLM Reasoning: An Empirical Study of Attention Diversion Authors: Jiaqian Zhu, Yang Zhang, Junhua Ding, Xiaowei Yu Published: 2026-08-22 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.22140v1 Large Language Models (LLMs) achieve strong reasoning performance, but their robustness to realistic lexical corruption remains poorly understood. We evaluate four open-weight instruction-tuned models and frontier models across four reasoning benchmarks under keyboard noise, character swaps, and filler insertion. Character-level perturbations substantially degrade accuracy, especially on multi-step reasoning tasks, while filler insertion has little effect. We trace this asymmetry to Attention Diversion: lexical corruption fragments subword tokenization, and the resulting fragments attract disproportionate attention mass, concentrated in middle and final transformer layers. Length-matched controls confirm that fragmentation, not prompt length, drives the loss. A factorial intervention then shows why the damage is hard to undo: fragmentation corrupts token content and attention allocation together, and the two are coupled. Restoring clean attention while the content remains corrupted is actively harmful, restoring content alone is insufficient, and only restoring both recovers a substantial share of the gap. This coupling explains why inference-time strategies, including chain-of-thought prompting, spell-checking, self-repair, and stronger repair models, fail to consistently recover performance: each addresses one channel at a time. Code and data are available at https://github.com/Jiaqian-Janelle/Attention-Diversion --- ### Measuring Stability and Failure Behavior in Language Models Under Structured Perturbations Authors: Samira Golsefid Published: 2026-08-22 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.22138v1 Language models are usually judged by a single accuracy score, which does not reveal how their performance degrades as inputs are perturbed. We present a graded, multi-family, failure-aware framework for stress-testing reasoning models. It perturbs each problem along a multi-level severity ladder across seven families: six that preserve the answer, paraphrase, input noise, formatting, irrelevant context, context load, and conflicting instructions, and a Knowledge Boundary family that removes answerability so that refusal becomes the correct response. Every test is validity-gated and labeled by its measured severity, and each model is summarized by per-level Accuracy, a magnitude-weighted Stability, and a per-family Collapse Point defined relative to the model's own baseline. Instantiated on the same 100 seed problems used by GSM-Symbolic, expanded into 4,473 gated tests and run on four models spanning capability tiers, the framework exposes structure that an aggregate score hides: the level at which a model fails is family-specific rather than global, and two stressors expose consistent weaknesses across all models: conflicting instructions and questions built on an impossible premise. Recognition of unanswerability is otherwise uneven, reliable on missing information and fabricated evidence but weak on impossible premises. These failure points are invisible to standard accuracy reporting. --- ### MegaMem: A Retrieval Solution for Ultra-Large Context Windows Authors: Xinyuan Song, Bowen Zhu, Hasibul Haque, Liang Zhao Published: 2026-08-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.22137v1 Modern language models and agents increasingly require persistent memory for complete codebases, long interaction histories, and heterogeneous enterprise records. The key challenge is to keep hundreds of millions of tokens searchable while passing only bounded source evidence to the answer model. We introduce MegaMem, a source-resolved dual-view retrieval system that separates semantic access from generation evidence. Distilled records and detailed evidence are searched with original and transformed queries; every distilled hit resolves to an immutable source ID before reciprocal-rank fusion, deduplication, and cross-encoder reranking; and only the highest-ranked detailed evidence within a fixed budget supports generation. Post-answer attribution then identifies which loaded sources support the fixed answer. We evaluate MegaMem on EnterpriseRAG-Bench, which contains more than 500,000 heterogeneous enterprise documents and approximately 650M tokens. MegaMem improves Overall from 68.22 to 82.26 and reaches 86.50 Correctness. These results show that MegaMem supports ultra-large persistent memory while preserving strong answer accuracy under a bounded generation context. By separating searchable memory scale from answer-context size, MegaMem provides a practical path toward accurate retrieval over memories ranging from hundreds of millions to one billion tokens. Our code is available at https://github.com/ xfab-xinyuansong/MegaMem.git. --- ### SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning Authors: Zhaohan Meng, Zaiqiao Meng, Siwei Liu, Hao Xu, Ke Yuan, Iadh Ounis Published: 2026-08-22 Categories: cs.CL, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2608.22132v1 Biomedical multi-hop question answering (QA) requires models to connect evidence across intermediate entities such as diseases, drugs, proteins, and phenotypes. Existing agents typically rely on static retrieval workflows or coarse-grained prompt rewriting, which can lead to instruction drift when reasoning procedures need to be updated. We propose SSE-Bio, a structured self-evolving agent with an agentic retrieval policy for multi-hop biomedical reasoning. Instead of globally rewriting agent instructions, SSE-Bio maintains a structured state, selectively retrieves knowledge triplets and prior templates through a trainable proxy policy, and improves its reasoning memory through fine-grained template editing. To optimise retrieval decisions, we introduce a proxy-training strategy based on group relative policy optimization, where the proxy is improved through decision-contrastive groups over alternative retrieval choices. Experiments on three biomedical multi-hop QA benchmarks show that SSE-Bio consistently outperforms existing baselines, achieving an improvement of 6.56 absolute points over the strongest self-evolving baseline on BioHopR. --- ### TRACE: Artifact-Robust Statistical Shape Modeling from Imperfect Surface Scans - A Case Study in Craniosynostosis 3D Photography Authors: Sanjay Bhandari, Nawazish Khan, Alzbeta Novotna, Tiffany Jeong, Loretta Bowman, Michael Hernandez, Tobi Somorin, Viraj Govani, Jesse Goldstein, Shireen Elhabian Published: 2026-08-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.22131v1 Craniosynostosis severity analysis increasingly relies on statistical shape models (SSMs) to quantify cranial morphology, but most existing workflows depend on computed tomography or heavily curated three-dimensional (3D) photographs. Raw clinical 3D photographs provide a radiation-free and repeatable alternative, yet often contain shoulders, hands, hair, clothing, scanner noise, and incomplete boundaries that corrupt correspondences. We introduce the Template-constrained Robust Artifact-aware Correspondence Estimation (TRACE) framework, an unsupervised method for constructing SSMs directly from artifact-contaminated clinical 3D head photographs. TRACE predicts sparse anatomically corresponding head-surface control points from the raw point cloud, refines them through a coarse-to-fine Surface-Aware Deformation cascade, and uses thin-plate spline warping to deform a clean template mesh into a subject-specific head reconstruction. This template-constrained formulation keeps dense correspondences on clinically relevant head anatomy while suppressing non-head artifacts. The correspondence module is decoupled from the point-cloud encoder, enabling the same deformation pipeline to be paired with different backbones, including PointNet, DGCNN, and Point Transformer V3. Across all backbones, TRACE substantially improves surface sampling, topology preservation, and shape-model quality over prior SSM methods, providing a scalable foundation for photograph-based craniosynostosis shape analysis and a framework that may extend to other artifact-contaminated surface scans when an appropriate clean template is available. --- ### PropUQ-MAS: Propagation-Aware Uncertainty Quantification for LLM Multi-Agent Systems Authors: Yaokun Liu, Yifan Liu, Daniel Yue Zhang, Ruichen Yao, Zelin Li, Dong Wang Published: 2026-08-22 Categories: cs.MA, cs.CL arXiv: https://arxiv.org/abs/2608.22130v3 LLM-based multi-agent systems (MAS) solve complex tasks through communication among role-specialized agents. However, inter-agent dependencies introduce reliability risks beyond isolated agent failures. For instance, errors in intermediate messages could be inherited and amplified by downstream agents. Existing uncertainty quantification (UQ) methods mainly target isolated responses or single-agent reasoning, and therefore fail to capture uncertainty propagation in MAS. To this end, we propose PropUQ-MAS, an error propagation-aware UQ framework that represents MAS execution as a communication-structured graph and estimates each step's reliability by combining local uncertainty with uncertainty inherited from upstream messages. Extensive experiments demonstrate that PropUQ-MAS consistently improves UQ in MAS, with average relative gains of +6.10% in AUROC and +47.58% in PRR. --- ### Blockwise Stabilized Adaptive Cubic Regularization with Subsolvers via Recurrence Authors: Rodion Podorozhny Published: 2026-08-22 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2608.22129v2 Cubic regularized Newton methods have the optimal $\mathcal{O}(ε^{-3/2})$ global rate, but a dense subproblem solve limits the feasible block size. Scalable Cubic Newton variants replace the true block curvature with a diagonal, low-rank, Kronecker-factored, or sketched surrogate and, most often, give up the exact cubic step. We introduce a blockwise optimizer that minimizes an independent cubic model per parameter tensor over the true block Hessian, under a per-block adaptive cubic constant and a monotone guard on the full loss. Arbitrarily large tensors are handled matrix-free in a Lanczos-built Krylov subspace, where we prove that the step minimizes the cubic model. The theory also supplies the $\mathcal{O}(ε^{-3/2})$ iteration complexity bound, a second-order guarantee, and monotone per-block descent. Four variants of this outer scheme are evaluated against the original adaptive regularization with cubics (ARC) optimizer, some other recent cubic Newton variants, Adam, SOAP, and L-BFGS. On a 91.4M-parameter implicit neural representation (INR), the variants introduced in this work are the only evaluated here cubic Newton methods whose steps stay exact on every block. Run to full convergence on FINER 2D image fitting, one of the ARC variants introduced here, ARC-$\varphi_1$, reaches 133.5 dB peak signal-to-noise ratio, while tuned Adam plateaus at 78.2 dB after about 70 minutes. In that time ARC-$\varphi_1$ reaches 95.6 dB. --- ### Task-Driven 3D Printability Assistance via Geometry- and Knowledge-Grounded LLM Reasoning Authors: Zhaoda Du, Qiaojie Zheng, Xiaoli Zhang Published: 2026-08-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.22128v1 Printability assessment in additive manufacturing is typically conducted at the geometry level before printing to determine whether a computer-aided design (CAD) model or stereolithography (STL) file can be successfully fabricated. Task suitability, in contrast, is usually evaluated after printing to determine whether the fabricated part satisfies the requirements of its intended use. As a result, for non-expert users to print functional parts, unsuitable material or process choices may only be identified after fabrication, leading to repeated printing, material waste, and user frustration. To address this challenge, this paper leverages the reasoning and language-understanding capabilities of large language models (LLMs), while grounding the reasoning with geometry evidence and structured material/printer knowledge to generate reliable pre-print recommendations. Given a stereolithography (STL) model and a natural-language task description, the framework generates a structured recommendation covering printability, material choice, process parameters, design guidance, risks, and explanations. We evaluate the framework on focused STL benchmark scenarios with novice-style task descriptions. The proposed method achieves 75.0% printability over 96 physical validation trials, with 88.9% task suitability among successfully printed samples. It also improves Gemini 2.5 Flash-Lite material-selection accuracy from 37.5% under pure LLM to 90.0%. Expert evaluation further shows improved report quality, while post-print feedback improves recommendations on selected problematic cases. These results suggest that user task intent, geometry evidence, and structured material knowledge are all important for reliable task-driven printability assistance. --- ### Who Should Teach? Confidence-Aware Dual-Teacher Learning for Few-Shot Node Classification on Text-Attributed Graphs Authors: Hojin Kim, Sujin Yoon, Sungsu Lim, Dongwon Lee, David Yoon Suk Kang Published: 2026-08-22 Categories: cs.LG, cs.SI arXiv: https://arxiv.org/abs/2608.22127v2 Text-Attributed Graphs (TAGs) integrate graph structures and node-associated textual attributes, and recent studies have increasingly leveraged Large Language Models (LLMs) to improve TAG learning in few-shot settings. However, existing approaches typically utilize LLM-derived information uniformly across all nodes, despite substantial variations in its reliability, while also incurring considerable monetary costs. We argue that the most appropriate source of supervision may differ across nodes, as Graph Neural Networks (GNNs) and LLMs exhibit complementary strengths in exploiting structural and semantic information, respectively. To this end, we propose CoTeach, a Confidence-aware dual-teacher learning framework that dynamically selects the more reliable teacher for each node. Experimental results demonstrate that CoTeach consistently improves few-shot node classification performance while reducing unnecessary LLM utilization and associated monetary costs. --- ### Decoupled Physical Modeling and Execution for Physics Reasoning Authors: Ye Zhang, Xuehang Guo, Rui Pan, Pengfei Yu, Denghui Zhang, Manling Li, Qingyun Wang Published: 2026-08-22 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.22126v2 Physics reasoning requires constructing a consistent model of the underlying physical system rather than relying solely on symbolic or formula-based manipulation. Although large language models have shown strong ability in solving math and coding problems, they still struggle with physics problems, as these problems entangle the physical modeling process with mathematical calculations. Humans approach physics by first building a representation of the system before performing calculations. Inspired by this, we introduce a unified framework that distills intermediate representations that explicitly encode the physical modeling process and adopt a two-stage post-training strategy, where supervised fine-tuning establishes structured modeling, and reinforcement learning with rubric-based feedback improves the quality of the modeling process. Experiments on multiple multimodal physics benchmarks show that our approach generally improves physical reasoning performance across different models and datasets. Across PhysReason, PhyX, and SeePhys, physical modeling outperforms GRPO by ~3% on average. showing that explicit physical modeling is an effective strategy for improving physics reasoning in small VLMs. --- ### LLM assisted writing deserves empirical evaluation Authors: Xuan Zhong Feng, Yi Lin, Yiye Zhang, Chunhua Weng, Yifan Peng Published: 2026-08-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.22124v1 LLM-assisted writing is often treated as a detection problem, as it raises questions about clarity, integrity, equity, and evaluation. An analysis of 69,209 Health Informatics papers links it to more focused presentation, broader citation practices, and more globally distributed authorship. These patterns do not prove better science, but they support evaluating manuscripts by scholarly quality and accountability rather than by tool use. --- ### The Price of Decentralization in Top-$K$ Arm Identification Authors: Larissa Xu, Jasmine Nguyen, William Chang Published: 2026-08-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.22120v1 Cooperative teams often need to agree on the best few options rather than simply accumulate reward, and they must do so while each member sees only a fragment of the team's collective experience. We study this as top-$K$ joint-arm identification in multi-agent multi-armed bandits: at every round $M$ agents simultaneously choose individual actions that compose a joint arm, and the team must ultimately return the $K$ joint arms of highest mean reward. The difficulty is that an agent may not observe the actions of others, their rewards, or either. We treat three observability regimes---(A) shared rewards with hidden actions, (B) observed actions with private rewards, and (C) full asymmetry---and design communication-free elimination algorithms (UCB-Intervals) that reconstruct implicit coordination from whatever signal each regime leaves intact: a shared arm ordering in (A), observable deviations in (B), and enlarged confidence radii under (C). We give matching analyses in both the fixed-budget and fixed-confidence objectives, then fold all three regimes into a single meta-guarantee indexed by a multiplicity $c$ and a consensus factor $ρ$. Our central result is quantitative rather than merely algorithmic: change-of-measure lower bounds show that shared-reward identification is optimal up to one universal logarithmic factor, and that the entire statistical price of removing communication is a multiplicative $ρ^2$ in sample complexity---a fixed $4\times$ penalty under full asymmetry. The resulting stopping time scales as $O\!\left(\sum_{\mathbf{a}} \frac{\log(A^M/δ)}{Δ_{\mathbf{a}}^2}\right)$ and the fixed-budget error as $\exp(-Θ(T/H_1))$, with the dependence on the joint-action count $A^M$ shown to be unavoidable. --- ### RAG Collapse: LLM Responses Collapse When Retrieved Documents Are Self-Authored Authors: Gregory Druck, Ethan Smith Published: 2026-08-22 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2608.22118v1 LLM responses are based on the internet (via training or RAG), and AI is now used to generate a significant amount of content online (Paredes et al., 2026), creating the potential for a self-reinforcing feedback loop. Prior work has shown that when LLMs are recursively trained on their own output, they experience model collapse (Shumailov et al., 2024): responses become less diverse, and eventually no longer resemble the original training data. In this paper, we show that a similar collapse occurs if LLM-based AI systems retrieve references they authored using a search tool. We call this RAG collapse. We conduct extensive experiments with three types of simulations of AI systems retrieving references they generated, using three model families, and 1,019 information-seeking prompts, totaling 1,528 simulations and over one million LLM API calls, and find that 79.6% (1,216/1,528) of simulations end in collapse. Surprisingly, even a single self-authored reference can trigger collapse because the LLM disproportionately cites its own content. This self-bias persists even after controlling for reference quality. --- ### TANGO: Token-Aggregated Nonlinear Gating Operators for Natural and Formal Language Modeling Authors: Joshua Nunley Published: 2026-08-22 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.22117v1 A standard Transformer block separates cross-token interaction in self-attention from a nonlinear feed-forward network applied independently at each position. We introduce the TANGO model (Token-Aggregated Nonlinear Gating Operators), which replaces these two sublayers with one cross-token gated residual update. Each source token produces a SwiGLU gate vector. Query-key similarities determine a weighted average of source gates for each destination, and the resulting gate rescales projected destination features. TANGO assigns a separate weight to every causally visible source and is quadratic in sequence length. The WANGO model (Windowed Aggregation of Nonlinear Gating Operators) retains the same unnormalized scores within a recent window and uses positive feature-map prefix statistics for older sources, giving linear sequence-length complexity for fixed window and feature dimensions. We compare TANGO and WANGO with Recurrent and Untied Transformer++, full-attention GAU, and FLASH. All models have approximately 44.3M nonembedding parameters and are trained in three matched runs. TANGO, WANGO, and Recurrent Transformer++ apply one shared block four times; the other architectures use four independent blocks. TANGO obtains the lowest mean validation negative log-likelihood on FineWeb-Edu, Lean, and DeepMind Mathematics, although it has the largest analytical forward-pass operation count. WANGO obtains the lowest mean FineWeb-Edu NLL among the architectures with computation linear in sequence length and outperforms Recurrent Transformer++ at nearly the same analytical forward-pass multiply-accumulate count. --- ### Vehicle speed dataset for the major European road network derived from Sentinel-2 imagery, 2022-2026 Authors: Maciej Adamiak, Sascha Fendrich, Julian Psotta, Alexander Zipf Published: 2026-08-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.22116v1 The dataset provides individual vehicle speed observations on European E-roads: motorways, trunk roads, primary and secondary roads, as tagged in OpenStreetMap as e-road, for the years 2022-2026. Speeds are derived from Copernicus Sentinel-2 Level-2A satellite optical imagery using a processing pipeline that exploits the short, well-characterized acquisition delays between the blue (B02_10m), green (B03_10m), and red bands (B04_10m) of the Sentinel-2 push-broom instrument. A moving vehicle appears at slightly displaced positions in the three bands, forming a moving echo. The detected displaced intensity peaks are linked into per-vehicle trajectories through a prediction-and-matching procedure. The resulting displacements are converted into ground speeds using publicly accessible inter-band time delays. Each record contains the trajectory geometry, per-channel displacements and headings, internal quality indicators, the estimated speed, the acquisition timestamp, and the source Sentinel-2 product identifier. The dataset is distributed as GeoPackage files, with one record per detected vehicle, and can support studies of traffic patterns, speed behavior, transport modeling, and the calibration of road network attributes at a continental scale. --- ### CST: Collaborative Selective Transmission for Communication-Efficient Multimodal Edge Inference Authors: Hai Chi, Junrui Zhang, Rui Ning, Chonggang Wang, Robert Gazda, Huanrui Yang, Hongyi Wu Published: 2026-08-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.22115v1 Collaborative multimodal inference improves edge perception by combining observations from distributed sensing devices, but transmitting high-dimensional helper representations incurs substantial communication overhead and can lead to high end-to-end latency. Existing communication-efficient methods reduce payloads through compression, semantic coding, or feature selection, yet typically optimize compactness or task relevance without explicitly accounting for information already represented at the main device. Consequently, task-relevant but redundant helper features may still consume bandwidth. We present Collaborative Selective Transmission (CST), a main-directed query--response framework that retrieves only helper information complementary to the current main representation. Inspired by Partial Information Decomposition and the Multiview Redundancy Assumption, CST learns sample-adaptive, helper-specific sparse retrieval supports while discouraging retrieval of semantics already covered by the main device or duplicated across helpers. During inference, the main device transmits only support indices, and each helper returns the corresponding latent values, avoiding dense helper-feature exchange. Across three real-world multimodal sensing benchmarks, CST transmits no more than 14.18% of helper feature values while achieving best or near-best task performance among the evaluated methods. Experiments on a five-node NVIDIA Jetson Orin Nano testbed across 5--100 Mbps demonstrate up to a $4.27\times$ speedup over Transmit-All in end-to-end inference, confirming practical end-to-end latency reductions. --- ### Symbolic Neural ODEs: Learning interpretable models from time-series data Authors: Nibodh Boddupalli, Jeff Moehlis Published: 2026-08-22 Categories: cs.LG, eess.SY, math.DS, stat.ML arXiv: https://arxiv.org/abs/2608.22112v1 We present a machine learning framework for identifying sparse, interpretable models of dynamical systems directly from time-series data. Our approach parameterizes the underlying vector field using a neural architecture and trains it by minimizing a multi-step prediction loss over a finite horizon. To ensure numerical tractability, we optimize a mean absolute error objective averaged across prediction steps, and progressively increase the horizon during training. A key feature of this formulation is that it enforces consistency under repeated composition of the learned dynamics. As a result, the identified models exhibit significantly improved stability compared with approaches based on one-step regression of the vector field. When combined with sparsity-promoting regularization, this leads to parsimonious models that generalize beyond the training data. We demonstrate accurate recovery of systems exhibiting a wide range of behaviors, including stable and unstable fixed points, periodic orbits, and chaotic attractors. For chaotic systems, while long-term trajectory prediction is inherently limited by sensitivity to initial conditions, we show that multi-step training yields models with accurate short-term dynamics and strong agreement in long-time statistical properties, including mean, variance, and Lyapunov exponents. Moreover, we establish theoretical bounds linking trajectory error to statistical accuracy, providing a step toward a principled explanation for this behavior. --- ### How Weight Encoding Affects Language Model Placement and Performance on the Apple Neural Engine Authors: Shahir M A Published: 2026-08-22 Categories: cs.LG, cs.AR, cs.PF arXiv: https://arxiv.org/abs/2608.22110v2 Weight compression can alter accelerator placement as well as memory traffic, complicating the interpretation of inference speedups. We investigate this interaction on the Apple Neural Engine through the public Core ML deployment path. Five independently trained language-model checkpoints span two architectures and dense fp16, int8, and ternary weights encoded with two-bit lookup tables. We combine compiler device plans, synchronized memory-controller measurements, and compute-unit exclusion controls for a fixed single-token forward workload. On an M1, the smaller fp16 export executes on the CPU despite permitting ANE execution, whereas its compressed counterparts exhibit ANE activity. The int8 export reduces warm forward latency by a factor of 1.9. The larger fp16 export also uses the ANE, indicating that dense encoding alone does not determine placement. Separate M3 energy measurements support the same direction of change. These results establish encoding-dependent placement in the measured deployment stack and show that compression comparisons require joint measurement of backend selection, latency, and traffic. --- ### Development and Feasibility Evaluation of an Edge AI as Medical Device System for Breast Cancer Multidisciplinary Team Meetings Authors: Aarzoo Dhiman, Farzana Haque, Iqtedar Muazzam, Kartikae Grover, Lydia Brian Smith, William Stephen Jones Published: 2026-08-22 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.22108v2 Breast Cancer Multidisciplinary Team (MDT) meetings manage increasingly complex cases under considerable time pressure, and documentation requirements can reduce clinical efficiency and decision quality. Existing AI based MDT workflows rely on cloud-based processing, limiting their use because patient discussions contain identifiable information. We developed a fully on-device AI pipeline using open-source Automatic Speech Recognition (ASR) and Large Language Models (LLMs) that transcribes breast cancer MDT discussions, structures clinical information, and generates treatment recommendations using retrieval-augmented generation (RAG) grounded in National Institute for Health and Care Excellence (NICE) guidance. The pipeline runs on a single NVIDIA Jetson AGX Orin, ensuring that patient audio, transcripts, and outputs remain within institutional infrastructure. Evaluation included two recorded simulated MDT discussions, ten clinically validated synthetic discussions, and 1,270 acoustically augmented recordings. Optimisation of Whisper large-v3 reduced word error rate by 20.7% and 24.4% on the recorded discussions and achieved performance within 0.58% WER and 1.58% word information lost of a commercial clinical ASR benchmark on augmented audio. MedGemma-RAG identified 2.3 times more MDT-concordant interventions than a proprietary cloud comparator (p = 0.020), with no significant difference in overall accuracy. Stakeholders identified automated documentation, treatment recommendation support, and case triage as the most credible near-term applications while highlighting workflow integration, governance, and clinician trust as key implementation challenges. These findings demonstrate the feasibility of privacy-preserving, fully on-device AI for MDT documentation and guideline-informed decision support, providing a foundation for prospective clinical evaluation. --- ### Hack-Verifiable Terminal Bench: Evaluating Reward Hacking in Terminal Tasks Authors: Amit Roth, Ivan Bercovich, Yonathan Efroni Published: 2026-08-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.22103v1 As agents grow more capable and autonomous, their tendency to reward hack, satisfying a task's checks while violating its intent, becomes an increasingly important failure mode. Measuring reward hacking is itself challenging, as detection typically relies on human inspection or LLM judges, both of which can be unreliable. The hack-verifiable environments (HVE) methodology addresses this challenge by embedding detectable hacks into tasks, allowing reward hacks to be identified automatically and reliably. In this work, we adapt HVE to Terminal Bench, a leading benchmark of real-world terminal and coding tasks, and introduce Hack-Verifiable Terminal Bench (HVTB). Using HVTB, we measure reward-hacking rates across frontier models and study whether prompts with varying amounts of information on the hack can mitigate this behavior. This lets us test whether prompting can prevent not only known reward-hacking strategies, but also 'unknown unknown' exploits that the prompt does not anticipate. We release all environments and agent traces at https://majoroth.github.io/hack-verifiable-environments/hvtb --- ### Learning Implicit Constitutive Laws for Dynamic 3D Gaussian Splatting from Monocular Videos Authors: Xiaoyang Liu, Kai Han Published: 2026-08-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.22102v1 We present GCA (Gaussian Constitutive Alignment), a framework for learning implicit constitutive laws from monocular dynamic video of deformable objects represented by 3D Gaussians. Given a static multi-view scan for geometric initialization, our method learns intrinsic physical dynamics solely from a single fixed-viewpoint video of the moving object. Existing implicit methods often suffer from local minima under noisy supervision and lack physical interpretability, while explicit approaches rely on predefined constitutive equations, limiting generalizability and becoming unstable in monocular settings. To address these challenges, our framework unifies LoRA-based adaptation with two key alignment modules. First, we propose Rank-based Depth-Geometric Anchors (RDGA) to establish robust geometric constraints from monocular dynamic observations via scale-invariant rank-based depth alignment, reducing the reliance on unreliable pixel-level color supervision. Second, a Constitutive Prior Regularizer (CPR) integrates classical constitutive models as soft differentiable priors, regularizing the optimization while preserving the flexibility of implicit modeling---even when the actual material is absent from the hypotheses. Extensive experiments on synthetic, real-to-sim, and real-world datasets demonstrate that GCA outperforms existing methods, achieving 48% lower Chamfer Distance than the strongest baseline on synthetic benchmarks while remaining robust under monocular supervision. --- ### Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents Authors: Sameep Chattopadhyay, Alexander Erdmann, Mari Ostendorf Published: 2026-08-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.22101v1 Modern voice-agent systems rely on streaming speech recognition models that operate under stringent latency constraints. This study shows that, due to the limited memory constraints of real-time processing, these systems are adversely impacted by conversational phenomena such as long silences and backchannels. While many agentic pipelines mitigate this by resetting state at each turn, this approach discards vital context and impairs performance at turn onsets. We propose two state-management strategies that preserve cross-utterance context to reduce onset errors. In experiments with two state-of-the-art streaming models on two spoken dialogue benchmarks, our best method yields an average of 15-21% relative WER reduction at utterance onsets. --- ### Pretreatment DCE-MRI Resolves Response Quality Within Pathologic Endpoints in Neoadjuvant Breast Cancer Authors: Dattatreya Kantha, Murray H. Loew Published: 2026-08-22 Categories: eess.IV, cs.CV, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2608.22097v1 Pathologic complete response (pCR) is a strong neoadjuvant endpoint, yet 5-15% of complete responders recur and clinical/genomic variables do not reliably identify them. We tested whether pretreatment dynamic contrast-enhanced MRI entropy - intratumoral enhancement heterogeneity - resolves response quality hidden within pCR and residual cancer burden (RCB). Across four cohorts (1,200 patients), a prespecified entropy threshold defined favorable and adverse structural states. Crossing structure with pathology yielded a four-tier framework spanning 4.1-fold recurrence in I-SPY1 and 7.7-fold at response extremes. In I-SPY2, 55 of 219 complete responders (25.1%) were structurally adverse, pretreatment. In an external HER2-positive responder synthesis (I-SPY1 pathology-confirmed pCR plus UCSF best-response proxy; n = 33, 10 events), adverse structure was associated with higher recurrence risk (HR = 2.87, 95% CI 1.38-5.96) capturing 7 of 10 recurrences, enriching rather than determining risk. In a HER2-positive RCB-0 subset, recurrence was 12.5% with favorable and 80.0% with adverse structure; Firth Cox regression preserved the association (HR = 8.13, 95% CI 1.71-49.21; n = 21, 6 events). In Duke (n = 908; 76 events), favorable structure remained independently associated with lower distant-recurrence risk (adjusted HR = 0.61, 95% CI 0.41-0.91). RNA linked favorable structure to a directionally reproduced immune-architecture program among non-overlapping patients within ISPY2; EMT-pathway enrichment was favorable-side, while the adverse tier contained a broadly immune-depleted substate. Yet full-cohort RNA models weakly discriminated structural state and did not recover continuous entropy. Pretreatment MRI therefore does not replace pCR or RCB; it reveals response-quality differences that these endpoints compress and identifies a recurrence-enriched group for prospective validation. --- ### Three-Phase Scribble-Adaptive Curriculum Learning for autoPETV Grand Challenge Authors: Libo Zhang, Yue Ning Published: 2026-08-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.22096v2 This report describes Libo Zhang's algorithmic solution to autoPETV Grand Challenge on interactive lesion segmentation in whole-body PET/CT. Interaction is encoded as two additional input channels that rasterize the accumulated foreground and background scribbles, and a residual-encoder U-Net of about 140 million parameters is trained with a three-phase curriculum over 4000 epochs: the network first learns fully automatic segmentation with silent interaction channels, then observes ground-truth-derived scribbles under randomly sampled visibility modes, and finally adapts to its own mistakes through online simulation of up to five error-driven correction steps. Training draws on 1811 autoPET and DeepPSMA studies, and the submission ensembles the best and final checkpoints of five folds by logit averaging. In interactive five-fold cross-validation with six interaction steps, the final checkpoints reach a mean AUC-Dice of 3.836 and a mean AUC-DMM of 3.869, improving monotonically in every fold, with roughly half of the total gain delivered by the first corrective scribble. Our code and trained model checkpoints are available on https://github.com/Libo1023/autoPETV-Curriculum. --- ### Counterfactual Quotient Models: Learning What Actions Change, Not What the World Does Authors: Junlin Chen, Ruijie Wang, Jianxin Li Published: 2026-08-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.22092v1 Reinforcement-learning models commonly predict complete future states, observations, or feature occupancies, even though action selection depends only on differences between the consequences of candidate actions. As a result, these models may devote substantial statistical and representational capacity to high-dimensional phenomena that evolve independently of the agent's current choice. We introduce the Counterfactual Quotient Model, which treats action-conditioned futures as equivalent when they differ only by a component shared across actions. Its canonical centered representation removes this common component while preserving every pairwise action comparison expressible by the modeled reward family. The implemented model learns these action-dependent effects directly from synchronized counterfactual rollouts, so shared stochastic dynamics cancel before function approximation rather than after complete futures have been predicted. We establish the decision sufficiency, identifiability, common-mode invariance, approximation behavior, and regret properties of the resulting representation. Controlled experiments in physics-based environments provide initial evidence for these properties: direct effect learning suppresses action-independent variation, supports previously unseen reward queries, and improves action ranking relative to models trained to predict absolute futures. --- ### Semantic Reasoning Denoising: Correcting Language Model Reasoning with Semantic Operators Authors: Yujiao Yang Published: 2026-08-22 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.22090v1 Large language models can produce fluent reasoning traces whose local semantic errors propagate to an incorrect conclusion, while unconstrained self-correction may preserve, amplify, or introduce errors. Existing diffusion language models provide iterative refinement, but usually define noise as token masking or replacement rather than as errors in the reasoning process. We present Semantic Reasoning Denoising (SRD), an operatorized Markov denoising method for natural-language reasoning trajectories. SRD represents semantic noise with executable error operators that describe the error type, its location, and the corrupted and repaired propositions. Composing these operators constructs progressively noisier states. During training, the model learns to identify the semantic noise active in the current trajectory and to reconstruct the paired adjacent lower-noise state. During inference, noise-level-aware denoising repeatedly predicts an inverse operator and checks whether it is applicable, so each executed update makes a localized move toward a stable trajectory. Across six in-domain benchmarks spanning mathematics, code, knowledge, and commonsense, SRD improves the strongest same backbone baseline by 3.2 points on average. On seven cross-dataset transfer targets, it remains competitive with Llama-3-8B-Instruct and improves the strongest Qwen3-8B baseline average by 2.9 points. Analyses of noise sources, objectives, and denoising depth further show that structured semantic-noise prediction and iterative operator execution are central to the improvement. --- ### On Predicting Vulnerability Severity Using In-Context Learning: An Industrial Case Study Authors: Daniel Rodriguez-Cardenas, David Nader Palacio, Anna Schmedding, Yiyang Lu, Aadil Mallick, Bill Hudson, Chris Gourley, Michael Roytman, Chris Shenefiel, Evgenia Smirni, Denys Poshyvanyk Published: 2026-08-22 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.22089v1 Modern software systems require earlier and more scalable vulnerability severity assessment to reduce exposure to high-impact security flaws. Security analysts typically assign CVSS scores, but this manual triage does not scale with the growth of disclosed vulnerabilities and often depends on cloud LLM services that raise confidentiality concerns. This paper presents an industrial case study on predicting CVSS v3.1 scores directly from vulnerable C/C++ snippets using in-context learning with locally deployable, open-source LLMs. We compare proprietary data with the Big-Vul dataset, showing sufficiently aligned CVSS distributions to justify Big-Vul as a proxy for industrial data when constructing prompt-based testbeds. We then vary in-context configurations and model parameters, evaluating CodeLlama2-7B, CodeLlama2-13B, Mistral-7B, gpt-oss, and GPT4o-mini using mean squared error (MSE) and feasibility metrics. Our results show that medium-sized open-source code models, particularly CodeLlama2-7B, can approximate the best cloud performance for CVSS regression when guided by lightweight, output-constraining prompts, offering a practical, privacy-preserving building block for severity triage in industrial settings. --- ### SweepLSD: A One-Pass, O(width)-Memory Line Segment Detector with an Integer-Only Streaming Core and a Real-Time FPGA Realization Authors: Yoshiyasu Shimizu Published: 2026-08-22 Categories: eess.IV, cs.AR, cs.CV arXiv: https://arxiv.org/abs/2608.22086v1 We present SweepLSD, a line segment detector that reads the image exactly once and emits each segment within a few rows of its last pixel passing the scan line. Every stage, including connected-component labeling and the final line test, processes the image as a row stream: intermediate memory is O(width) rather than O(pixels), and the per-pixel core is integer-only. We give the first complete description of the algorithm, designed in the author's 2014 master's thesis but never published, together with an open-source C++17 implementation and an FPGA realization -- held bit-exact against the software in its hardware configuration -- detecting segments in live 1080p30 video on 2009-era silicon without frame buffer or external memory. On structure-rich public 4K photographs downscaled to Full-HD, one CPU thread detects segments in ~11 ms -- 4.6x/5.2x/25x faster than the original authors' implementations of ELSED, EDLines, and LSD -- with the tightest frame-time distribution and the best per-segment direction accuracy of the four detectors, and curve rejection by design, while trailing ELSED in F-score on synthetic ground truth. A Manhattan-frame vanishing-point study on York Urban and NYU-VP scores every detector under a selection/evaluation-separated best-estimator-per-detector protocol, under which SweepLSD leads on NYU-VP by ~0.3 degrees and trails by 0.1 degrees on York Urban, with the fastest end-to-end pipeline of the four detectors on both. A single-frame camera-attitude application, evaluated on synthetic scenes with exact ground truth and on EuRoC and TUM-VI, matches the baselines' accuracy at a fraction of their memory, and drives a 4K horizon lock to 0.06 degrees median attitude error at 32 ms median per frame. --- ### Dissecting Neuro-Symbolic Quality Assurance for Synthetic Oncology Data Generation Authors: Laxmigayathri Challa, Yuhan Zhou, Ana Cleveland, Haihua Chen Published: 2026-08-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.22085v1 Synthetic clinical data generation with large language models addresses the scarcity that limits cancer staging research, but oncology hallucinations are categorically harmful: one clinically impossible staging assignment contaminates every downstream model trained on it. Neuro-symbolic pipelines validate during generation, yet the contribution of individual quality-assurance components remains unclear. We report three controlled studies isolating gate necessity, constraint attribution, and retrieval conditionality, holding generation protocol, diversity thresholds, and fine-tuning hyperparameters constant across adapter conditions. The symbolic gate enforces schema completeness, ontology coverage against the Systematized Nomenclature of Medicine, and staging-logic consistency under American Joint Committee on Cancer eighth-edition rules. Ungated, 29.9% of records contain schema failures and 20.1% contain clinically invalid staging. Schema validation is the load-bearing filter: within the fully gated corpus it rejects 148 of 512 records, ontology grounding a further 24, and staging-logic validation none---the only generator producing logic violations is already excluded on schema, making clinical-logic validation a generator-conditional safeguard rather than the dominant filter. Retrieval augmentation is strongly model-dependent: it improves gate compliance for one generator by 12.5 percentage points, has no measurable effect for a second, and collapses output in a third. Across gated configurations ontology density is largely unchanged, indicating that symbolic validation improves clinical validity rather than vocabulary richness. Symbolic gating therefore buys corpus validity but no commensurate gain on real lung-cancer notes in this study; retrieval should be evaluated per model, and ontology density should not be reported as a proxy for corpus quality. --- ### When More References Hurt: Contamination-Aware DINOv2 Memory Banks for Few-Shot Steel Defect Detection Authors: Hannaneh Kalantary, Javad Khoramdel Published: 2026-08-22 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.22082v2 Patch-memory anomaly detectors assume that their reference bank is normal, an assumption that is difficult to guarantee when additional industrial images are unverified. We study whether a few trusted normal images can safely recover useful normal patches from such references without defect masks. Starting from the DINOv2 patch-memory formulation used by AnomalyDINO, we score candidate patches by distance to a clean seed bank, discard the most suspicious 20%, merge the retained patches with the seed, and enforce a fixed budget by greedy coreset selection. On Severstal, naive additional references contain 9.46% anomalous patches; the proposed trim rejects 78.1\% of them and reduces residual contamination to 2.59%. At an equal 51,200-patch development budget, the proposed bank reaches 0.1084 AUPRC versus 0.0950 for naive expansion, 0.0952 for random removal, and 0.1030 for eight clean images. Injecting only 0.5\% anomalous patches into a clean bank reduces AUPRC from 0.1030 to 0.0759. On all five completed held-out pairs, the proposed bank improves over naive expansion, with a mean gain of 0.0142 AUPRC. Reference purity is therefore a first-order design variable, and unverified images are useful only when their contribution is filtered explicitly. --- ### W-RAG: Source-Aware Retrieval for Enterprise Document Generation from Heterogeneous Knowledge Bases Authors: Hridya Dhulipala, Rajesh Ombase, Michael Wang, Tien N. Nguyen Published: 2026-08-22 Categories: cs.SE, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2608.22081v1 Retrieval-Augmented Generation (RAG) enables large language models to incorporate external knowledge during generation, improving factual grounding and domain adaptability. However, existing RAG pipelines assume that evidence retrieved from multiple repositories can be ranked globally using a single similarity function. While suitable for open-domain retrieval, this assumption breaks down in enterprise document generation, where heterogeneous knowledge bases (such as policies, regulations, technical documentation, and departmental guidelines) serve distinct roles and must be jointly represented in the generated document. As a result, global ranking often produces unbalanced context dominated by a subset of sources, leading to incomplete enterprise drafts. To address this limitation, we propose W-RAG, a source-aware retrieval framework that performs ontology-guided retrieval, local ranking within each knowledge base, and source-level weighting to regulate evidence composition. We further introduce a new dataset for retrieval-grounded enterprise document generation spanning multiple document types and industry domains. Experiments show that standard RAG pipelines struggle on this task, while W-RAG significantly improves document coverage and generation quality. --- ### Spine-Branch Coordination for Multi-agent Computer Use Authors: Mian Zhang, Manasi Sharma, Sheng Zhang, Minglai Yang, Kejian Shi, Ying Liu, Zhiyu Zoey Chen, Daniel Yue Zhang Published: 2026-08-22 Categories: cs.CL, cs.MA arXiv: https://arxiv.org/abs/2608.22077v1 Computer use agents (CUAs) are increasingly deployed as multi-agent systems that decompose a task into multiple subtasks executed across parallel virtual machines (VMs). However, a critical physical bottleneck is that the state of two VMs cannot be merged. Previous systems handle this ad-hoc rather than treating it as a first-class concern. We propose Spine-Branch Coordination for multi-agent computer use, a framework that decomposes a task into a "spine-branch" graph, where the spine carries the main task flow with continuous VM state and branch tasks execute in parallel to collect information the spine needs to complete the task. Branch VMs are discarded once their tasks finish, so no VM merging ever occurs. Experiments show that on 200 long-horizon tasks from Odysseys and across three CUA backbones, Spine-Branch improves success rate over the baseline system by 6.0% to 16.5%, while reducing per-task cost by 34% to 70%, indicating that explicitly modeling VM-state merging constraint enables multi-agent computer use to scale efficiently. --- ### Improving Energy Efficiency of Oil Platforms Through Optimal Loading of Diesel Generators Using Machine Learning and Search Algorithms Authors: Khivishta Boodhoo, Isaac Triguero, Josh Plumbly, Bruce Nicolson, William Meredith, Nicholas Watson Published: 2026-08-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.22076v3 Rising energy demand, fossil fuel depletion and climate change highlight the need for more efficient energy production and consumption. Offshore oil and gas platforms face challenges related to inefficient energy use, system failures, accessibility and environmental impact. Machine learning (ML) offers opportunities to improve the safety, sustainability and efficiency of these systems; however, previous research has largely focused on increasing oil production rather than reducing energy consumption on platforms. This study investigates the use of ML and search algorithms to improve diesel efficiency on an offshore oil platform. Data collected over 18 months from a platform in Scotland were analysed, focusing on four diesel generators as the primary diesel-consuming equipment. Following exploratory data analysis and outlier detection, regression models were developed to predict daily diesel consumption for different generator power loads. Multiple Linear Regression and Artificial Neural Networks achieved the best predictive performance compared with Extra Trees Regression, Extreme Gradient Boosting and Random Forest. Search algorithms were then used to identify combinations of generator power loads that minimised daily diesel consumption. The results showed an average diesel saving of 27% per day compared with the worst daily power-load combinations, equivalent to approximately 24,000 litres/day. These findings demonstrate significant opportunities for improving energy efficiency on offshore oil platforms using ML-based optimisation. --- ### Autonomous Cyber Defense: Real-Time Attack Detection and Mitigation in Software-Defined Networks Using Machine Learning Authors: Alexandre Amaral, Fernando Moro, Ana Malheiro Published: 2026-08-22 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.22075v3 Autonomous response has evolved into a timing-critical challenge rather than solely a matter of detection accuracy. In recent intrusions, the interval between initial access and the first lateral movement has been observed to be as short as 27 seconds, a window that precludes any human-in-the-loop workflow. This paper presents a closed-loop framework that detects and blocks attacks in software-defined networks without operator involvement, evaluating its performance against this stringent temporal constraint rather than relying exclusively on detection accuracy. An automated data pipeline collects IP flows and aggregates them into labeled training data, while a prevention module selects and trains candidate classifiers and issues blocking rules directly to the SDN controller. In a SYN flooding denial of service case study, the deployed K-Nearest Neighbors classifier achieved an F1 score of 96.7% and the cycle from flow availability to enforced block completed in 21 seconds, below the fastest breakout time reported to date. ---