# Research Papers — 2026-08 · bundle page 196 of 240 > Full-text markdown of papers #9751–9800 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/196 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/195.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/197.md) ### DBLAST: Dependent Block Drafting for Stochastic Speculative Decoding Authors: Amirmohammad Karimi, Chao Gao, Negar Hassanpour Published: 2026-08-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.05448v1 Speculative decoding accelerates large language models' inference by using a lightweight drafter to propose multiple future tokens and a target model to verify them. While recent block and diffusion-style drafters can predict several positions in a single pass, their training and sampling procedures are typically optimized for greedy decoding or assume that positions in the draft block are conditionally independent. This assumption becomes brittle in non-greedy speculative decoding, where the target distribution is deliberately stochastic and multiple continuations become plausible. We study this mismatch for block diffusion drafters and show that the accepted draft length degrades as the entropy of the target sampling distribution increases. We propose a dependent block drafter based on a low-rank latent mixture over token positions, complemented by an acceptance-oriented training objective that directly targets the expected verified length. Experiments with Qwen3-4B and Qwen3-8B on GSM8K, MT-Bench, HumanEval, and creative-writing benchmarks show that our approach, namely DBLast, consistently improves accepted length over independent block sampling, especially in higher-entropy decoding regimes. --- ### Example-Guided Prompting for Document-Level Text Simplification Authors: Marina Litvak, Ariel Perstin, Ilan Shtilman, Michael Färber Published: 2026-08-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.05447v1 Document-level text simplification requires large language models (LLMs) to rewrite complex documents while preserving meaning, readability, and discourse coherence. Although prompt-based LLMs have shown promising performance, they often produce inconsistent simplifications because textual instructions alone provide limited guidance for complex document-level transformations. We investigate whether retrieved document-simplification examples can improve document-level generation by augmenting prompts with examples selected from a parallel simplification corpus. This example-guided prompting approach enables LLMs to exploit relevant simplification patterns without task-specific fine-tuning. Experiments on the OneStopEnglish corpus using multiple state-of-the-art LLMs show that incorporating retrieved examples consistently improves simplification quality over prompt-only generation and achieves competitive or superior performance compared with representative supervised (T5) and planning-based (PlanSimp) document simplification systems. Furthermore, we find that the benefits of example-guided prompting vary across LLMs, suggesting that effective use of retrieved examples depends on a model's ability to integrate contextual information during generation. --- ### EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents Authors: Xuying Ning, Dongqi Fu, Tianxin Wei, Hanqing Zeng, Yuanchen Bei, Bingxuan Li, Zihao Li, Qifan Wang, Xiang Shen, Yifan Wu, Jiayi Liu, Hong Li et al. Published: 2026-08-05 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.05446v1 Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, invoke tools, verify outcomes, and reuse experience across interactions. However, effective harness use raises two coupled challenges: state formation from noisy interaction traces and runtime control over external-state access. Existing agents usually handle both through prompts, heuristics, or domain-specific conventions, leaving the external workspace and its usage policy manually engineered. To address this, we study the problem of harness policy learning, where agents learn harness policies offline and deploy them to construct and update external harness state online during runtime task execution. We introduce EvoHarness-RL, which exposes Belief, Progress, and Experience (BPE) as policy-facing harness state. Supervised harness fine-tuning teaches the base agent the harness action space and how to construct useful external state, while cost-aware GRPO explores coordination policies to selectively read, update, and consolidate that state during long-horizon interaction. Instantiated on ALFWorld with a Qwen3-8B LLM, EvoHarness-RL reaches 96.9% success and reveals two key dynamics: harness annealing, where training internalizes recurring harness-use patterns into the model policy and shifts the agent from frequent harness calls toward selective external-state access, and harness evolution, where progress updates and experience consolidation refine the harness into a compact, task-adaptive state substrate. These results suggest that long-horizon agents benefit from trainable policies for constructing and coordinating with external harness workspaces, beyond simply adding stronger tools or larger memories. --- ### SCP-NL2TL: Selective Conformal Prediction with Semantic Verification for Natural Language to Temporal Logic Specifications Authors: Yixuan Wang, Licheng Luo, Yu Fu, Kaidi Xu, Yue Dong, Mingyu Cai Published: 2026-08-05 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.05439v1 Translating natural language instructions into machine-interpretable formal specifications enables robots and autonomous systems to plan, reason, and formally verify their behavior. However, existing translation models typically generate a specification for every input, even when the result is unreliable or fails to capture the user's intent, creating risks in safety-critical applications. Inspired by selective conformal prediction, we propose a selective translation framework that not only generates formal specifications but also determines when they can be trusted. Reliability is scored by two complementary black-box signals, the fidelity of the specification back-translated into natural language and the dispersion of repeated translations under exact semantic equivalence, which fail on different errors and jointly separate incorrect translations more sharply than either alone. Conformal risk control calibrates this score into a decision that accepts a specification or abstains, with a distribution-free bound on the rate at which incorrect specifications are accepted for execution, and a conformal anomaly detector on instruction embeddings screens out-of-distribution inputs before any translation is attempted. The proposed framework is general across formal specification languages, with experiments on Signal Temporal Logic (STL), Linear Temporal Logic (LTL), and geometric Spatio-Temporal Logic (SpaTiaL) demonstrating improved translation reliability, robustness under the evaluated cross-tier shifts, and effective uncertainty-aware abstention. This work establishes a foundation for trustworthy natural language interfaces by enabling AI systems to recognize when generated specifications may not be reliable. --- ### Discrete energy as an exact label-free training objective for finite-element surrogates Authors: Ruifeng Cao, Xidan Song Published: 2026-08-05 Categories: cs.CE, cs.LG, math.NA arXiv: https://arxiv.org/abs/2608.05437v1 Supervised training of finite-element (FE) surrogate models requires reference solutions, and each reference solution is obtained by solving the system that the surrogate is intended to replace. The assembled discrete potential energy provides a training signal that requires no reference solution. This note records, with proofs, the identities that make this signal exact for linear elastostatics: the difference between the energy of a prediction and the energy of the reference solution equals one half of the squared stiffness-norm error, and the gradient of the energy equals the stiffness-weighted error. Label-free discrete-energy minimisation and supervised regression in the stiffness norm therefore have the same unique minimiser and identical gradients at every point. Around this central result, the note states a conditioning lemma that bounds the displacement error by the energy gap, a modewise contraction identity that explains why the Euclidean displacement error is an unsuitable primary metric, the Chebyshev bound that governs conjugate-gradient post-processing of surrogate predictions, and a conditional latent-separation proposition for joint-embedding predictive architecture (JEPA) pretraining on a shared stiffness operator, with an explicit numerical counterexample that delimits its scope. Every claim with numeric content is implemented as an executable falsification check; the checks were executed twice, on synthetic test problems and on a probe set of 16 instances from the validation split of a pre-registered experimental run, and every inequality holds, with the measured tightness reported. A closing section explains why the construction does not extend to elastodynamics through direct minimisation of the action functional, and which time-discrete formulation restores exactness. --- ### The ethics of artificial intelligence in the life sciences: Universality, cultural diversity and an architecture of care Authors: Jean-Pierre Changeux, Gustavo Deco, Morten L. Kringelbach Published: 2026-08-05 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2608.05436v1 The life sciences and health research have started to benefit from artificial intelligence, which raises ethical concerns that are real but, we argue, not special. Any science should be governed by values that rest on how the human brain is built and socialised rather than anything distinct to artificial intelligence. Importantly, the human brain has a different, much less costly computational architecture than these machines. This is achieved through the orchestration of a global neuronal workspace, and through reward best described not as a quantity to be maximised but as a continuous cycle of wanting, liking and satiety. As such, this creates the deep tension running through the ethics of the human person, between the universality of ethical judgement and the diversity of morals. The brain networks of the global workspace and emotion are universally shared, but the diversity of content is shaped by epigenetic appropriation of the particulars of the physical, social and cultural world, which makes every person unique. Still, if we were to build machines on these principles rather than the present unaffordable reward maximisers, the question of their governance would change from restraint to upbringing. We set out the institutions such a future would require, together with the questions that remain open. --- ### Risk-Aware Quantile Learning for Personalized Dynamic Treatment Regimes Authors: Chunyin Lei, Annie Qu Published: 2026-08-05 Categories: stat.ME, math.ST, stat.ML arXiv: https://arxiv.org/abs/2608.05434v1 Sequential clinical decision-making often involves more than maximizing average efficacy. Clinicians may need to simultaneously optimize clinically relevant tails of the outcome distribution, control treatment-related risk, and choose among multiple treatment options. Existing quantile dynamic treatment regime (DTR) methods capture distributional features of treatment outcomes but remain largely restricted to efficacy-only objectives and binary treatments. To address these limitations, we propose Risk-Aware Quantile Dynamic Treatment Regimes (RQDTR), a unified framework that optimizes a prespecified quantile of the cumulative potential outcome while explicitly incorporating treatment-related risk. We also develop an angle-based formulation for jointly learning decision rules across multiple treatment categories. Our framework includes three interpretable subclasses: efficacy-only quantile learning, constraint-based learning with population-level risk control, and utility-based learning through a composite benefit-risk utility. Theoretically, we establish identification and oracle equivalence, Fisher consistency of the smoothed surrogate, consistency of the estimated regime, and finite-sample performance error rates. Extensive simulation studies and applications to All of Us major depressive disorder and MIMIC-III sepsis data demonstrate that RQDTR improves tail-oriented efficacy and achieves more favorable benefit-risk trade-offs than existing quantile DTR methods. --- ### Robust Context-Aware Detection of Malicious Instructions in Text Authors: Buzhao Liu, Xinhang Ma, Yevgeniy Vorobeychik Published: 2026-08-05 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.05430v1 The remarkable instruction-following ability of modern LLMs has enabled their practical use as the minds of agents that can autonomously complete increasingly complex tasks. Therein, however, also lies their vulnerability to attacks which embed malicious instructions in text, common variants of which are known as indirect prompt injection (IPI). A fundamental task in addressing this vulnerability is successful segmentation of a given text into benign and malicious sentences (if any). While a number of approaches for this task have been proposed, no detector combines query-relative detection at the segment level, and none are hardened against adaptive evasion attacks realizable in agentic executions. We address the former limitation by developing an approach for malicious sentence classification that is both context- and query-aware. Next, to harden the resulting classifier against evasion, we present two adversarial training methods. The first is directly adapted feature-space adversarial training (AT) in which evasions are approximated using projected-gradient-based optimization in the embedding space. The second simulates realizable evasion attacks in the AT loop through LLM-based paraphrasing. Crucially, we parametrize both AT variants to facilitate a smooth tradeoff between utility and attack robustness. In extensive experiments using indirect prompt injection benchmarks we show that the proposed approach outperforms state-of-the-art IPI defense baselines under static attacks, while in the case of adaptive attacks, our AT variants provide significantly higher utility, lower attack success rate, and often both. Finally, we show that the best AT parameters can depend intimately on the particular application domain. Consequently, domain-dependent tuning of malicious text detectors is likely necessary in practice. Our code is publicly available at https://github.com/tavia-liu/CAD. --- ### Invisible Shortcuts: Why Vision Encoders Know Your Camera Authors: Vladan Stojnić, Ryan Ramos, Giorgos Kordopatis-Zilos, Noa Garcia, Giorgos Tolias Published: 2026-08-05 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.05424v1 Deep vision models exploit shortcuts, relying on cues that correlate with supervision signals. Prior work has focused on visible biases, such as object-background or texture correlations. We identify a different source of shortcut learning: invisible metadata traces embedded at the pixel level, for metadata such as image processing and photo acquisition. We hypothesize that large-scale semantic supervision, whether through categorical labels (ImageNet) or billion-scale captions (LAION), naturally induces metadata-semantics correlations during pretraining, leading models to convert low-level signals into predictive features. By introducing controlled metadata-semantics correlations, we show that stronger ones produce systematically higher sensitivity to metadata traces and larger performance degradation under metadata distribution shifts. We further explore mitigation strategies applied during and after pretraining that reduce sensitivity not only to targeted metadata but also to unseen ones, without sacrificing performance on downstream tasks. Metadata sensitivity also has a positive side: it partly explains the strong generated-image detection ability of some encoders, while its mitigation can improve out-of-distribution generalization. Code: https://github.com/ryan-caesar-ramos/visual-encoder-traces --- ### Why the Third Axis Is Freedom Authors: Michael Timothy Bennett Published: 2026-08-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.05423v1 In generative training, a model produces an output and is penalised for its difference from an example. With one output per comparison, a model that produces one common answer can outperform a model retaining a broader repertoire. Explorative Modeling (XM) produces $K$ outputs per comparison and updates on the closest, claiming exploration as a "third pretraining axis" associated with generative expressivity. Here I show the third axis is actually freedom, meaning the weakness of the constraint implied by a model's behaviour. Previous work showed freedom is a property of function rather than form. Parameters, architecture, minimum-description-length (MDL), and data can vary while the behavioural constraint remains unchanged. It was formally proved that weakest models are likeliest to generalise, and freedom selection beat MDL by 110-500\% in induction experiments. I prove average XM loss depends on the chance a candidate misses an acceptable region, with exploration raising miss probability to power $K$. For $K>1$, match probability rises with freedom. I then demonstrate empirically that XM optimises for freedom. In a Forward XM experiment, larger $K$ increased or saturated measured freedom, and increased freedom at every tested value under context-dependent targets. I trained XM candidate pools and compared validation selection with a freedom selector that read unlabelled parent contexts. Freedom won in 29 of 30 cases. Generative expressivity is a mode-count proxy for freedom, that discards the extension structure that gives freedom its generalisation significance. XM is a means, freedom an end, and selecting for freedom improved XM under distribution shift. --- ### IFlowNets: Extending Generative Samplers to Learn Strategies in Incomplete Information Games Authors: Conor M. Artman, Nicholas Di, Scott Perkins Published: 2026-08-05 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2608.05422v1 While many algorithms blend reinforcement learning (RL) with counterfactual regret (CFR) methods to leverage tradeoffs in computational speed and performance, there are fewer investigations into generative sampling frameworks in game theoretic applications in incomplete information games. We extend a generative flow network framework, Adversarial Flow Networks (AFlowNets), to incomplete information games, called Information Flow Networks (IFNs). We prove that previously established constraints for generative flow networks in complete information games are inadmissible for obtaining valid densities (corresponding to player strategies) and a valid training objective. We show that our proposed generalization, IFlowNets, alleviates this issue and strictly generalizes AFlowNets. In preliminary results for three standard game environments, IFlowNets perform comparably to or better than Outcome Sampling Monte Carlo Counterfactual Regret (OSMCCFR) and standard RL-based methods in performance and speed. --- ### Can Open-Weight LLMs Produce Kernel-Verified Coq Proofs? A Pilot Study Authors: Ahmed Ryan, Md Erfan, Akond Ashfaque Ur Rahman, Md Rayhanur Rahman Published: 2026-08-05 Categories: cs.LO, cs.LG arXiv: https://arxiv.org/abs/2608.05420v1 Large language models (LLMs) can generate text that resembles a mathematical proof, but resemblance does not establish correctness. A formal proof checker verifies whether each proof step follows established logical rules. Coq bases its rules on the Calculus of Inductive Constructions, a logical framework that defines which proof steps the system may accept. This pilot study evaluated six open-weight LLMs on the same 100 theorems from CoqStoq, a benchmark derived from real Coq projects. Each LLM received one attempt per theorem with the temperature set to 0, and Coq checked every proposed proof in the theorem's original project environment. We counted a proof as successful only if the Coq kernel accepted it. Gemma 4 verified 12 of 100 theorems, Llama 3.3 verified 8, and DeepSeek Coder V2 Lite verified 1. Qwen 3.5, Mistral Small 3.1, and GPT-OSS verified none. The 21 successful model-theorem results covered 15 distinct theorems, 11 of which were not solved by a baseline of standard Coq tactics. All verified theorems had short or medium human-written reference proofs; no model verified a theorem with a long reference proof. Because the proof-length analysis was exploratory, this pattern does not establish that proof length caused the difference. For the three models with at least one success, the total generation cost per verified proof ranged from 741 to 36,193 output tokens, 14.9 to 178.0 seconds, and 0.0167 to 0.2000 aggregate GPU hours. We could not calculate these ratios for models with no verified proofs. Across 600 attempts, the models produced 21 kernel-verified proofs, giving an overall success rate of 3.5%. The study reports descriptive differences among the models but does not statistically test whether one model outperforms another. Therefore, the results do not establish a universal ranking of the six models. --- ### Perturbation Sensitivity at Convergence: A Simple Signal for Identifying Spuriously Correlated Samples Authors: Nilesh Kumar Published: 2026-08-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.05419v1 Models trained by empirical risk minimization on data containing spurious correlations achieve high average accuracy while failing on subpopulations where the correlation does not hold. Existing methods for identifying the affected samples without group annotations rely on signals from early training, which requires locating the epoch at which to intervene, a hyperparameter typically selected using group-labeled validation data. We show that a usable signal is available after convergence, when loss no longer distinguishes the two populations. Samples consistent with the spurious correlation are classified by a shared rule, while the remaining samples are fit through configurations specific to individual inputs and are correspondingly more fragile. Applying a fixed perturbation to a converged model's inputs flips the predictions of the latter far more often than the former. The resulting procedure requires two forward passes per training sample, no group annotations at any stage, and no early-stopping epoch. Using the detected samples to rebalance training raises worst-group accuracy on Waterbirds from 57.3% to 80.8%, against 85.8% with ground-truth group labels. --- ### Negotiating Risk Boundaries in AI for Policing Through Mixed-Stakeholder Deliberation Authors: Mackenzie Jorgensen, Jo Reilly, Alex Sutherland, Miri Zilka Published: 2026-08-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.05418v2 AI tools are being increasingly adopted in policing in the UK and worldwide. Racial bias is a known and well-documented risk, yet representatives of affected communities are rarely included in decisions about AI adoption. We present results from a mixed-stakeholder deliberation workshop bringing together 30 community representatives, police officers, and academics to assess the risks of 13 AI use cases in policing, with an explicit focus on racial bias. We found that participants were broadly open to AI adoption, rejecting only three use cases outright -- most notably recidivism risk assessment, where objections targeted the premise rather than the implementation. Our analysis reveals that foregrounding racial equity did not narrow the deliberation. Instead, discussions gravitated toward a fundamental set of questions: does this tool actually work, will it deliver genuine benefit, and will that benefit extend to everyone? This integrated reasoning---reminiscent of the curb-cut effect in inclusive design---highlights the benefit of incorporating the racial bias lens into the risk-benefit analysis of AI use cases from the outset. --- ### Negotiating Risk Boundaries in AI for Policing Through Mixed-Stakeholder Deliberation Authors: Mackenzie Jorgensen, Jo Reilly, Alex Sutherland, Miri Zilka Published: 2026-08-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.05418v1 AI tools are being increasingly adopted in policing in the UK and worldwide. Racial bias is a known and well-documented risk, yet representatives of affected communities are rarely included in decisions about AI adoption. We present results from a mixed-stakeholder deliberation workshop bringing together 30 community representatives, police officers, and academics to assess the risks of 13 AI use cases in policing, with an explicit focus on racial bias. We found that participants were broadly open to AI adoption, rejecting only three use cases outright, most notably recidivism risk assessment, where objections targeted the premise rather than the implementation. Our analysis reveals that foregrounding racial equity did not narrow the deliberation. Instead, discussions gravitated toward a fundamental set of questions: does this tool actually work, will it deliver genuine benefit, and will that benefit extend to everyone? This integrated reasoning, reminiscent of the curb-cut effect in inclusive design, highlights the benefit of incorporating the racial bias lens into the risk-benefit analysis of AI use cases from the outset. --- ### Spectral Distillation: From Nonlinear Dynamics to Linear State-Space Models Authors: Liane Galanti, Devan Shah, Shlomo Fortgang, Elad Hazan Published: 2026-08-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.05416v1 Can nonlinear dynamical systems be learned through a compact linear state-space representation, without directly solving a non-convex system-identification problem? We give a provable pipeline for doing so. Starting from observations of an unknown nonlinear dynamical system, we first learn an implicit spectral predictor using Observation Spectral Filtering (OSF), a convex method that competes with the best linear observer for the system. We then apply spectral-to-LDS distillation to convert this predictor into an explicit recurrent linear dynamical system. Our main theorem shows that the average prediction error of the distilled LDS decomposes into an exponentially-small distillation term and the OSF learning term governed by the Luenberger complexity of the best observer. The guarantee is dimension-free: it depends on observer complexity rather than on the latent dimension needed to represent the nonlinear system. To our knowledge, this yields the first end-to-end provable method for extracting a best-in-hindsight LDS representation of nonlinear dynamics through convex learning followed by provable distillation. Experiments on linear LDS benchmarks and MuJoCo behavior cloning show that the train-then-distill pipeline produces compact LDS predictors that match or outperform directly trained baselines. --- ### Evaluating and Improving Pedagogical Fit in LLM-Based AI Tutors with the Pedagogical Suitability Index Authors: Benjamin Barlog, Hudson Craig, Zedong Peng Published: 2026-08-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.05411v1 Large language models (LLMs) are increasingly used as AI tutors, but a correct answer is not always a pedagogically appropriate one. In classroom learning, effective help depends not only on correctness, but also on whether a response matches the learner's current foundation, the course sequence, and the timing of concept introduction. Existing evaluations focus mainly on answer quality, leaving this instructional fit under-measured. We present the Pedagogical Suitability Index (PSI), a composite metric of six theory-informed sub-scores that evaluates how well LLM-generated tutoring responses align with learner readiness and curricular progression, and we further use PSI as a structured feedback signal for response improvement. We evaluate four LLM tutors (ChatGPT, Gemini, Gemma4, and Qwen3) across 240 scenario-based evaluations using paired standard and defective prompts, then apply a PSI-guided regeneration protocol to 62 weak-performing cases. Baseline differences across the four tested models were modest overall (PSI range: 0.557 to 0.638), and open-weight and closed models did not exhibit a clear separation in pedagogical fit. Under the tested prompt perturbations, overall PSI remained largely stable (Delta = -0.002), though sub-score trade-offs emerged. More importantly, PSI-guided feedback substantially improved weak-performing cases: 51 of 62 cases improved (82.3%). Focused manual evaluation of the 62 PSI-selected weak cases provides initial evidence that the identified weaknesses are instructionally meaningful and that many PSI-guided regenerations correspond to human-judged improvement. These results suggest that learner- and curriculum-aware alignment may matter more for effective tutoring than model category alone, and that such alignment is both measurable and improvable. --- ### Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment Authors: Alina Klerings, Jannik Brinkmann, Heiner Stuckenschmidt, Simone Paolo Ponzetto Published: 2026-08-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.05409v1 Large language models typically undergo post-training to align them with safety policies but there exist many sophisticated jailbreaks that sidestep established safeguards. For instance, prior work by Andriushchenko et al. (2025) has found that changing the grammatical tense from present to past can be enough to elicit harmful responses. In this work, we uncover a more general failure of non-imperative syntactic forms. We demonstrate that this syntactic vulnerability exists in 16 models up to 70B parameters, using behavioral evaluation. To investigate the root cause, we apply causal mediation analysis, finding that refusal is partially conditioned on upstream syntactic features. By steering these purely syntactic features we are able to trigger and suppress refusal. Finally, we trace this ill-conditioning to linguistically biased post-training data of open-source models and show that increasing syntactic diversity can mitigate the issue. Our findings suggest that current alignment approaches introduce confounders that prevent a pure semantic grounding of the refusal decision. --- ### Adapting Vision Foundation Models with Cascaded Semantics Authors: Xi Xiao, Xingjian Li, Cheng Han, Tianyang Wang, Lin Zhao, Yunbei Zhang, Guosheng Hu, Runmin Jiang, Xi Li, Xiao Wang, Min Xu Published: 2026-08-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.05393v1 Prompt tuning, a leading parameter-efficient adaptation paradigm in NLP, has recently been extended to computer vision. Visual prompt tuning (VPT) adapts pre-trained vision transformers (ViTs) by updating a small set of additional prompt parameters. However, existing visual prompts are randomly initialized and do not exploit prior knowledge, such as instructions in NLP. We address this gap by injecting two complementary semantic priors into VPT. Fundamental image priors, including color, texture, and shape, are extracted with classical hand-crafted operators and injected into the input space, while self-attention maps provide instance-aware semantics in the feature space. We further propose a cascaded scheme that integrates both priors throughout ViT adaptation. Experiments on 34 challenging image classification datasets demonstrate superior downstream adaptation while tuning only 0.74% of ViT parameters. Project page: https://xixiaouab.github.io/Cascaded-Semantics/. --- ### Adaptive Arena-based Contestable Argumentative Network-of-Experts for Open-Ended Care Plan Coordination Authors: Truong Thanh Hung Nguyen, Hoang-Loc Cao, Phuc Ho, Phuc Truong Loc Nguyen, René Richard, Hung Cao Published: 2026-08-05 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.05391v1 Care plan coordination demands synthesizing heterogeneous clinical, functional, and psychosocial information across multiple professional disciplines, where monolithic LLM pipelines cannot perform in a transparent or safe manner. We present CANOE (Contestable Argumentative Network-of-Experts), a multi-agent neuro-symbolic framework that addresses these limitations through five modules: complexity assessment, adaptive team recruitment, role-based argumentative computation via an Arena-based Quantitative Bipolar Argumentation Framework (A-QBAF), human-in-the-loop contestation, and care-plan synthesis. Role-specialized agents generate supporting and attacking arguments for candidate interventions; conflicts are resolved through arena-based clash resolution before acceptability scores propagate across the argumentation graph. Care planners may accept, reject, edit, or add arguments, and the framework will deterministically recompute the final plan. Evaluation on Discharge Me! and MedicalRAG using ROUGE-L, AlignScore, MEDCON F1, FKGL, and LLM-as-a-judge shows that medically fine-tuned models achieve the strongest clinical correctness and safety, while CANOE's argumentative structure provides faithful explanation and human contestability. --- ### Text-Guided Refinement of Multi-sequence Glioma Subregion Segmentation with a Vision-Language Foundation Model Authors: Zach Eidex, Yu-nong Lin, Mojtaba Safari, Sean Pitroda, Ralph Weichselbaum, Zhen Tian, Xiaofeng Yang Published: 2026-08-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.05389v1 Background: Accurate glioma subregion delineation is important for radiotherapy planning and longitudinal monitoring, but manual contour correction is time-consuming. Models such as nnU-Net may generalize imperfectly and lack clinician-directed text correction. Purpose: We investigated adapting a three-dimensional (3D) vision-language foundation model for text-guided brain tumor segmentation refinement. Methods: We developed a lightweight VoxTell-based framework. Pretrained VoxTell generated initial masks. Oracle prompts derived from segmentation errors encoded target, action, location, imaging evidence, edit size, and preservation constraints. Frozen Qwen/VoxTell prompt embeddings were injected through trainable projections into its multiscale decoder conditioning; other weights remained frozen. Training, validation, and testing used 901, 100, and 250 BraTS-GLI cases. Cross-dataset transfer was evaluated on 100 meningioma, metastasis, pediatric tumor, and UPENN-GBM cases. Results: On the internal test set using post-contrast T1-weighted input, correct instructions improved subregion Dice similarity coefficient (DSC; enhancing tumor, edema, and necrotic/non-enhancing core) from $0.774\pm0.158$ to $0.796\pm0.137$. They outperformed blank prompts ($0.762\pm0.155$; Holm-adjusted $p<0.001$, $d_z=0.71$) and contradictory prompts ($0.770\pm0.163$; $p<0.001$, $d_z=0.48$). In cross-dataset testing, correct instructions improved DSC from $0.527\pm0.287$ to $0.550\pm0.278$ and outperformed contradictory instructions ($0.504\pm0.275$; $p<0.001$, $d_z=0.43$). Conclusion: A 3D vision-language foundation model can perform instruction-guided refinement of glioma subregion segmentations. Sensitivity to correct, blank, and contradictory prompts suggests text-dependent contour editing rather than nonspecific post-processing, supporting further evaluation as a clinician-in-the-loop tool. --- ### C$^3$PO: Evaluating Cross-Modal Composition and Counterfactual Performance in Omnimodal Models Authors: Swapnanil Mukherjee, Agyeya Negi, Tanuja Ganu, Ponnurangam Kumaraguru Published: 2026-08-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.05381v1 Current Multimodal Large Language Models (MLLMs) can process diverse sensory inputs, yet their reasoning remains heavily biased toward a dominant modality, resulting in brittle cross-modal reasoning. We introduce C$^3$PO, a benchmark of 3,404 samples spanning video, audio, image, and text, evaluating two abilities: information composition (fusing dispersed evidence) and counterfactual conflict (resolving deliberate contradictions). C$^3$PO's paired IC/CC structure and four-tier design enable targeted diagnosis of when and why cross-modal reasoning fails. Built through a fully automatic pipeline using 25 logically grounded templates, C$^3$PO reveals that while humans achieve 88.64% accuracy, the best model (Gemini-3.1-Pro) reaches only 73.17%, with open-source models collapsing under conflict. Through attention probes, we find 86-95% of failures stem from modality dominance: models commit to one modality while ignoring contradictory evidence, concentrating 87-95% of attention on text. Mid-layer attention entropy predicts correctness-sustained exploration succeeds, premature collapse fails. The 56-point accuracy gap between equally complex templates reveals that performance depends on modalities' structural roles in conflict resolution, not combinations. These findings show multimodal perception does not guarantee robust reasoning; architectures must enable sustained cross-modal attention to avoid premature --- ### DoctorAgents: an agentic framework to iteratively refine AutoML pipeline for small clinical temporal data Authors: Ruilin Wang, Bo-Hong Wang, Elizabeth Kourbatski, Jun Bai, Hegang Chen, Ziyang Song, Gilles Boire, Marie Hudson, Yue Li Published: 2026-08-05 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2608.05375v1 Clinical machine learning (ML) has the potential to support high-stakes medical decision-making, but reliable deployment is often constrained by scarce, heterogeneous, and temporal complexity. Developing effective ML pipelines for such data remains time-consuming and error-prone, while existing automated machine learning (AutoML) systems only partially address this challenge because they largely rely on brute-force search over predefined spaces and lack explicit reasoning and memory. We therefore reformulate AutoML for small clinical data from exhaustive search to reasoning-driven refinement. We propose DoctorAgents, an agentic AI framework that autonomously constructs and optimizes end-to-end ML pipelines through specialized large language model (LLM) agents for generation, validation, and refinement. DoctorAgents backpropagates natural-language feedback through textual gradient descent to perform targeted updates without exhaustive search. Experiments across diverse clinical tasks show that DoctorAgents consistently outperforms established AutoML baselines while producing more interpretable task-specific representations. --- ### Velocity- and Regime-Aware Detection of Intraday Options Market Manipulation, with Explainable Attribution Authors: Alex Chen, Maria Hybinette Published: 2026-08-05 Categories: q-fin.TR, cs.LG, q-fin.ST arXiv: https://arxiv.org/abs/2608.05373v1 Intraday market manipulation is hard to detect because its footprint is brief, buried in millions of quotes, and statistically similar to ordinary volatility. Detectors reach high recall only by flagging so many other days that measured precision collapses, producing alerts no regulator can act on. We show that this manipulation leaves a distinctive dynamic signature: a pump-and-crash pattern visible in the velocity of market state, rather than its level. We build a minute-level detection pipeline, strictly partitioned in time, based on smoothed state velocity: option-Delta velocity for index options and price velocity for equities. We explain every alert with SHAP attribution. We hold the test period strictly out-of-sample and fix all thresholds before evaluation. On the locked Indian BANKNIFTY index-options test, the plain autoencoder recovers 10 of 10 regulator-identified manipulation days. Conditioning detection on market regimes inferred by a hidden Markov model yields an instructive negative result. The regimes are descriptively distinct, but using them trades recall for precision. Under the closed-world assumption that unlabeled days are normal, precision remains near 25%. The same dynamic appears in thinly traded U.S. equities (SEC v. Patel). The shape of the signature survives the transfer; its velocity magnitude does not. A pump-reversal shape score ranks the complaint's alleged manipulation days with AUC 0.91 (ARQQ) and 0.81 (ACY). On the ARQQ worked example, the score peaks inside the complaint's documented minute window. Finally, exact SHAP attribution over every alert shows that unconfirmed alerts share the regulator-identified days' attribution profile (cosine similarity 0.99). The precision ceiling is consistent with incomplete enforcement labels rather than detector failure. What transfers across markets and instrument types is the dynamic signature itself. --- ### Quantum-Structured World Models (QSWMs) for Predictive Latent Dynamics Authors: Hailong Jiang, Emran Hossain, Feng Yu, Jianfeng Zhu, Guilin Zhang, Wulan Guo Published: 2026-08-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.05371v1 World models learn latent states that summarize interaction histories, evolve over time, and support prediction, simulation, or planning. Most existing world models represent these states using classical vectors, probability distributions, recurrent hidden states, or transformer activations. In this paper, we introduce Quantum-Structured World Models (QSWMs), a quantum-inspired framework for predictive world modeling with structured latent states, latent transition operators, and measurement-inspired decoding maps. We study whether mathematical structures inspired by quantum theory, such as complex-valued representations and density-matrix-like latents, provide useful inductive biases for world modeling. We establish three foundational properties: classical inclusion, predictive sufficiency, and structured compactness. We then instantiate complex-valued and density-matrix-like QSWM variants and evaluate them on elementary cellular automata against strong classical baselines. Results show promising local predictive potential for complex-valued QSWMs, while also revealing limitations in long-horizon rollout, density-matrix variants --- ### World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation Authors: Yuhao Pan, Haosong Peng, Zhengshen Zhang, Zhengyang Yan, Yalun Dai, Fushuo Huo, Chujie Wang, Tianyu Qi, Xiucheng Wang, Nan Cheng, Wenchao Xu Published: 2026-08-05 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2608.05369v1 Vision-language-action (VLA) models often treat main-view and wrist-view observations as parallel visual inputs, overlooking their distinct roles in robot manipulation. Fine-grained manipulation, however, benefits from anticipating how wrist-local interactions may evolve under the global task context. To address this limitation, we present World-to-Wrist VLA (W2-VLA), a VLA model for fine-grained robot manipulation with task-conditioned future wrist modeling. Given current multi-view observations and a task instruction, W2-VLA contextualizes a set of latent modeling tokens as a compact interface between the vision-language model and the wrist predictor. Conditioned on this interface and the observed wrist history, the predictor forecasts future wrist latents, which are transformed into future-aware context for action prediction. In addition, we introduce W2-CoT, a synthesis pipeline that produces structured annotations describing manipulation progress, physical transition cues, and wrist-local evidence. These annotations provide auxiliary supervision that shapes the task-conditioned latent interface. Experiments on LIBERO, RoboTwin 2.0, and real-world manipulation tasks demonstrate improved fine-grained and contact-sensitive manipulation across both single-arm and bimanual settings, while maintaining action-generation rates above 80 Hz. --- ### Counterfactual Analysis via Large Language Models Authors: Zonghao Yang Published: 2026-08-05 Categories: cs.AI, q-fin.GN arXiv: https://arxiv.org/abs/2608.05367v1 Counterfactual analysis aims to predict potential outcomes under hypothetical scenarios, offering valuable insights for decision-making. This paper investigates the application of large language models (LLMs), specifically the GPT-3.5 model, for counterfactual analysis. We focus on the online lending context, where the counterfactual return on investment (ROI) is crucial for evaluating different interest rate schemes. We begin by assessing the predictive performance of GPT and comparing it with advanced machine learning algorithms. The results show that prompt engineering can significantly enhance GPT's predictions, with the R-squared increasing from 1.97% to 2.84%, closely approaching the 3.48% achieved by gradient-boosted regression. Subsequently, we utilize GPT to generate counterfactual ROIs under a set of alternative interest rates. GPT exhibits logical coherence and causal reasoning in its responses. The findings underscore the potential of LLMs as effective tools for counterfactual analysis in online lending, suggesting broader applications for LLMs in various predictive and decision-making contexts. --- ### The interface of intonation and lexical tone: Boundary phenomena in Mandarin varieties Authors: Cong Zhang, Yiya Chen Published: 2026-08-05 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2608.05364v1 This chapter explores the intricate interplay between intonation and tone in Mandarin Chinese varieties, focusing on f0, the primary acoustic cue for both intonation and tone. The main empirical base is intonation boundary phenomena, where intonation and tone intersect and influence each other in conveying a range of sentence-level linguistic functions -- such as question vs. statement -- and a rich array of speakers' attitudinal information. Theoretical models and emerging techniques are also discussed to account for the observed interactions of tonal aspects and boundary phenomena to convey multiple levels of communicative meanings. --- ### CASCADE: An Agentic Regulatory Network Framework for Patient-Data-Validated Downstream Perturbation Prediction Authors: Jose A. Bird Published: 2026-08-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.05359v2 CASCADE is an agentic framework that predicts downstream transcriptional effects of gene perturbation from precomputed ARACNe regulatory networks, exposed via MCP. Prior work validates such tools by checking whether predicted genes are known cancer genes (membership); we instead test whether the predicted direction of change matches reality, using focal-gene copy-number amplification as a dosage-based proxy for the inverse of knockdown against real TCGA patient tumor data. For MYC, CASCADE's predicted knockdown targets show strong concordance with real amplified-vs-non-amplified tumor expression across three cancer types (BRCA: 90.0%, COAD: 72.0%, STAD: 85.7%; all p<0.0013), well above permutation baselines, surviving a PAM50 subtype control and replicating in an independent cohort (METABRIC, 87.2%). Compared against curated MSigDB gene-set baselines via Fisher's exact test, CASCADE's accuracy is not shown to exceed existing public knowledge of MYC- or E2F-driven biology, though its gene-specific direction-calling clearly outperforms a naive uniform guess. Extending to fifteen additional genes, validation proves gene-specific rather than universal: proliferation-machinery regulators mostly replicate, while lineage-identity transcription factors and one cyclin-D paralog (CCND2) consistently fail, a pattern we discuss as a hedged, post-hoc hypothesis. We separately benchmark whether an LLM-based agent correctly grounds natural-language requests into CASCADE's real MCP tool calls. Across 35 queries, a documented local model reaches 71.4% exact match (85.7% for a larger model); schema and gene-alias failures are resolved by scale or server-side correction, but both models confidently default to the wrong perturbation type on ambiguous queries, a failure a targeted fix could not resolve because its trigger condition never occurs. --- ### CASCADE: An Agentic Regulatory Network Framework for Patient-Data-Validated Downstream Perturbation Prediction Authors: Jose A. Bird Published: 2026-08-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.05359v1 CASCADE is an agentic framework that predicts downstream transcriptional effects of gene perturbation from precomputed ARACNe regulatory networks, exposed via MCP. Prior work validates such tools by checking whether predicted genes are known cancer genes (membership); we instead test whether the predicted direction of change matches reality, using focal-gene copy-number amplification as a dosage-based proxy for the inverse of knockdown against real TCGA patient tumor data. For MYC, CASCADE's predicted knockdown targets show strong concordance with real amplified-vs-non-amplified tumor expression across three cancer types (BRCA: 90.0%, COAD: 72.0%, STAD: 85.7%; all p<0.0013), well above permutation baselines, surviving a PAM50 subtype control and replicating in an independent cohort (METABRIC, 87.2%). Compared against curated MSigDB gene-set baselines via Fisher's exact test, CASCADE's accuracy is not shown to exceed existing public knowledge of MYC- or E2F-driven biology, though its gene-specific direction-calling clearly outperforms a naive uniform guess. Extending to fifteen additional genes, validation proves gene-specific rather than universal: proliferation-machinery regulators mostly replicate, while lineage-identity transcription factors and one cyclin-D paralog (CCND2) consistently fail, a pattern we discuss as a hedged, post-hoc hypothesis. We separately benchmark whether an LLM-based agent correctly grounds natural-language requests into CASCADE's real MCP tool calls. Across 35 queries, a documented local model reaches 71.4% exact match (85.7% for a larger model); schema and gene-alias failures are resolved by scale or server-side correction, but both models confidently default to the wrong perturbation type on ambiguous queries, a failure a targeted fix could not resolve because its trigger condition never occurs. --- ### DG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accounting Authors: Rahil Aftab, Vineet Kumar Rakesh, Soumya Mazumdar, Tapas Samanta Published: 2026-08-05 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2608.05358v1 Federated learning repeatedly incurs local optimization and model-update transmission. We study DG-FedReuse, a simulator-level mechanism that allows selected clients to contribute age-decayed cached updates when a stochastic head-gradient discrepancy proxy remains below a round-dependent threshold. A hard cache-age limit and minimum fresh-client quota constrain reuse, while fresh updates use an adaptive per-tensor Top-K numerical-field representation. Experiments cover six image-classification datasets, 50 virtual clients, Dirichlet label heterogeneity (α=0.5), and three seeds. At a common 90-round budget, DG-FedReuse yields 83.36-85.42% modeled update-data-field uplink saving, compared with 76.88% for matched Top-K FedAvg; the seed-aligned accuracy differences range from -5.29 to -0.14 percentage points. Best-observed test accuracies obtained under test-controlled checkpointing are retained only as exploratory archival evidence and range from -2.38 to +0.45 percentage points relative to matched FedAvg. A symmetric dense-model-downlink sensitivity reduces the headline saving to 41.68-F42.71% and the incremental gain over Top-K FedAvg to 3.24-4.27 percentage points, demonstrating the dependence of communication conclusions on the accounting boundary. The study characterizes the proposed reuse rule in the implemented simulator; it does not establish unbiased generalization, end-to-end bandwidth reduction, runtime or energy savings, faster convergence, or superiority over existing stale-update and lazy-aggregation methods. --- ### LoDA: A Level of Detection Aware Method and a Multimodal Sensing Benchmark for Object Level Change Detection Authors: Haitian Wang, Xinyu Wang, Sheldon Fung, Xian Zhang, Zichen Geng Published: 2026-08-05 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2608.05356v2 High-definition 3D LiDAR maps are important for autonomous driving and smart-city services, which require reliable detection of object-level changes in multi-temporal urban LiDAR to keep digital maps aligned with the physical world. Existing approaches from raster height differencing to depth image and point-cloud networks often remain tile-based and threshold-driven, yielding per-point scores without explicit detection limits or consistent object-level labels. We propose an object-level 3D change-detection pipeline that integrates detection-limit-aware registration, geometry-driven object proxies with rule-based semantic and instance segmentation, and displacement cues in height, volume, and surface-normal direction to assign five change labels with confidence. By decoupling registration, geometry, and semantics, the pipeline propagates pose uncertainty into spatially varying detection limits, stabilizes cross-epoch correspondences, and suppresses false changes caused by residual misalignment and density variation. We also present LoDA, a level-of-detection (LoD) aware benchmark for the Subiaco district with fused multi-temporal vehicle-LiDAR maps constructed with LiDAR, GNSS, and IMU support, semantic instances, and object-level annotations. On this benchmark, our method achieves 95.0% accuracy, 90.8% macro F1, and 83.0% macro IoU, exceeding the best baseline by 8.7 IoU points and 4.4 F1 points. On the public Urb3DCD-V2 benchmark evaluated under the official point-wise protocol, it reaches 96.81% mean accuracy and 89.52% mean change IoU, improving over the strongest reported baselines by 1.36 points in mAcc and 3.18 points in mIoUch. --- ### LoDA: A Level of Detection Aware Method and a Multimodal Sensing Benchmark for Object Level Change Detection Authors: Haitian Wang, Xinyu Wang, Sheldon Fung, Xian Zhang, Zichen Geng Published: 2026-08-05 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2608.05356v1 High-definition 3D LiDAR maps are important for autonomous driving and smart-city services, which require reliable detection of object-level changes in multi-temporal urban LiDAR to keep digital maps aligned with the physical world. Existing approaches from raster height differencing to depth image and point-cloud networks often remain tile-based and threshold-driven, yielding per-point scores without explicit detection limits or consistent object-level labels. We propose an object-level 3D change-detection pipeline that integrates detection-limit-aware registration, geometry-driven object proxies with rule-based semantic and instance segmentation, and displacement cues in height, volume, and surface-normal direction to assign five change labels with confidence. By decoupling registration, geometry, and semantics, the pipeline propagates pose uncertainty into spatially varying detection limits, stabilizes cross-epoch correspondences, and suppresses false changes caused by residual misalignment and density variation. We also present LoDA, a level-of-detection (LoD) aware benchmark for the Subiaco district with fused multi-temporal vehicle-LiDAR maps constructed with LiDAR, GNSS, and IMU support, semantic instances, and object-level annotations. On this benchmark, our method achieves 95.0% accuracy, 90.8% macro F1, and 83.0% macro IoU, exceeding the best baseline by 8.7 IoU points and 4.4 F1 points. On the public Urb3DCD-V2 benchmark evaluated under the official point-wise protocol, it reaches 96.81% mean accuracy and 89.52% mean change IoU, improving over the strongest reported baselines by 1.36 points in mAcc and 3.18 points in mIoUch. --- ### Evidence Lock Before Commitment: A Frozen Interface Degrades LLM-as-Judge Evaluation Authors: Divyansh Singh Published: 2026-08-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.05353v2 LLM judges are often asked to extract criteria and evidence before choosing between candidate answers. This workflow assumes that the intermediate record preserves the information needed for a later verdict. For reasoning-capable models, visible field order does not reveal internal decision order, so we test an observable alternative: persist the evidence in one call and make it the exclusive input to the next. Across 24,000 judgments over HelpSteer3, FeedbackQA, and CoVal, we compare standard pairwise judging, structured one-call judging, two-call evidence locking, and three-call pointwise locking with Claude Sonnet 4.5 and GPT-5. Evidence locking reduces agreement with released human preferences by 4 to 6 percentage points and increases answer-order inconsistency by 8 to 10 points relative to structured one-call judging. Pointwise locking is also harmful, while structured evidence elicitation remains close to standard judging. The result holds for both judges and all three datasets. Persisted evidence can support auditability, but it should not replace the source answers at decision time. --- ### Evidence Lock Before Commitment: A Frozen Interface Degrades LLM-as-Judge Evaluation Authors: Divyansh Singh Published: 2026-08-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.05353v1 LLM judges are often asked to extract criteria and evidence before choosing between candidate answers. This workflow assumes that the intermediate record preserves the information needed for a later verdict. For reasoning-capable models, visible field order does not reveal internal decision order, so we test an observable alternative: persist the evidence in one call and make it the exclusive input to the next. Across 24,000 judgments over HelpSteer3, FeedbackQA, and CoVal, we compare standard pairwise judging, structured one-call judging, two-call evidence locking, and three-call pointwise locking with Claude Sonnet 4.5 and GPT-5. Evidence locking reduces agreement with released human preferences by 4 to 6 percentage points and increases answer-order inconsistency by 8 to 10 points relative to structured one-call judging. Pointwise locking is also harmful, while structured evidence elicitation remains close to standard judging. The result holds for both judges and all three datasets. Persisted evidence can support auditability, but it should not replace the source answers at decision time. --- ### Multi-Agent Reinforcement Learning for Online Traffic Scheduling in Time-Sensitive Application Authors: Marcos Carvalho, Fatih Temiz, Shavbo Salehi, Melike Erol-Kantarci, Daniel F. Macedo Published: 2026-08-05 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2608.05346v1 Time-sensitive networking (TSN) is increasingly integrated into mobile edge computing (MEC) to support applications with stringent latency requirements, such as extended reality (XR). However, existing TSN scheduling solutions predominantly rely on static optimization techniques or centralized learning models that are based on fixed traffic patterns, limiting their effectiveness in dynamic environments. In practice, MEC environments often host multiple co-located XR traffic flows whose characteristics evolve over time, creating complex inter-queue dependencies that current schedulers fail to capture. Addressing these challenges requires adaptive, decentralized scheduling mechanisms capable of coordinating multiple TSN queues under varying traffic conditions. To this end, this paper proposes a multi-agent reinforcement learning (MARL) framework for TSN scheduling, where each TSN queue is modeled as an autonomous agent. The Heterogeneous-Agent Proximal Policy Optimization (HAPPO) algorithm is employed to explicitly model inter-agent dependencies and jointly optimize service delivery across queues. The simulation results demonstrate that the proposed approach reduces average frame waiting times by up to 26.8% and worst-case delays by approximately 16.8%, highlighting its effectiveness in dynamic XR-driven MEC scenarios. --- ### Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation Authors: Yuta Kobayashi, Pradyun Ramesh, Muhammad Ahmed Chaudhry, Vincent Jeanselme, Judy Wawira Gichoya, Sanmi Koyejo, Kathleen Capaccione, Shalmali Joshi Published: 2026-08-05 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.05341v1 Vision-Language Models (VLMs) for radiology report generation are typically trained on retrospective clinical reports, which suffer from omission noise: clinically present findings are left unreported due to the omission of subtle findings. For example, prior studies show that cardiomegaly may be omitted from ICU chest X-ray reports when the imaging request is focused on monitoring support device placement. As a result, models trained with standard approaches inherit these omissions, learning to under-report findings themselves. We propose PU-DPO, a preference optimization framework to prevent omission noise from corrupting the preference signal. We reformulate the objective under a positive-unlabeled (PU) learning framework, treating absent mentions as unlabeled rather than truly negative. Our framework provides preference supervision using constructed contrastive pairs, generated using edits to model responses, producing variants that explicitly mention or omit a specific finding. Generated responses that mention the finding are naturally preferred in the context of visual evidence. Across semi-synthetic experiments and analyses on real-world chest radiograph benchmarks where adjudicated labels are available, PU-DPO yields consistent gains in detection rates and recovery of hidden positives across multiple pathologies, and is more robust to omission noise than prior approaches. --- ### Multi-Agent Transformer for Queue-Level XR Traffic Scheduling in TSN Networks Authors: Marcos Carvalho, Fatih Temiz, Shavbo Salehi, Melike Erol-Kantarci, Daniel F. Macedo Published: 2026-08-05 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2608.05340v1 Time-Sensitive Networking (TSN) and Mobile Edge Computing (MEC) hold strong potential for enabling ultra-reliable low-latency communication for time-sensitive applications, such as eXtended Reality (XR). However, the widespread adoption of XR introduces significant challenges due to co-located services in MEC environments, leading to contention for shared network resources. Moreover, XR traffic types have distinct characteristics and criticality in terms of timing requirements, further increasing the complexity and dynamics of such environments. Although reinforcement learning has shown promise for TSN scheduling optimization in dynamic network scenarios, existing approaches rely on centralized or high-level multi-agent designs and are typically tailored to periodic and predictable industrial traffic, limiting their applicability to XR workloads. As a result, these approaches suffer from (i) limited ability to capture inter-queue dependencies due to coarse-grained control, and (ii) poor adaptability to highly dynamic and heterogeneous XR traffic. To address these gaps, we propose a multi-agent reinforcement learning approach for queue-level XR traffic scheduling. We adopt the multi-agent transformer (MAT) to model inter-queue dependencies via attention over agents' observations and actions, enabling implicit coordination across heterogeneous co-located XR applications. Our simulation results show that the proposed method outperforms baselines, achieving up to 71.42% latency reduction and up to 83.2% reduction in failure rate, while consistently achieving high reliability across all queues. --- ### Physics-Based Molecular Fingerprints from Spectral Graph Theory Provide Efficient Geometry-Aware Measures of Chemical Similarity Authors: Jacob W. Toney, Ayleen Y. Farnood, Samir Darouich, Heather J. Kulik Published: 2026-08-05 Categories: physics.chem-ph, cs.LG arXiv: https://arxiv.org/abs/2608.05336v1 Molecular representations are essential for the evaluation of molecular similarity and the development of structure-property relationships. Despite the known importance of 3D structure to determine chemical and physical properties, the most widely used molecular fingerprints encode only two-dimensional connectivity. Such representations fail to distinguish similar but distinct stereoisomers and conformers. Alternative 3D methods are typically defined pairwise, making their application to large chemical spaces prohibitive, while deep learning embeddings are expressive but uninterpretable and limited by their training data diversity. Here, we introduce novel physics-inspired molecular fingerprints based on principles from spectral graph theory. We represent molecules as a complete graph in 3D space, with edge weights encoding heuristic physical interactions. Eigenvalue decomposition of the resulting graph Laplacian matrix results in a computationally efficient fixed-length chemical fingerprint that encodes 3D structure while obeying necessary physical symmetries of permutation and E(3) invariance. Spectral fingerprints differentiate between unique molecular structures with identical 2D connectivity, overcoming a limitation of 2D descriptors, while maintaining the low computational cost needed for efficient screening of vast chemical spaces. We evaluate our fingerprints with community detection algorithms and observe strong performance against representative baselines across datasets from organic, inorganic, biological, reticular, and reaction chemistry. Nearest-neighbor property estimation and applicability domain analyses reveal the utility of our molecular representation in machine learning and cheminformatics. We anticipate that spectral fingerprints will serve as generalizable, interpretable, and efficient measures of chemical similarity that incorporate 3D information at minimal cost. --- ### Context Matters: Support Set Selection and Failure Detection for In-Context Medical Image Segmentation Authors: Youssef Gehad, Emmanuel Zerefa, Krish Kabra, Guha Balakrishnan Published: 2026-08-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.05333v1 In-context learning (ICL) adapts medical image segmentation models to unseen structures and modalities without retraining by conditioning on a task-specific support set of image-mask exemplars. Because this support set is the model's only task-specific signal, its composition directly influences segmentation performance. In this work, we investigate the support set as a controllable determinant of ICL reliability. First, we compare random sampling against similarity-based selection, where exemplars are retrieved based on their visual similarity to the query image. Second, we train a transformer-based classifier to predict, from the query and support images alone, whether a segmentation will fall below a specified Intersection-over-Union (IoU) threshold. Using MultiverSeg with DINOv3 embeddings across four benchmarks and three imaging modalities, we show that similarity-based selection consistently matches or outperforms random sampling, with the largest gains at the smallest support set sizes. Furthermore, our classifier predicts segmentation failure above chance on all four benchmarks. Ultimately, these results demonstrate that the reliability of in-context segmentation can be both improved via informed support selection and anticipated before use, providing practical mechanisms for safer clinical deployment. --- ### Hierarchical Server Architecture for Agentic Science Authors: Vanessa Sochat, Daniel Milroy Published: 2026-08-05 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2608.05332v2 Agentic science is transforming the landscape of computational work, and is applied to scientific pipelines and workload managers. Scientific workloads require specialized hardware within and between institutions. Automated resource discovery is an essential step for scheduling workloads with specific hardware and environmental requirements. In this paper, we present a hierarchical, dynamic architecture and accompanying software to discover resources across diverse cloud, edge, and HPC systems. The design enables concurrent, asynchronous negotiation, selection, and dispatch of requests for work using secretary agents. The agents probe and discover 51 real and simulated providers across 7 categories. We perform 19,973 negotiation and 6,952 selection simulations to assess reliability of decisions, demonstrating high (87.71%) negotiation accuracy and selection costs comparable to more traditional strategies. Designed for extensibility and currently supporting the US DOE Genesis Mission, this architecture exemplifies the importance of careful coordination between agents, discovery tools, and infrastructure for agentic science. --- ### Hierarchical Server Architecture for Agentic Science Authors: Vanessa Sochat, Daniel Milroy Published: 2026-08-05 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2608.05332v1 Agentic science is transforming the landscape of computational work, extending to scientific pipelines and workload managers. The workloads require specialized hardware within and across institutions. If assessing workload needs against environments is required for scheduling, automated discovery of resources is an essential step. In this paper, we present a hierarchical, dynamic architecture and software to discover resources across diverse cloud, edge, and HPC systems. The design enables concurrent, asynchronous negotiation, selection, and dispatch of requests for work using secretary agents. The agents probe and discover 51 real and simulated providers across 7 categories. We perform 19,973 negotiation and 6,952 selection simulations to assess reliability of decisions, demonstrating high (87.71\%) negotiation accuracy and selection costs comparable to more traditional strategies. Designed for extensibility and currently supporting the Genesis Mission, this architecture exemplifies the importance of careful coordination between agents, discovery tools, and infrastructure for agentic science. --- ### Computationally Efficient Collaborative Communication Via Regularity-Based Coarsening Authors: Mark Bedaywi, Scott Emmons, Nika Haghtalab, Stuart Russell Published: 2026-08-05 Categories: cs.GT, cs.DS, cs.LG arXiv: https://arxiv.org/abs/2608.05327v1 Our results show that the existence of a short high-utility protocol already suffices for efficient communication. In particular, in a game with $n$ possible observations and $m$ actions: (1) For any achievable target utility $α$, we give an algorithm with $\mathrm{poly}(n, m, 1/ε)$ runtime that designs a protocol achieving utility at least $α-ε$ using only $2^{\mathcal O(CC_α(G))}/ε^2$ bits of communication. Here, $CC_α(G)$ is the minimum number of bits used by any protocol, even a computationally inefficient one, to achieve utility $α$. (2) We prove that this exponential dependence on $CC_α(G)$ is tight up to a constant. That is, unless $\mathrm P=\mathrm{NP}$, no polynomial-time algorithm can in general find optimal protocols using fewer than $2^{CC_α(G) -2}$ bits. We note that our results strictly weaken the assumptions required by prior work in the multi-agent information aggregation literature, filling a gap that had remained elusive even for games with constant $CC_α(G)$. In particular, prior guarantees for agreement-based information aggregation rely on structural assumptions such as informational substitutes or weak learnability. We show that these assumptions already imply $CC_α(G) = O(1)$ and are therefore more restrictive conditions than required by our protocol to succeed. On a technical level, our results involve a novel strengthening of the Frieze-Kannan weak regularity lemma and yield the following powerful polynomial-time transformation tool: for every communication game $G$, it constructs a game $\hat G$ that is a coarsening of the agents' observation spaces into constant-size partitions, such that $G$ and $\hat G$ are indistinguishable with respect to every short communication protocol. This coarsening theorem is the engine behind our algorithm and may be of independent interest. --- ### QEvict: Recoverable Quantized KV Eviction for Attention-Drift-Robust Long-Context Decoding Authors: Ayushman Garg, Akshita Gupta, Shaswata Bhattacharya, Abhishek Gupta, Sandeep Kumar, Manoj Kumar Published: 2026-08-05 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.05326v1 Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache. A dominant line of work reduces this footprint by evicting tokens that appear unimportant under attention-derived scores. However, such policies make an implicit irreversible decision: once a token is evicted, it cannot become useful again. We show that this assumption is brittle during decoding. Token and window importance drift as generated queries evolve, causing standard eviction policies to permanently discard states that later receive substantial attention under the full-cache model. To characterize this behaviour, we introduce Future Missed Mass and Global LIR, two diagnostics that measure future attention assigned to discarded states and the reactivation of historically inactive regions. We propose QEvict, a three-tier KV-cache management scheme that replaces binary retain-or-delete eviction with recoverable eviction. QEvict maintains high-confidence windows in full precision, stores intermediate windows in a quantized recoverable tier, and deletes only the lowest-confidence windows. During decoding, cumulative attention scores update window importance and when a quantized window becomes important again, it is dequantized and promoted to the full-precision. Under a fixed memory budget, this design preserves broader historical context while retaining exact full precision for the most important regions. Across long-context understanding, retrieval, and reasoning benchmarks, QEvict consistently improves over representative eviction and quantization baselines, reducing missed attention and improving information retention --- ### Rectifying Geometric Misalignment: Online Source-Free Adaptation for Class-Imbalanced EEG Authors: Shiwen Chu, Shanglin Li, Motoaki Kawanabe, Reinmar Kobler Published: 2026-08-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.05315v1 Electroencephalography (EEG) based Brain-Computer Interfaces (BCIs) often require unsupervised domain adaptation (UDA) to generalize across subjects and sessions. While Riemannian alignment methods like the Riemannian Centering Transformation (RCT) are effective for handling covariate shifts, they implicitly assume balanced class priors. However, in realistic online BCI scenarios, the label distributions vary dynamically (label shift), causing standard alignment techniques to geometrically misalign the target data distributions. In this work, we propose OSPDIM (Online SPD manifold information maximization), a source-free online UDA framework designed to address label shifts on the Riemannian manifold. OSPDIM introduces a manifold-constrained bias parameter into the tangent space mapping, which is optimized via information maximization to correct the geometric skew caused by imbalanced data streams. Unlike offline methods relying on global batch statistics, OSPDIM estimates and corrects geometric bias on-the-fly. Simulations on 2D SPD matrices visually demonstrate that OSPDIM successfully rectifies the misalignment where standard centering fails. Extensive experiments on multiple motor imagery datasets show that OSPDIM significantly outperforms standard Riemannian baselines, particularly in challenging online adaptation scenarios with severe class imbalance, offering a robust solution for practical, plug-and-play BCI systems. --- ### Failing Gracefully: Mitigating Impact of Inevitable Robot Failures Authors: Duc M. Nguyen, Saad A. Ghani, Andrew Marshall, Allison Andreyev, Gregory J. Stein, Xuesu Xiao Published: 2026-08-05 Categories: cs.RO, cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2608.05313v1 Service robots operate in household environments shared with humans, pets, and everyday objects, where they are highly susceptible to failures such as software crashes, hardware degradation, or unpredictable interactions. While roboticists strive to minimize failures, some remain inevitable, making it critical to mitigate their potential consequences for safe and reliable deployment. This paper introduces a novel safety formulation that evaluates both the probability of impactful interactions between robots and surrounding entities during failures, and the severity of their outcomes. By quantifying the impact of failures on different entities, our approach enables robots to make informed planning decisions that balance safety with task efficiency. To support systematic evaluation, we also present FailBench, a MuJoCo-based simulation framework for studying robot-environment interactions under diverse failure modes, including sensing issues and actuator malfunctions. Together, our safety formulation and FailBench provide a foundation for developing safer and more robust motion plans and learned policies in real-world household environments. --- ### EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding Authors: Sangwoo Ha, Hyunwoo Seo, Yurim Jo, Youngjin Moon, Hoi-Jun Yoo Published: 2026-08-05 Categories: cs.AR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.05303v1 On-device deployment of Large Language Models (LLMs) has become essential for personalized edge applications. A primary bottleneck is external memory access (EMA) in feed-forward network (FFN) layers. Speculative decoding and mixture-of-experts (MoE) are promising solutions. Speculative decoding reduces the number of decoding stages by generating multiple tokens per stage, and MoE minimizes per-stage cost through sparse expert activation. However, there is an incompatibility when combining these two techniques. We propose EdgeXpert, a software-hardware co-designed LLM accelerator that resolves this incompatibility. In the prefill stage, the prompt-wise expert reuse reformulates routing as prompt-level expert reuse rather than independent per-token expert selection. It identifies important tokens using a lightweight encoder, constructs a shared expert set from them, and routes less important tokens with a reduced expert budget to lower expert EMA. In the decode stage, depth-aware expert coalescing exploits the contextual similarity and mutual exclusivity of same-depth candidate tokens. Rather than loading the union of all required channels, EdgeXpert loads only salient channels and applies computational calibration to recover accuracy without additional memory access. Synthesized in Samsung 28nm technology at 800 MHz, EdgeXpert achieves up to 56.3% latency reduction and 44.1% energy reduction compared to prior works, while maintaining near-baseline accuracy. --- ### Agentic self-driving microscopy benchmarks support qualification but do not necessarily generalize to unseen tasks Authors: Nathan S Johnson, Ian Abshire Published: 2026-08-05 Categories: cs.AI, cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2608.05266v1 Large language model agents are increasingly being developed to control a wide range of scientific characterization tools including microscopes and synchrotron beamlines. Research into agentic control of physical infrastructure is nascent and there are few well-established paradigms for how to engineer an agentic system. There are many choices to make when designing a microscopy agent, including the choice of LLM, the number of agents to use, agent responsibilities and delegation rules, retrieval-augmented generation parameters, and more. When designing and optimizing an agentic microscope controller, researchers not only want to ensure that the agent can correctly perform known tasks but also that the agent can generalize to new tasks that it has not encountered before. In this study, we develop a benchmark and trace-logging framework that reveals a) how different choices of agent architecture impact performance at microscopy tasks and b) the limitations of benchmarks for predicting if a particular agent will perform well on unseen microscopy tasks. The framework was used to evaluate one-, two-, and three-agent graph topologies, five LLMs, RAG and context parameters, and operational constraints across 53 microscopy benchmark tests. In total, 105 agent configurations, 1,949 individual test runs, and 49,109 RAG retrievals were recorded. Direct comparisons showed clear differences in latency, token use, cost, and failure mode between configurations. However, surrogate models trained on agent architecture and test results did not reliably predict an agent's performance on new, unseen tasks. These results show that these benchmarks are useful for qualification, regression testing, diagnosis, and direct comparison, but the current heterogeneous test suite does not support a task-independent global configuration model. --- ### Evaluating Machine Learning Models for Post-Wildfire Debris-Flow Prediction Authors: Quinn Ledingham, Zhengsen Xu, Yimin Zhu, Zack Dewis, Mabel Heffring, Saeid Taleghanidoozdoozan, Motasem Alkayid, Megan Greenwood, Lincoln Linlin Xu Published: 2026-08-05 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2608.05265v1 Prediction of post-wildfire debris flows is critical for mitigating hazards to communities, infrastructure, and resources during intense rainfall in recently burned areas. However, identifying reliable machine learning models is complicated by overlapping debris-flow and non-debris-flow events in feature space, the need for model interpretability, and limited training data. This paper addresses these challenges through a systematic evaluation of machine learning models in terms of predictive performance, feature importance, and synthetic data augmentation. Using basin-scale observations of post-wildfire debris-flow events across the western United States, we compare 15 models, including the Tabular Prior-Data Fitted Network (TabPFN). Repeated stratified cross-validation shows that TabPFN achieves the highest unaugmented performance with a threat score of 0.637, closely followed by the best tree-based models. SHapley Additive exPlanations (SHAP) are used to identify the features driving predictions, revealing that short-duration rainfall intensity and storm accumulation consistently rank highest, while burn severity and terrain features contribute less. We further evaluate synthetic data augmentation using TabPFN-generated samples to address the scarcity of debris-flow observations. Synthetic augmentation improves the performance of all models except CNN, with the largest mean threat score increase of +0.041 among the deep learning models. By combining rigorous model benchmarking, interpretable feature analysis, and synthetic data augmentation, this work provides a comprehensive framework for improving post-wildfire debris-flow prediction. --- ### OrchestraBench: Evaluating Multi-Agent Orchestration Failure Modes, Recovery, and Decomposition Quality Authors: Yidian Chen, Yingzi Gu, Natan Vidra, Spurthi Setty, Sharon Zheng Published: 2026-08-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.05263v1 Multi-agent orchestration frameworks are moving from demos to production, yet benchmarks typically report task accuracy without diagnosing why a pipeline failed, where a cascade began, or which routing decision caused the breakdown. OrchestraBench evaluates failure, recovery, and decomposition through a controlled, seed-reproducible failure-injection harness over templated enterprise workflows. It introduces cascade radius and per-failure-mode recovery as primary metrics and compares routing policies with bootstrap confidence intervals and paired tests. On a 26-case gold-labelled diagnostic, a keyword/flag router scored 0% on adversarial cases with misleading or missing surface flags, whereas an intent-reasoning model router scored 100%, matching the oracle. Controlled mechanism probes with a real Claude agent over a verifiable arithmetic dependency chain revealed three failure-handling tiers across five MAST modes: tool faults recovered fully (1.0), ambiguous delegation recovered partially (0.30), and three latent or semantic modes never recovered (0.0). This ordering persisted when the computation was reframed as a loan-approval workflow and across Sonnet, Opus, and Haiku, although absolute rates shifted with context. Blind retry reproduced latent faults and increased time to detection, indicating that detection and attribution are necessary for containment. Cascade radius increased with pipeline depth (mean 0.9 to 4.7 across depths 3-7). A trusted-state repair ablation showed that apparent containment gains primarily came from the trusted-state signal rather than autonomous detection. These results are controlled-chain mechanism probes, not domain-workload claims. ---