# Research Papers — 2026-08 · bundle page 26 of 240 > Full-text markdown of papers #1251–1300 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/26 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/25.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/27.md) ### Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents Authors: Nan Li Published: 2026-08-28 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.28458v1 Interactive dialogue games test a capability that static benchmarks largely leave implicit: a model must carry state across turns, interpret feedback, and choose valid actions under changing constraints. We study this setting in the LM Playschool Challenge with a 2B open-weight model, and find that many failures are not only broad knowledge failures but also local decision failures: repeated guesses, malformed actions, and violations of feedback that the model has just seen. These diagnostics motivate a training recipe organized around three steps: acquire broad game participation through supervised fine-tuning, repair mechanically verifiable failures within one targeted dialogue-game family using turn-local preference pairs, and preserve general capabilities beyond these dialogue games. In the official final evaluation, our submission improves public clemscore from 10.67 to 38.92 and closed in-domain score from 13.41 to 41.17, while approximately preserving aggregate static performance (44.14 vs. 44.24 for the baseline). Out-of-domain clemscore remains low at 7.88, with the largest gains concentrated in unseen variants of the targeted family. Our results suggest that broad SFT brings most of the model's capability improvement; turn-local supervision can be effective when failure detection is precise, with observed transfer concentrated primarily within-family. --- ### ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning for 3D Chest CT Authors: Huseyin Umut Isik, Mehmet Alp Ozaydin, Sila Kurugol, Şeyda Ertekin Published: 2026-08-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.28455v1 Contrastive vision-language learning uses paired chest CT volumes and radiology reports to learn abnormality classifiers without manually annotated labels. However, two characteristics of chest CT challenge conventional global contrastive learning. First, many critical abnormalities are small or anatomically localized, and pooling an en- tire volume into a single embedding may dilute their visual evidence. Second, the standard contrastive objective treats every other scan in a batch as a negative. Because many chest CTs share abnormalities, this objective incorrectly pushes co-positive pairs apart. We propose Anatomy-Routed Contrastive Learning for 3D Chest CT (ARC-CT), a region-aware framework that addresses these limitations using only la- bels extracted from reports by an LLM, with no manual annotations or bounding boxes. ARC-CT combines three components: (1) an Anato- myQFormer localizing evidence via queries constrained by automatically generated organ masks; (2) a label-Jaccard soft InfoNCE objective in- tegrating the standard one-hot target with the label-set overlap of each pair, which reduces false-negative penalties between studies that share clinical findings; and (3) an organ-level alignment loss connecting mask- pooled visual features to organ-specific report text extracted offline with a large language model. ARC-CT achieves a 0.86 mask-free macro AUC across 18 abnormalities using a compact 3D ResNet-18 backbone. Over- all, ARC-CT outperforms both comparable efficient baselines and sev- eral larger transformer models. Our code and weights are available at https://github.com/arc-ct/arc-ct. --- ### Prompt-Guided Interactive Segmentation of Interstitial Lung Disease in Thoracic CT Authors: Vasilis Dedousis, Lubnaa Abdur Rahman, Lorenzo Brigatο, Ethan Dack, Andreas Christe, Christoph Frank, Manuela Funke-Chambour, Justus Roos, Adrian Huber, Lukas Ebner, Stavroula Mougiakakou Published: 2026-08-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28453v1 Accurate segmentation of interstitial lung disease (ILD) patterns is essential for quantitative disease assessment and longitudinal monitoring. However, existing approaches remain limited by relying on dense annotations and producing static predictions that cannot be refined, motivating interactive approaches. While promptable models show promise in interactive segmentation, their adaptation to ILDs remains largely unexplored. To address this gap, we investigate prompt-guided foundation models for ILD refinement and present, to the best of our knowledge, the first adaptation of MedSAM2 for interactive 3D ILD segmentation on thoracic CT. We investigate three fine-tuning strategies and multiple clinically motivated prompts: bounding-boxes (BBox), point, lasso, and scribble. On a dataset spanning seven ILD patterns and healthy lung tissue, full model fine-tuning performed best, improving the average Dice score by 4.7 percentage points over MedSAM2.While BBox prompts achieve the strongest performance, non-native MedSAM2 interactions such as lasso and scribble prompts also prove effective. Finally, we present and evaluate a proof-of-concept end-to-end workflow in which MedSAM2 is initialized from an automatic segmentation prior and subsequently refined using radiologist prompts. Model weights and plug-ins made available at: https://github.com/AIHNlab/ILD-SemiSegTool. --- ### Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning Authors: Minghui Xu, Zi Wang Published: 2026-08-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28447v1 Current large language models (LLMs) increasingly benefit from external tool integration, especially for tasks requiring reliable computation and verification. Motivated by this, we study calculator tool calling for improving mathematical reasoning on the Countdown task. We first analyze reasoning failures and find that calculation errors account for a substantial portion of incorrect responses. We then construct supervised fine-tuning datasets to teach the model useful tool-use patterns and how to interpret returned outputs. Building on this tool-formatted policy, we apply several on-policy reinforcement learning methods, including RLOO, RLOO++, GRPO, and DAPO, using automatically verifiable final-answer rewards. To enable a more reliable evaluation, we construct a fresh 1,024-problem held-out Countdown benchmark with no exact overlap with the training data. Our results show that calculator tool integration consistently improves both SFT and RL baselines, yielding roughly 10 percentage-point gains across pass@k. Among the RL methods, Tool-DAPO achieves the strongest performance, improving pass@1 from 35.8% for Tool-SFT to 66.0%. Further analysis shows that RL encourages more effective tool use even when only final-answer rewards are provided. These findings suggest that tool integration reduces arithmetic and verification errors, while RL increases the probability of correct reasoning traces. --- ### Generalized Splines and Gaussian Processes Authors: Michael Unser Published: 2026-08-28 Categories: math.ST, cs.LG, math.FA, stat.ML arXiv: https://arxiv.org/abs/2608.28446v1 For finite-dimensional linear inverse problems where the variables are Gaussian, it is well-known that the minimum-mean-square error estimator takes the form of a regularized least-squares data fit. In this chapter, we show that this equivalence extends to a much broader infinite-dimensional setting where generalized splines take the role of linear regressors and generalized Gaussian processes on a nuclear space $S$ are the counterpart of Gaussian random vectors. The scope of this extension is of the same nature as the switch from the classic notion of function to that of a distribution, also known as a "generalized function." Our formalism involves a whitening/regularization operator $L: S\to S'$ whose continuous extension induces a native Hilbert space $H\subset S'$ that plays a central role in our characterization. The presentation is self-contained for the most part and remarkably general and powerful. It allows for the recovery of all known instances of such equivalences; in particular, the methods involving innovations and reproducing-kernel Hilbert spaces developed by Kailath and his students, and the mathematical correspondence between fractional splines and Mandelbrot's fractional Brownian motion (fractals), with the former being the optimal estimators of the latter. It also covers general Bayesian methods for the resolution of infinite-dimensional inverse problems. --- ### Sliding-window beats linear attention Authors: Alexia Jolicoeur-Martineau, Rhea Sanjay Sukthanker, Pashmina Cameron, Emy Gervais Published: 2026-08-28 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.28444v1 Due to the nature of quadratic attention, Large Language Models (LLMs) consume a lot of memory and energy. Every new token costs more than the previous one. For each additional token, the keys and values must be stored in memory indefinitely, which is unsustainable. Several alternatives have been proposed to fix the quadratic scaling problem, one of which is retrofitting LLMs to use Linear Attention. This idea has attracted a lot of attention, given its promise to solve the quadratic scaling problem with state-of-the-art performance at low cost. However, this line of research has not been properly compared to simpler baselines. In this work, we show that Sliding Window Attention (SWA) with sinks performs as well or better than post-trained Linear Attention models. We observe this across multiple LLMs on various downstream tasks. For long-context reasoning tasks (Needle-in-a-Haystack and BABILong), SWA achieves massively higher performance (2 to 10 times higher than linear attention). SWA requires no post-training, is extremely fast, and requires low memory; therefore, making it an extremely cheap and reliable solution. To reduce inference memory cost, we strongly recommend switching to SWA instead of post-training linear models. Linear attention models may have shown some promise, but they likely require to be trained from scratch or extensive post-training in order to even match SWA. --- ### Curvature-Conditioned Multiscale Momentum with Sphere Constraints for LLM Pretraining Authors: Shuchen Zhu, Yuxin Fang, Mingze Wang, Kun Yuan Published: 2026-08-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.28442v1 Pretraining accounts for a large fraction of the total computational cost in LLM training. However, noise-dominant gradients and the highly ill-conditioned loss landscape bring severe challenges. Although modern adaptive optimizers such as AdamW and Muon have achieved great success in large-scale pretraining, their reliance on gradient normalization offers limited mitigation of the ill-conditioned curvature. The progress along flat directions (eigen-directions of small eigenvalues), which dominates the final loss reduction, remains relatively slow. To enhance training dynamics along flat directions, we propose a curvature-conditioned multiscale momentum method with sphere constraints, delivering steady acceleration in LLM pretraining. This multiscale momentum, applied only along flat directions, pairs a slow-decay component for noise reduction with a fast-decay component for rapid curvature adaptation, harnessing their complementary strengths. Crucially, we employ a sphere constraint technique to prevent parameter inflation and excessively rapid effective learning rate decay that would otherwise arise from a naive combination. Extensive experiments show that the proposed method significantly accelerates Muon across diverse architectures (dense, MoE) and model sizes (0.12B--2.3B parameters). Theoretically, we verify the acceleration effect and provide insight into the design principles underlying the flat-direction multiscale momentum. --- ### Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction Authors: Qing Ye, Meng-Hsuan Lin Published: 2026-08-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.28439v1 One model passed our fidelity check without ever opening the datasheet. We found it while qualifying models for an internal extraction service: a structured-output constraint had silently disabled tool use, and the model answered anyway, with fabricated source text. Only the per-tool trace exposed it. Fidelity -- whether an extracted value matches the source -- is the standard measure for agentic document extraction, and it scores that run a success. We therefore log every tool call in an agentic benchmark of 25 hand-curated claims over three components, with 12 more on a fourth, 37 in all. From that dispatch record we build two instruments: a rule-based failure-attribution classifier, and a silent-failure detector whose two rules check only which tools were called, never the extracted value. The detector raises no flag on 207 clean fidelity-passing extractions across three model families, and recovers all 50 planted faults that withhold exactly the tools its rules check. The two results are not symmetric: the first bounds the false-positive rate, the second is recall by construction, and detection power against runs that call their tools and still answer wrongly is unmeasured. A second, independent oracle, a causal chamber that tests whether the datasheet's claims hold under physical measurement, is intentionally partial: it confirms only what the apparatus can exercise, a verifiable envelope of 2 of those 37 claims, and we give a taxonomy of why the rest are not physically gradable. Under a controlled perturbation, fidelity passes throughout while the chamber verdict flips exactly at the measurement uncertainty. Across three deployed model stacks (one destabilised by its serving stack, not by any capability gap) the tool layer buys portability and observability rather than accuracy, and earns its premium only once a document outgrows the context window. --- ### Prove2Me: An Open Collaborative Platform for Scaling Math Formalization Authors: Shuze Chen, Kunal Marwaha, Xiaoyang Lu, Henry Yuen, Tianyi Peng Published: 2026-08-28 Categories: cs.AI, cs.LO, cs.MA arXiv: https://arxiv.org/abs/2608.28433v2 Proof assistants such as Lean 4 promise the paradigm of formally verified mathematics, but large-scale formalization projects have faced major barriers to entry, including the need for expertise in formal verification (as well as the underlying mathematics) and the significant time required for writing formal proofs. AI coding agents have dramatically reduced these barriers; human users can now use natural language to prompt agents to write complex proofs in Lean. This opens up the intriguing possibility of internet-scale mathematical collaboration involving both humans and AI agents, where correctness is machine-checked. To realize this possibility, we introduce Prove2Me (https://prove2.me), an open collaborative platform for formalizing mathematics. Users launch formalization "missions", to which AI agents contribute formal proofs toward completion. We designed mechanisms and a specialized harness in Prove2Me that enable large-scale collaboration so that agents can build on one another's work and freely reuse existing results. In doing so, Prove2Me aims to turn math formalization into a scalable, crowd-sourced effort open to anyone with an agent. --- ### Prove2Me: An Open Collaborative Platform for Scaling Math Formalization Authors: Shuze Chen, Kunal Marwaha, Xiaoyang Lu, Henry Yuen, Tianyi Peng Published: 2026-08-28 Categories: cs.AI, cs.LO, cs.MA arXiv: https://arxiv.org/abs/2608.28433v1 Proof assistants such as Lean 4 promise the paradigm of formally verified mathematics, but large-scale formalization projects have faced major barriers to entry, including the need for expertise in formal verification (as well as the underlying mathematics) and the significant time required for writing formal proofs. AI coding agents have dramatically reduced these barriers; human users can now use natural language to prompt agents to write complex proofs in Lean. This opens up the intriguing possibility of internet-scale mathematical collaboration involving both humans and AI agents, where correctness is machine-checked. To realize this possibility, we introduce Prove2Me (https://prove2.me), an open collaborative platform for formalizing mathematics. Users launch formalization "missions", to which AI agents contribute formal proofs toward completion. We designed mechanisms and a specialized harness in Prove2Me that enable large-scale collaboration so that agents can build on one another's work and freely reuse existing results. In doing so, Prove2Me aims to turn math formalization into a scalable, crowd-sourced effort open to anyone with an agent. --- ### Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQL Authors: Jiayan Lin, Yujia Liu, Zijin Hong, Zheng Yuan, Yilin Xiao, Hao Chen, Qinggang Zhang, Xiao Huang, Feiran Huang Published: 2026-08-28 Categories: cs.CL, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2608.28432v1 Recent advances in in-context learning (ICL) text-to-SQL have substantially improved execution accuracy on public benchmarks by assembling increasingly elaborate pipelines around the base generator, yet existing studies typically report aggregate end-to-end accuracy, without quantifying the marginal accuracy-cost contribution of individual design choices. Consequently, providing a unified, paradigm-level cost-accuracy quantification remains a critical challenge for understanding and configuring modern text-to-SQL. To address this, we instantiate 17 paradigm-level configurations across five recurring modules of the ICL text-to-SQL pipeline under a single controlled implementation, and attribute each paradigm's marginal contribution and incurred cost across all four backbones spanning diverse capability levels and reasoning styles. Our analysis reveals that execution-feedback refinement is the only paradigm whose benefit holds universally at consistently low cost, while most other modules help only under backbone-dependent conditions. Token accounting shows that input demand is more closely tied to pipeline structure, whereas output demand is more sensitive to backbone generation behavior. Cross-module analysis further shows that stacking improves accuracy on most backbones, although how the gains compose varies with backbone capability. We also find that a fixed budget is often better spent engineering a more elaborate pipeline over a mid-tier backbone than upgrading to a frontier model with a lean pipeline. These findings distill into an actionable, cost-aware tiered guideline that transfers to five additional backbones without per-paradigm search. --- ### Lossy Event Compression: From Event Stream Distortion to Task Performance Authors: Zahra Rezaee, Catarina Brites, João Ascenso Published: 2026-08-28 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2608.28429v1 Event cameras generate asynchronous, sparse data streams with microsecond temporal resolution, but in moderate-to-high motion scenes they can produce as many as hundreds of millions of events per second, creating significant bandwidth and storage challenges. Lossy compression is therefore essential for practical deployment, yet existing event stream distortion metrics fail to reliably predict compression-induced degradation at the task level, forcing codec optimization to rely on expensive task-specific evaluations. To address this gap, this paper introduces two fundamentally different event compression pipelines: i) an aggregation-based pipeline that converts the event stream into polarity-based histogram frames for compression with the conventional image codec JPEG 2000, and ii) a frame-free point cloud-based pipeline that codes events natively as 3D points using the octree-based codec G-PCC. Both pipelines are then assessed within a unified task-driven evaluation framework that relates event stream distortion to downstream application performance across four representative tasks: i) video reconstruction, ii) object detection, iii) optical flow estimation, and a delay-sensitive task iv) asynchronous feature tracking under a reference-relative protocol. Building on this framework, five classification-based distortion metrics are applied to event compression for the first time, to the best of the authors' knowledge, and benchmarked against existing event stream metrics. Experimental results demonstrate that the proposed metrics reliably predict compression-induced task degradation across different coding frameworks. This demonstrates that event stream distortion assessment can be an efficient alternative to repeated task-specific evaluation, providing direct guidance for the development and optimization of future event data coding solutions. --- ### Euclidean Fourier Neural Operators Authors: Nathanael Bosch, Niklas Frederik Schmitz, Michael F. Herbst Published: 2026-08-28 Categories: cs.LG, cond-mat.mtrl-sci, physics.comp-ph arXiv: https://arxiv.org/abs/2608.28425v2 Fourier neural operators (FNOs) provide an efficient framework for learning mappings between function spaces as they are, by construction, independent of the grid resolution at which they are trained and evaluated. However, FNOs are not independent of the periodic domain they are applied to: their discrete spectral weights are indexed by integer Fourier mode numbers, which correspond to physical wavevectors. When applied to a different domain, the same trained weights act at different wavevectors, and the FNO silently represents a different operator. This makes FNOs unsuitable for tasks where transfer across domains is crucial. We propose Euclidean Fourier neural operators~(EFNOs) as a domain-independent alternative to FNOs. By parameterizing the spectral kernel as a continuous function of the physical wavevector, the EFNO can learn operators that act consistently across periodic domains of varying shape and size. We evaluate the EFNO on a simple heat equation and on a practically relevant materials science task of learning exchange-correlation potentials across different crystal structures, and demonstrate that the EFNO is able to generalize to unseen grid sizes and domains. --- ### Euclidean Fourier Neural Operators Authors: Nathanael Bosch, Niklas Frederik Schmitz, Michael F. Herbst Published: 2026-08-28 Categories: cs.LG, cond-mat.mtrl-sci, physics.comp-ph arXiv: https://arxiv.org/abs/2608.28425v1 Fourier neural operators (FNOs) provide an efficient framework for learning mappings between function spaces as they are, by construction, independent of the grid resolution at which they are trained and evaluated. However, FNOs are not independent of the periodic domain they are applied to: their discrete spectral weights are indexed by integer Fourier mode numbers, which correspond to physical wavevectors. When applied to a different domain, the same trained weights act at different wavevectors, and the FNO silently represents a different operator. This makes FNOs unsuitable for tasks where transfer across domains is crucial. We propose Euclidean Fourier neural operators~(EFNOs) as a domain-independent alternative to FNOs. By parameterizing the spectral kernel as a continuous function of the physical wavevector, the EFNO can learn operators that act consistently across periodic domains of varying shape and size. We evaluate the EFNO on a simple heat equation and on a practically relevant materials science task of learning exchange-correlation potentials across different crystal structures, and demonstrate that the EFNO is able to generalize to unseen grid sizes and domains. --- ### Program Learning with Verifiable Rewards: Symbolic Backpropagation for Post-Training LLMs Authors: Vishvesh Bhat Published: 2026-08-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28421v1 Post training a language model to reason means updating its weights. Supervised finetuning and reinforcement learning both place the acquired capability inside the model where it cannot be inspected cannot be checked step by step and cannot be moved to another model. We argue that for tasks whose intermediate steps admit verification, reasoning is better placed outside the base models weights as an explicit program composed from deterministic and neural primitives. We introduce PLVR (Program Learning with Verifiable Rewards): a post training method that learns such programs directly from input-output examples. Its mechanism is symbolic backpropagation: each program layer carries a typed ontology a loss is computed at the output against ground truth and required input ontologies are propagated backward by type inference over primitive signatures: an analogue of the chain rule in which credit assignment is a derivation rather than an estimate. Where RLVR verifies a terminal outcome, PLVRs reward is a per step contract verdict dense over program structure. On LiveCodeBench v6 and Tau2Bench, 30B base models with PLVR outperform RL at matched budget by 27.8 points on average and frontier models an order of magnitude larger by 13.6 points. A single primitive library serves two benchmarks, so the marginal cost of a new task is 100 examples of program search and no new finetuning data. Replacing the loss guided search with uniform sampling over the same type admissible space at equal budget collapses the median program from 65.6 to 17.5, identifying the backward pass rather than the type system as the source of the advantage. We release the symbolic backpropagation library and a conformance checker so the method can be applied to primitive libraries other than our own. --- ### LongPIBench: A Long-Context Benchmark for Prompt Injection Authors: Yupei Liu, Yuqi Jia, Neil Zhenqiang Gong, Jinyuan Jia Published: 2026-08-28 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.28411v1 Prompt injection attacks pose a serious security risk to large language models in real-world applications. However, existing prompt injection benchmarks primarily focus on short-context inputs, leaving the attacks and defenses in long-context settings largely unexplored. This gap leads to a substantial overestimation of the effectiveness of current defenses. In this paper, we bridge the gap by introducing LongPIBench, a long-context benchmark for prompt injection covering 4 realistic application scenarios: paper peer review, resume screening, code review, and email summary. For each scenario, we construct a synthetic dataset and a real-world dataset, with context lengths ranging from thousands to tens of thousands of tokens. The evaluation results on LongPIBench reveal significant vulnerabilities of prompt injection defenses under long-context settings: even simple heuristic prompt injection attacks achieve high success rates and frequently bypass state-of-the-art defenses. We hope LongPIBench can serve as a practical benchmark for systematically evaluating prompt injection defenses in realistic long-context scenarios. --- ### SymboLLM-FE: LLM-Accelerated Symbolic Regression for Automated Feature Engineering on Tabular Data Authors: Zi-Jian Cheng, Zi-Yi Jia, Zhi Zhou, Yu-Feng Li, Lan-Zhe Guo Published: 2026-08-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.28408v1 Tabular data, as a core data format in machine learning, often lacks the discriminative power needed for high-performance modeling due to insufficient feature informativeness. Automated Feature Engineering (AutoFE) overcomes this by automating feature generation and selection, ensuring both model performance and operational efficiency. However, traditional AutoFE often yield features with poor interpretability because they rely on blind mathematical transformations, while large language models (LLM)-based AutoFE faces challenges in requiring costly multi-round iterations to generate high-utility features to effectively enhance model performance, compounded by inherent risks of bias and hallucination. In this paper, we combine symbolic regression with LLMs for feature engineering (SymboLLM-FE) to solve these challenges. We extract mathematically expressive formulas strongly correlated with the target via symbolic regression, which can enhance model performance, then refine them by LLMs with rich prior knowledge to ensure interpretability. Empirical results on six real-world datasets and four Kaggle competitions demonstrate that SymboLLM-FE outperforms existing AutoFE. SymboLLM-FE also addresses the dual challenges of poor interpretability and numerous iterations by employing a statistical prior-grounded LLM refinement mechanism and single-digit LLM calls. --- ### A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring Authors: Shihang Yang, Sanwoo Lee, Ningning Zhao, Yunfang Wu Published: 2026-08-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.28407v1 Multi-trait Automated Essay Scoring (AES) requires rubric-grounded reasoning across interdependent traits, rather than isolated score prediction. Existing feedback-enhanced methods often decouple feedback from scoring or assess traits independently, weakening score--feedback consistency and rubric alignment. We propose HiFTS, a unified autoregressive framework that generates hierarchical CoT feedback before predicting trait-level and holistic scores. HiFTS distills rubric-grounded hierarchical CoT feedback from a teacher LLM and trains student models to jointly generate feedback and scores. HiFTS further applies Group Relative Policy Optimization with a composite reward balancing score agreement, calibration, feedback quality, and structural validity. At inference, a lightweight global prior provides holistic guidance to reduce drift during long-form reasoning. We also introduce CFMS-34, a Chinese multi-trait AES dataset with 951 essays annotated with holistic scores and 34 rubric-based traits. Experiments on CFMS-34 and ASAP++ show that HiFTS achieves strong holistic and trait-level scoring while producing coherent, rubric-aligned feedback. --- ### Post-Training VLMs for Video Mistake Detection Authors: Federico Spurio, Olga Zatsarynna, Lars Doorenbos, Emad Bahrami, Gianpiero Francesca, Juergen Gall Published: 2026-08-28 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.28406v1 Human mistakes are inevitable when following instructions, yet they can lead to severe consequences. As such, there has been an increased interest in developing methods for detecting mistakes in videos, with current methods mostly focusing on closed-set protocols. While successful in controlled settings, the closed-set assumption limits their wider applicability, as any changes to the task require collecting new data and re-training models. Instead, we argue that mistake detection methods should learn the general concept of a mistake, rather than overfitting to step-specific details. To reflect this, we introduce the Mistake Detection Video Question Answering (MD-VQA) protocol and accompanying benchmark. MD-VQA tests whether methods can discern if a step was executed correctly with respect to its description, for both seen and unseen actions. To address this important challenge, we propose the first video-language-model post-training technique for mistake detection. Our method uses a tailored reward function to encourage the model to identify discrepancies between an instruction and the corresponding video. Extensive evaluations demonstrate that this approach outperforms zero-shot, supervised fine-tuning, and post-training baselines. Notably, our method generalizes especially well to unseen procedures, for instance, with an improvement of up to 11.6% over the best-performing baseline on EP-VQA, paving the way toward general mistake detection. We release our code and benchmark at https://github.com/FedeSpu/mstk. --- ### CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia Authors: Bryan Chen Zhengyu Tan, Weihua Zheng, Thong T. Doan, Bich Ngoc Doan, Jia Wang Peh, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen, Zhengyuan Liu, JinYeong Bak, Wafi Shamdi et al. Published: 2026-08-28 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2608.28405v2 Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common use case: users seeking practical help over multiple turns in culturally grounded scenarios. We introduce CultureConverse, a scalable, multilingual simulation and evaluation harness for culturally grounded assistant dialogue that covers 10 East and Southeast Asian regions, 58 subgroup identities, and 7 domains. Each simulated and evaluated episode produces a scored interaction where the assistant assists the user and infers cultural constraints from partial information. The resulting CultureConverse-DS dataset contains 14,610 benchmark (evaluation) episodes and 274,295 oracle-guided (gold-mode) dialogues. In our benchmark evaluation of 18 models, GPT-5 mini achieves the highest assistance quality. Human annotation experiments suggest that our evaluation framework is a sufficient proxy for human judgment. Performance gains from fine-tuning on 27,860 high-quality CultureConverse-DS samples improve in-domain assistance and transfer out-of-domain to cultural MCQ and safety classification benchmarks. We release the harness, both splits, and judge prompts to support interactive evaluation of cultural competency. --- ### CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia Authors: Bryan Chen Zhengyu Tan, Weihua Zheng, Thong T. Doan, Bich Ngoc Doan, Jia Wang Peh, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen, Zhengyuan Liu, JinYeong Bak, Wafi Shamdi et al. Published: 2026-08-28 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2608.28405v1 Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common use case: users seeking practical help over multiple turns in culturally grounded scenarios. We introduce CultureConverse, a scalable, multilingual simulation and evaluation harness for culturally grounded assistant dialogue that covers 10 East and Southeast Asian regions, 58 subgroup identities, and 7 domains. Each simulated and evaluated episode produces a scored interaction where the assistant assists the user and infers cultural constraints from partial information. The resulting CultureConverse-DS dataset contains 14,610 benchmark (evaluation) episodes and 274,295 oracle-guided (gold-mode) dialogues. In our benchmark evaluation of 18 models, GPT-5 mini achieves the highest assistance quality. Human annotation experiments suggest that our evaluation framework is a sufficient proxy for human judgment. Performance gains from fine-tuning on 27,860 high-quality CultureConverse-DS samples improve in-domain assistance and transfer out-of-domain to cultural MCQ and safety classification benchmarks. We release the harness, both splits, and judge prompts to support interactive evaluation of cultural competency. --- ### How Far Can 5,500 Hours of Driving Take You? A Scaling Law Analysis of Video Diffusion Models Authors: Victor Besnier, Anh-Quan Cao, Elias Ramzi, Spyros Gidaris, Tuan-Hung Vu, Andrei Bursuc, Eloi Zablocki, Matthieu Cord Published: 2026-08-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28404v2 Video generation for autonomous driving cannot follow the web-scale route: driving data is expensive to collect, bound by privacy requirements, and cannot be scraped at will, so models must make the most of a fixed corpus. We present a systematic scaling-law study of video diffusion models trained from scratch on driving data: a family of models from 1M to 9B parameters, trained at different exposures on up to 5,500 hours of driving. Validation loss follows consistent power laws in both model size and training exposure, answering the questions that shape a training budget: whether compute is better spent on longer training or on a larger model, and whether more data is needed. Loss improves much faster with training exposure than with model size, making longer training the most effective way to improve a fixed model under limited compute. However, larger models continue to achieve lower asymptotic loss, so compute-optimal scaling still favors increasing model size when sufficient compute and data are available. Guided by these laws, we train a 9B-parameter model, to our knowledge the largest video diffusion model trained from scratch on driving data: it sets a new open-source state of the art for driving video generation, as measured on nuScenes. Our code and pretrained models are available at https://github.com/valeoai/VATIX. NATIX is separately releasing the underlying driving data in stages. --- ### How Far Can 5,500 Hours of Driving Take You? A Scaling Law Analysis of Video Diffusion Models Authors: Victor Besnier, Anh-Quan Cao, Elias Ramzi, Spyros Gidaris, Tuan-Hung Vu, Andrei Bursuc, Eloi Zablocki, Matthieu Cord Published: 2026-08-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28404v1 Video generation for autonomous driving cannot follow the web-scale route: driving data is expensive to collect, bound by privacy requirements, and cannot be scraped at will, so models must make the most of a fixed corpus. We present a systematic scaling-law study of video diffusion models trained from scratch on driving data: a family of models from 1M to 9B parameters, trained at different exposures on up to 5,500 hours of driving. Validation loss follows consistent power laws in both model size and training exposure, answering the questions that shape a training budget: whether compute is better spent on longer training or on a larger model, and whether more data is needed. Loss improves much faster with training exposure than with model size, making longer training the most effective way to improve a fixed model under limited compute. However, larger models continue to achieve lower asymptotic loss, so compute-optimal scaling still favors increasing model size when sufficient compute and data are available. Guided by these laws, we train a 9B-parameter model, to our knowledge the largest video diffusion model trained from scratch on driving data: it sets a new open-source state of the art for driving video generation, as measured on nuScenes. Our code and pretrained models are available at https://github.com/valeoai/VATIX. NATIX is separately releasing the underlying driving data in stages. --- ### VERA-8B: Evidence-Grounded Audit Risk Reasoning from SEC Filings Authors: Menghan Liu, Elynn Chen Published: 2026-08-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28402v1 Across audit applications, judgments must be supported by reasonable evidence. However, standard financial language models prioritize fluency over evidence. They are built for general financial reasoning and may produce plausible but ambiguous answers, creating a grounding gap that makes them unsuitable for audit work. We address this gap with VERA-8B, a new end-to-end audit reasoning system that identifies audit risks before enforcement actions occur. Constructing such a model raises several challenges, as no prior machine learning work targets pre-enforcement audit prediction. To our knowledge, we are the first to unify SFT and GRPO for evidence-grounded audit reasoning under one evidence standard, achieving performance that surpasses all evaluated baselines. Because auditing cannot tolerate unsupported claims, we introduce abstention and uncertainty qualification to defer uncertain or evidence-incomplete cases. Finally, we design an AuditBridge to ground model reasoning for practical audit work. It transforms raw filings into verified records and then into reviewer-ready reports, bridging finance and computation with broad generality. Together, these components produce auditable, review-ready outputs suitable for practical audit work. --- ### RetailAgent: Structured Adverse Timing in Self-Conditioned Multimodal LLM Trading Agents Authors: Yupeng Zhang, Liuyuan Jiang, Hongyi Huang, Bingheng Li, Lisha Chen Published: 2026-08-28 Categories: cs.AI, q-fin.TR arXiv: https://arxiv.org/abs/2608.28399v1 In financial markets, a sequential policy that reacts systematically to price movements may become predictable to other market participants. This paper studies whether large language model (LLM) agents exhibit such directional structure through RetailAgent, an experimental framework in which an LLM observes anonymized intraday equity price histories and permitted state, then repeatedly chooses long (hold the stock) or flat (stay out) before the subsequent interval return is revealed. We compare returns during long and flat intervals along the same stock's intraday path after removing the overall fraction of long decisions. This exposure-matched measure reveals persistent negative timing across modality, horizon, state, and model family. Shuffling saved action sequences substantially attenuates the effect, showing that alignment between actions and subsequent returns drives the negative score. Feeding self-authored memories into decisions further increases policy persistence, while timing becomes more negative among stock-days on which the agent uses both actions. These results reveal stable, recoverable directional structure in sequential LLM financial decisions and a behavioral signal for studying how another participant could respond to a predictable policy. --- ### BEACON: Behavior-Anchored Cross-Source Knowledge Graph Construction for Cyber Threat Intelligence Authors: Changze Li, Yutong Cheng, Tsania Camila Finnisa, Qian Cui, Wei Ding, Peng Gao Published: 2026-08-28 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2608.28394v1 Cyber threat intelligence (CTI) is foundational to modern cyber defense, yet much of it resides in unstructured reports whose volume and heterogeneity far exceed manual analysis, motivating research on automatically constructing knowledge graphs from CTI reports. However, existing approaches mainly extract partial information within a single report, leaving the cross-source setting unexplored, where the same threat is given unrelated names. Our key insight is that attack behaviors, once mapped to MITRE ATT&CK (a standardized catalog of attack techniques), can anchor the rest of a report. Attack behaviors are the adversarial actions a report describes, while contextual entities (e.g., threat actors, campaigns, and affected products) and Indicators of Compromise (IoCs; e.g., IP addresses) are their participants and traces. Attaching them to these anchors places every per-report graph in one canonical space. We realize this insight in BEACON, an LLM-driven framework for cross-source CTI knowledge graph construction. Its first stage extracts each report into a graph under a propose-then-verify paradigm, grounding candidates in report evidence and official ATT&CK definitions, to suppress LLM misclassification and hallucination. Its second stage merges these graphs with a hierarchical alignment strategy that applies signals in decreasing order of determinism, from character-level and semantic similarity to overlapping technique neighborhoods, iterating as merges pool neighborhoods. No existing benchmark links entities to technique anchors or provides cross-source alignment ground truth. We therefore construct and release two human-annotated datasets from 34 sources: to our knowledge the largest for report-level CTI extraction (8,395 elements) and the first for cross-source consolidation (3,487). On them, BEACON outperforms all baselines by at least 23% and 9%, respectively. --- ### Timing-Aware Repurchase Prediction for Web-Scale E-Commerce: Survival Models for Multi-Surface Grocery Recommendation Authors: Akshay Kekuda, Shreeranjani Srirangamsridharan, Ishan Bhatt, Yanan Cao, Sinduja Subramaniam, Evren Korpeoglu, Kaushiki Nag, Kannan Achan Published: 2026-08-28 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.28393v2 Repurchase recommenders in e-commerce are commonly framed as a binary question asking "will this customer buy this item within W days", a formulation that requires a separately trained model for every horizon of interest. We replace this stack with survival models that predict time-to-repurchase directly, and evaluate them on millions of customers from a major grocery e-commerce platform across more than thirty ablation configurations. Our study makes three contributions. First, an empirical hazard analysis reveals a slightly decreasing marginal hazard (k ~ 0.9), differing from the common intuition that grocery items become more likely to be repurchased the longer since the last purchase (increasing hazard, k > 1). Log-Normal achieves the best marginal fit (R^2 = 0.998) and the best ranking, despite Weibull providing the best conditional residual fit, revealing an apparent discrepancy we analyze in detail. Second, a single Accelerated Failure Time (AFT) model replaces three per-horizon binary classifiers, matching or exceeding each at its own horizon while using roughly 3x fewer total trees. Feature importance reshuffles under the survival objective: channel-cadence and recency signals rise while aggregate frequency counts fall. Third, a 4-parameter parametric calibration maps raw survival CDFs to per-horizon probabilities with zero cross-horizon monotonicity violations. Calibration quality varies by an order of magnitude across the AFT family: Exponential AFT (Weibull k=1) achieves expected calibration error (ECE) ~1e-4, roughly 10x lower than Log-Normal, while ranking metrics agree within 0.3% relative. We adopt Exponential AFT for probability-consuming surfaces and Log-Normal for pure ranking, exposing a principled calibration-ranking trade-off within a single AFT family. --- ### Timing-Aware Repurchase Prediction for Web-Scale E-Commerce: Survival Models for Multi-Surface Grocery Recommendation Authors: Akshay Kekuda, Shreeranjani Srirangamsridharan, Ishan Bhatt, Yanan Cao, Sinduja Subramaniam, Evren Korpeoglu, Kaushiki Nag, Kannan Achan Published: 2026-08-28 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.28393v1 Repurchase recommenders in e-commerce are commonly framed as a binary question asking "will this customer buy this item within W days", a formulation that requires a separately trained model for every horizon of interest. We replace this stack with survival models that predict time-to-repurchase directly, and evaluate them on millions of customers from a major grocery e-commerce platform across more than thirty ablation configurations. Our study makes three contributions. First, an empirical hazard analysis reveals a slightly decreasing marginal hazard (k ~ 0.9), differing from the common intuition that grocery items become more likely to be repurchased the longer since the last purchase (increasing hazard, k > 1). Log-Normal achieves the best marginal fit (R^2 = 0.998) and the best ranking, despite Weibull providing the best conditional residual fit, revealing an apparent discrepancy we analyze in detail. Second, a single Accelerated Failure Time (AFT) model replaces three per-horizon binary classifiers, matching or exceeding each at its own horizon while using roughly 3x fewer total trees. Feature importance reshuffles under the survival objective: channel-cadence and recency signals rise while aggregate frequency counts fall. Third, a 4-parameter parametric calibration maps raw survival CDFs to per-horizon probabilities with zero cross-horizon monotonicity violations. Calibration quality varies by an order of magnitude across the AFT family: Exponential AFT (Weibull k=1) achieves expected calibration error (ECE) ~1e-4, roughly 10x lower than Log-Normal, while ranking metrics agree within 0.3% relative. We adopt Exponential AFT for probability-consuming surfaces and Log-Normal for pure ranking, exposing a principled calibration-ranking trade-off within a single AFT family. --- ### CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents Authors: Jaewon Jung, Haizhong Zheng, Hongsun Jang, Jaeyong Song, Beidi Chen, Jinho Lee Published: 2026-08-28 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2608.28389v1 Retrieval-augmented generation (RAG) augments LLMs with external documents, but public or user-editable sources expose RAG systems to data poisoning: attackers can inject malicious documents to steer outputs toward targeted answers. Existing poisoning attacks often rely on query inclusion, inserting the target query into poisoned documents to improve retrieval; however, this creates lexical and embedding-space artifacts that make them easy to filter. We propose CamoDocs, a poisoning attack that avoids direct query inclusion by camouflaging adversarial documents among benign content. CamoDocs chunks synthesized benign and adversarial drafts, replaces selected tokens in benign chunks with dispersion tokens that spread poisoned-document embeddings, and applies coherence filtering to limit readability degradation. Across seven RAG defenses, three open-weight LLMs, and three benchmarks, CamoDocs achieves strong average ASR while avoiding query-overlap artifacts exploited by simple query detection. It also remains effective against proprietary models, achieving average ASRs of 61.80% on GPT-5.4-mini and 55.09% on Claude-Haiku-4.5. Finally, we show that erasure-heavy clustering defenses such as TrustRAG can reduce ASR, but only with substantial utility drops on retrieval-dependent benchmarks such as NeoQA. Code is available at https://github.com/jaewonalive/CamoDocs. --- ### GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image Authors: Semin Kim, Haechan Shin, Jongyoo Kim Published: 2026-08-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28386v2 Existing monocular full-body 3D human-object interaction (HOI) methods do not combine explicit finger-level grasp optimization with category-agnostic object reconstruction. Despite plausible body-object configurations, their fingers may float from or penetrate objects instead of forming a grasp. We present GraspHOI, the first framework that reconstructs a full-body 3D HOI from a single image while explicitly optimizing finger articulation against the reconstructed object. GraspHOI recovers object geometry directly, without predefined meshes or a fixed category vocabulary. It reconstructs the body, hands, and object separately, aligning them in metric camera space via depth-based registration and image-space alignment. Occlusion-aware palmar correspondences seat the object against the grasping hand, and contact-aware optimization refines arm and finger articulation to form surface contact without excessive penetration. Across four benchmarks and six baselines, GraspHOI improves relative human-object placement, hand accuracy, and contact plausibility. Full pipeline code will be released. --- ### GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image Authors: Semin Kim, Haechan Shin, Jongyoo Kim Published: 2026-08-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28386v1 Existing monocular full-body 3D human-object interaction (HOI) methods do not combine explicit finger-level grasp optimization with category-agnostic object reconstruction. Despite plausible body-object configurations, their fingers may float from or penetrate objects instead of forming a grasp. We present GraspHOI, the first framework that reconstructs a full-body 3D HOI from a single image while explicitly optimizing finger articulation against the reconstructed object. GraspHOI recovers object geometry directly, without predefined meshes or a fixed category vocabulary. It reconstructs the body, hands, and object separately, aligning them in metric camera space via depth-based registration and image-space alignment. Occlusion-aware palmar correspondences seat the object against the grasping hand, and contact-aware optimization refines arm and finger articulation to form surface contact without excessive penetration. Across four benchmarks and six baselines, GraspHOI improves relative human-object placement, hand accuracy, and contact plausibility. Full pipeline code will be released. --- ### MAP: A Benchmark on Multimodal Accessibility Planning for Real World Places Authors: Jason Armitage, Ioannis Tsochantaridis, Linda Mazzone, Chuqiao Yan, Srini Narayanan, Sarah Ebling Published: 2026-08-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28384v1 We introduce MAP, the first benchmark to evaluate multimodal AI systems as assistants for users with accessibility requirements when planning visits to places in the real world. In our evaluation, systems are presented with requests to verify or recommend a point of interest meeting an accessibility requirement. MAP contains two novel assessments: Claim verification for accessibility planning assesses if information on places and stated accessibility features is supported and identifies places that satisfy requested accessibility features. Visual evidence retrieval for accessibility planning checks if a multimodal AI system can select visual evidence for the requested place and accessibility feature. Our methodology supports comparison of AI systems in a setting where place information and accessibility information can change over time by evaluating systems and refreshing ground truth data at scheduled times. The benchmark is based on automatic rating and human rating for a proportion of responses. --- ### Semantic Head Specialization Guides Hybrid ViT Attention for Multimodal LLMs Authors: Chenhong He, Lei Li, Shicheng Li, Hanglong Lv, Lingpeng Kong, Qi Liu, Tong Yang, Shuhuai Ren Published: 2026-08-28 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2608.28383v1 Hybrid attention dominates frontier LLMs, yet Vision Transformers (ViTs) in multimodal LLMs lack a satisfactory hybrid design, with no consensus on why certain attention patterns work better. To fill this gap, we study ViT attention heads and find they differentiate into object- and background-specialist roles, a pattern most pronounced under full attention; we call this Semantic Head Specialization (SHS). We propose SHS-Index to quantify this specialization, show that it distinguishes full-attention from chunk-window ViTs, and find that it strongly tracks downstream benchmark performance. We then identify three structural factors that shape SHS---window interaction, token serialization, and local softmax allocation---and use them as design principles for hybrid attention. Guided by these factors, we design Ariadne Attention, a hybrid that matches full attention on 22 image and video tasks at 6.5x less attention compute. Our findings establish head specialization as a measurable property for diagnosing and designing principled hybrid ViT attention at the multimodal-LLM scale. --- ### When Linguistic and Internal Confidence Diverge in Large Language Models Authors: Hefan Zhang, Bingquan Zhang, Ming Cheng, Saeed Hassanpour, Weicheng Ma, Soroush Vosoughi Published: 2026-08-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.28382v2 Users often ask large language models (LLMs) to report how confident they are, but it is unclear whether such linguistic confidence tracks the model's internal confidence. We study this question across 8 classification tasks, 2 generation tasks and 30 models from three families. For classification, we compare linguistic confidence with logits-based confidence along three axes: association, magnitude agreement and calibration. For generation, we test whether linguistic confidence tracks semantic-entropy-based uncertainty. The axes frequently diverge. Instance-level association is weak on average, although it improves on easier items and for stronger base models. Instruction-tuned models often report higher confidence and sometimes show higher association, but they also have larger confidence gaps and worse calibration. Prompt design mostly changes the distribution of reported confidence. Attitude cues inflate confidence without improving alignment, while score exemplars can preserve rank-order signal when they avoid collapsed confidence values. Regression analyses show that distributional properties of confidence scores explain much of the observed alignment pattern, with model metadata playing a smaller role after controls. These results support a lossy-channel view of linguistic confidence. A more dispersed verbal confidence distribution can carry useful rank information, but it does not make the scores calibrated. Linguistic confidence should therefore be evaluated with multi-axis diagnostics before being used in downstream reliability pipelines. --- ### When Linguistic and Internal Confidence Diverge in Large Language Models Authors: Hefan Zhang, Bingquan Zhang, Ming Cheng, Saeed Hassanpour, Weicheng Ma, Soroush Vosoughi Published: 2026-08-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.28382v1 Users often ask large language models (LLMs) to report how confident they are, but it is unclear whether such linguistic confidence tracks the model's internal confidence. We study this question across 8 classification tasks, 2 generation tasks and 30 models from three families. For classification, we compare linguistic confidence with logits-based confidence along three axes: association, magnitude agreement and calibration. For generation, we test whether linguistic confidence tracks semantic-entropy-based uncertainty. The axes frequently diverge. Instance-level association is weak on average, although it improves on easier items and for stronger base models. Instruction-tuned models often report higher confidence and sometimes show higher association, but they also have larger confidence gaps and worse calibration. Prompt design mostly changes the distribution of reported confidence. Attitude cues inflate confidence without improving alignment, while score exemplars can preserve rank-order signal when they avoid collapsed confidence values. Regression analyses show that distributional properties of confidence scores explain much of the observed alignment pattern, with model metadata playing a smaller role after controls. These results support a lossy-channel view of linguistic confidence. A more dispersed verbal confidence distribution can carry useful rank information, but it does not make the scores calibrated. Linguistic confidence should therefore be evaluated with multi-axis diagnostics before being used in downstream reliability pipelines. --- ### Quantum Federated Learning Based on Bures--Uhlmann Geometry for Heterogeneous Noisy Clients Authors: Haruki Emori, Masaki Uchihara, Yuuki Tokunaga Published: 2026-08-28 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2608.28379v1 Quantum federated learning enables collaborative model training across quantum devices without sharing raw data, and it faces the data and hardware heterogeneity inherent to noisy quantum devices. Utilizing the quantum geometric tensor is a natural remedy, yet pure-state approaches and diagonal approximations discard the correlations that encode parameter incompatibility. To address this, we extend the parameter-space geometry to the mixed states that noisy clients actually prepare. The real part of the resulting mixed-state geometric tensor is the Bures metric, which measures how fast the physical state changes under parameter variation, and the imaginary part is the mean Uhlmann curvature, which quantifies the incompatibility of estimating multiple parameters simultaneously. Accordingly, we employ the Bures metric as a local preconditioner and use the mean Uhlmann curvature to develop an achievable-precision aggregation rule that dynamically down-weights unreliable clients. Furthermore, we establish theoretical guarantees by proving a convergence theorem and a variance-dominance proposition. Empirical evaluations on a trapped-ion quantum emulator demonstrate that the proposed method maintains high accuracy across diverse device-heterogeneity conditions and outperforms standard federated averaging, whose accuracy degrades under strong noise. --- ### PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems Authors: Hanglong Lv, Dawei Zhu, Lei Li, Bowen Ye, Huaqiu Liu, Yifan Song, Bofei Gao, Weimin Xiong, Jinhao Dong, Chenhong He, Lingpeng Kong, Qi Liu et al. Published: 2026-08-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.28378v1 Large language models are increasingly used as agentic workflow executors, yet existing training data and benchmarks largely assume informationally complete, single-turn queries. Our analysis of 16K real-world sessions shows that 75.9% of interactions are multi-turn, revealing a substantial gap between how users interact with agents and how such systems are trained and evaluated. We introduce \textbf{PersonaForge}, a user simulation framework for synthesizing realistic multi-turn user--agent interactions. PersonaForge combines a four-dimensional persona space, SOUL-driven behavioral control calibrated to real-user statistics, and Reverse Deep Construction grounded in authentic seed queries. Using PersonaForge, we construct a 6.3K-record training dataset and \textbf{PersonaForge-Bench}, a manually annotated 138-task benchmark spanning over 20 professional domains with four-dimensional scoring. Experiments on Qwen3.5-27B show that PersonaForge training improves the composite score by +4.1%, with gains across all four dimensions and the largest improvements in Task Completion (+6.0%) and Response Quality (+6.8%). Further analyses show that PersonaForge-trained agents use fewer turns and tool calls, suggesting improved interaction efficiency, while ablations confirm the contribution of SOUL components and adaptive simulation. Together, PersonaForge and PersonaForge-Bench establish a foundation for training and evaluating agents under realistic multi-turn user interaction. --- ### Localizing Global Discrepancies: Marginal Contributions and Contextual Anomaly Detection Authors: Tommaso dorigo Published: 2026-08-28 Categories: stat.ML, cs.LG, physics.data-an arXiv: https://arxiv.org/abs/2608.28375v1 Global goodness-of-fit and discrepancy statistics can establish that a sample departs from a reference distribution without identifying which observations drive the departure. We develop a framework for this localization problem by assigning to each observation its conditional or marginal contribution across random statistical contexts. This connects resampling diagnostics and data valuation to projection theory and event-level anomaly detection. For symmetric statistics, fixed-size replacement is exactly equivalent to centered conditional localization. For U-statistics, the addition score equals the first Hoeffding/Hájek contribution; for smooth distributional functionals it is related at leading order to the influence function; and for unbiased known-background MMD it reduces exactly to the MMD witness. This viewpoint also yields more efficient estimators. Matched-context subtraction removes fluctuations unrelated to the observation, while for pairwise MMD the event-containing terms give a simple localizer. On the LHC Olympics anomaly-detection benchmark, the pair estimator converges to the direct empirical MMD witness with the predicted 1/(Rm^2) scaling, where m is batch size and R the number of batches. At m=1000 and R=5x106 it reaches correlation 0.9993 with essentially identical AUC. We also ask when context contains information beyond an event's own features. In a shared-latent toy model, the full single-event signal and background distributions are identical by construction, forcing isolated-event AUC=0.5. Discriminating information survives only in cross-event dependence induced by the shared latent parameter; the ensemble recovers this information, whereas an independent-latent control does not. This separates two roles of context: efficient localization of a global discrepancy and genuinely additional class information when the alternative contains shared structure. --- ### AI as Teammate: Rethinking Task Distribution in Medical Training Authors: Fendi Tsim, Alina Gutoreva, Anthony Weiss, Nicole Dubosh Published: 2026-08-28 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2608.28373v1 Integrating Artificial Intelligence (AI), particularly generative AI, into medical training has prompted concerns about learner over-reliance, misuse, and erosion of foundational clinical competencies. We propose a conceptual reframing at the decision level: the problem is not misuse but misclassification - a mechanistic failure of real-time metacognitive evaluation in selecting a subzone-inappropriate AI interaction mode. Drawing on "SCAN" (Substitute, Complement, Aid, Non-Negotiable), a human-centric decision-making framework for generative AI task allocation grounded in Vygotsky's Zone of Proximal Development and metacognition, we advance the emerging social-constructivist conversation around AI in medical education by offering a testable account of AI's role in clinical reasoning development. This framework yields testable predictions for how misclassification can be detected, mitigated, and, more importantly, prevented in the clinical learning environment. Regarding clinical reasoning development, we show how trajectories of skill acquisition (upskilling) and failure (the triad of skill failure: de-skilling, never-skilling, and mis-skilling) operate at the individual task level in ways that fixed-phase, cohort-wide treatments fail to capture. We further identify passive engagement within correctly classified AI-scaffolded tasks as a particularly insidious, detection-resistant pathway to mis-skilling - one requiring subzone re-identification from AI assistance to expert assistance, with human experts serving as epistemic auditors. The paper operationalizes SCAN for clinical curriculum design, supervision, and assessment, and opens an empirical research agenda grounded in cognitive science. This paradigm shift from misuse to misclassification is not semantic: it offers educators a clear perspective on what to look for, what to assess, and what to intervene on. --- ### Real-Time Musculoskeletal Surrogates for Pediatric Cerebral Palsy: a Credibility Pilot Authors: Mohammad Arif Ul Alam Published: 2026-08-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.28371v1 Real-time musculoskeletal (MSK) surrogates could support personalized rehabilitation for children with cerebral palsy (CP), but their credibility depends on subject-wise evaluation, low inference latency, and calibrated uncertainty. We develop a subject-conditioned causal neural surrogate using OpenSim-derived static parameters, temporal joint kinematics, true muscle capacities, and training-only perturbations. On a real pediatric CP gait dataset comprising nine children, we use leave-one-subject-out validation on six development subjects and evaluate a frozen configuration once on three locked test subjects. The surrogate accurately reproduces musculotendon lengths (R-square = 0.92 in development validation and approximately 0.95 on locked subjects; nRMSE < 8%) while requiring only sub-millisecond to few-millisecond neural inference, well below a 100 ms interactive-rehabilitation target. In contrast, direct muscle-force estimation remains unstable at this small, heterogeneous scale: pooled metrics can overstate within-subject, per-muscle accuracy. A Monte Carlo credibility pilot further shows that propagating only +/-5% anthropometry and muscle-capacity variation produces severely overconfident nominal 90% intervals (approximately 4% force coverage and below 1% MT-length coverage). These results establish a leakage-free evaluation and credibility framework for pediatric MSK surrogates, while identifying force modeling and epistemic uncertainty as the central next challenges for clinically credible digital twins. --- ### Real-Time Monitoring of MHD Liquid Metal Flows with Shallow Recurrent Decoders Authors: Claudio Scardino, Stefano Riva, Carolina Introini, Matteo Lo Verso, Eric Cervi, Antonio Cammi, Laura Savoldi Published: 2026-08-28 Categories: physics.comp-ph, cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2608.28366v1 State estimation in magnetohydrodynamic flows is critical for real-time monitoring of liquid metal blankets in tokamak fusion reactors. Due to the multiphysics nature of these phenomena, high-fidelity simulations are computationally prohibitive for real-time applications. This work investigates a data- driven Reduced Order Model framework: the Shallow Recurrent Decoder (SHRED) coupled with Principal Component Analysis, to map sparse temperature measurements to the full thermo-hydraulic system's state. The major contribution of this work lies in the two-parameter analysis of a fully three-dimensional domain representative of the DEMO breeding blanket configuration. Here, the flow is subjected to an external magnetic field varying in direction and intensity and is hindered by two cylinders acting as a water-cooling system, which impose a temperature boundary condition on their surfaces. This double-parametric magnetic variation induces nonlinear transitions in the flow dynamics, ranging from chaotic behavior at low magnetic field intensities to laminarized regimes at high intensities, characterized by the formation of asymmetric side layers at an inclination angle of 30 degrees. SHRED reconstruction maintains a mean relative error of approximately 5% for the temperature, pressure, and velocity fields. This accuracy is maintained across both weak and strong magnetic fields, ranging from 0.075 T to 0.300 T, and for inclination angles from 5 to 30 degrees, reflecting its dominant toroidal component. These errors are only slightly larger than the lower error bound dictated by low-rank truncation. The results establish SHRED as a reliable state estimator for complex and realistic engineering applications involving completely unseen parametric scenarios and validate it as an accurate real-time state estimation technique suitable for online monitoring and control of real facilities. --- ### EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses Authors: Tanmay Sah, Dolly Sah, Harshul Jain, Tanya Sah Published: 2026-08-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28363v2 LLM agents increasingly modify their own prompts, tools, middleware, resources, and execution harnesses at runtime. Such self-evolution can improve capability, but a successful mutation may leave persistent effects that cannot be safely reversed in states different from the one in which it was created. We introduce EvoUndo, a framework for representing, synthesizing, diagnosing, and independently verifying recoverability of model-generated self-modifications across counterfactual states. Across 600 unseen one-shot self-evolution tasks, we identify 197 capability-improving mutations that fail recoverability verification. Under the original recovery representation, conventional repair strategies recover 0/197 of these natural failures. Deterministic oracle analysis recovers 48/197 under the original recovery language L0, while the extended recovery calculus increases empirical oracle recovery to 191/197. A protocol-locked 2x2 grounding-by-expressivity intervention then separates two bottlenecks: exact state-address grounding increases successful recovery from 0/48 to 38/48 (79.2%) when the original language is sufficient, while extending the recovery language enables recovery on 142/143 (99.3%) failures in the oracle-defined S1 stratum. On the primary gpt-oss-120b backbone, adding exact-address diagnostics to the richer language reduces recovery to 133/143 (93.0%); a Qwen3.8-27B replication preserves the grounding and expressivity effects but not this negative interaction, indicating that the latter is model-dependent. These results indicate that reliable agent self-evolution requires co-designing verification, state grounding, witness semantics, and recovery-language expressivity rather than relying on iterative prompting alone. --- ### EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses Authors: Tanmay Sah, Dolly Sah, Harshul Jain, Tanya Sah Published: 2026-08-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28363v1 LLM agents increasingly modify their own prompts, tools, middleware, resources, and execution harnesses at runtime. Such self-evolution can improve capability, but a successful mutation may leave persistent effects that cannot be safely reversed in states different from the one in which it was created. We introduce EvoUndo, a framework for representing, synthesizing, diagnosing, and independently verifying recoverability of model-generated self-modifications across counterfactual states. Across 600 unseen one-shot self-evolution tasks, we identify 197 capability-improving mutations that fail recoverability verification. Under the original recovery representation, conventional repair strategies recover 0/197 of these natural failures. Deterministic oracle analysis recovers 48/197 under the original recovery language L0, while the extended recovery calculus increases empirical oracle recovery to 191/197. A protocol-locked 2x2 grounding-by-expressivity intervention then separates two bottlenecks: exact state-address grounding increases successful recovery from 0/48 to 38/48 (79.2%) when the original language is sufficient, while extending the recovery language enables recovery on 142/143 (99.3%) failures in the oracle-defined S1 stratum. On the primary gpt-oss-120b backbone, adding exact-address diagnostics to the richer language reduces recovery to 133/143 (93.0%); a Qwen3.8-27B replication preserves the grounding and expressivity effects but not this negative interaction, indicating that the latter is model-dependent. These results indicate that reliable agent self-evolution requires co-designing verification, state grounding, witness semantics, and recovery-language expressivity rather than relying on iterative prompting alone. --- ### Optimal Adversarial Testing: Extracting Honest Test Results from Dishonest Test Takers Authors: Owen Cox, April Xu, Weiyu Xu Published: 2026-08-28 Categories: cs.CR, cs.AI, cs.GT, eess.SP, stat.AP, stat.ME arXiv: https://arxiv.org/abs/2608.28362v1 In applications, it is often required to test objects or people to determine their qualities in terms of certain metrics. However, besides being naturally noisy, the test results can be corrupted by adversarial behaviors of objects or people being tested (test takers). For example, dishonest test takers can cheat in the exams to distort the test results. With the development of AI technologies, such distortions driven by cheating using AI technologies are becoming more commonplace and severe. In this paper, we propose optimal testing strategies which can still recover needed test results even if there are cheaters polluting the results. The proposed testing strategies will optimally re-test selected group of test takers using different testing security measures. We determine the optimal testing strategies using a dynamic programming method. --- ### GRACE:Gradient-guided Coreset Selection for LLM Unlearning Authors: Praveen Bushipaka, Andrea D'Angelo, Lucia Passaro, Tommaso Cucinotta Published: 2026-08-28 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.28361v1 Machine Unlearning methods for Large Language Models typically assume pre-specified forget and retain sets. In realistic settings, however, requests may provide only a few examples of undesired behavior, requiring forget and retain sets to be inferred from heterogeneous corpora. We study this data-selection problem and propose GRACE , a gradient-guided coreset selection method that constructs both forget and retain sets for LLM unlearning. GRACE first computes a forget direction from seed examples that elicit the undesired behavior, then selects a compact forget coreset whose gradients approximate this direction using non-negative orthogonal matching pursuit. To preserve model utility, it selects retain examples after projecting out the forget direction and applying clustered orthogonal matching pursuit in the remaining gradient space. Across two target domains, two model families, and four unlearning algorithms, GRACE improves model utility while maintaining comparable forget quality, with particularly consistent gains over prior gradient-based selection methods. --- ### Propagating construction-time knowledge quality into medical question answering: A framework grounded in clinical guidelines Authors: Jie Hu, Junjie Wang, Shan Lu, Yifang Hu, Gong Cheng, Yun Liu Published: 2026-08-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28360v1 Large language models have facilitated knowledge graph (KG) construction from clinical guidelines, but extracted triples vary in structural validity and evidential support. Meanwhile, graph-augmented question answering (QA) systems typically optimize query relevance during retrieval, with limited reuse of quality information produced during KG construction. This creates a disconnect between construction-time quality control and inference-time evidence use. We investigate whether construction-time triple quality can serve as a persistent signal for downstream evidence selection and presentation. We propose a quality-aware framework that models structural conformance (SchemaConf) and evidential support (EvidScore) as complementary dimensions and fuses them into a per-triple quality signal, Q(t). Rather than using quality solely for filtering, the framework retains Q(t) and derived quality tiers as graph attributes and propagates them into quality-weighted subgraph retrieval and tier-conditioned evidence prompting, while preserving passage-level provenance. Experiments on Chinese diabetes clinical guidelines show that the utility of the quality signal is distribution dependent. Under cross-version and cross-model shift, the fused Q(t) provides stronger triple-quality discrimination than either component alone (AUC 0.748 vs. 0.703 for EvidScore and 0.645 for SchemaConf). In guideline-grounded QA, propagating construction-time quality reduces required-knowledge omission from 16.3% to 5.3% and conflicting outputs from 16.3% to 2.7%, with an evidence-grounded precision of 81.6% and near-zero invalid citations. Blinded clinician ratings favor the full framework over no retrieval (4.68 vs. 4.21 on a five-point scale) and approach the oracle condition (4.80), while cross-generator experiments show consistent trends. --- ### AGENT-O: A Semantic Agent Card Framework for Interoperable and Governed Healthcare AI Agents Authors: Pengze Li, Cui Tao Published: 2026-08-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28345v1 AGENT-O is a modular ontology framework that defines a semantic Agent Card for representing health-oriented AI agent systems and supports assessment of reporting completeness in scientific publications. AGENT-O was developed as an OWL 2/RDF ontology covering runtime, models, workflow, tools, clinical use, evaluation, provenance, governance, and reporting assessment. Evaluation included ontology inventory, OWL-RL reasoning, three SHACL suites, 12 SPARQL competency queries, three cases, and model-assisted reporting-completeness assessment of 279 papers across five dimensions. The ontology contained 1,962 RDF triples and 1,922 Protege axioms, with 252 active classes, 198 active object properties, and 51 datatype properties. All SHACL suites conformed on example graphs, all competency queries returned prespecified evidence, and all 279 papers were scored. Incomplete reporting was highest for runtime/architecture (84.6%), governance/safety (82.8%), and provenance/reproducibility (78.1%), compared with evaluation (25.8%) and benchmark-process alignment (29.8%). AGENT-O supported semantic Agent Card representation and reporting assessment while revealing an evaluation-specification gap: evaluation and benchmark procedures were reported more consistently than runtime architecture, governance, and reproducibility. AGENT-O provides a reusable ontology, semantic Agent Card profile, and reporting-completeness workflow for structured reporting and gap identification, but does not assess agent quality or deployment readiness. --- ### Denoising-Aware Temporal Point Cloud Completion for 3D Crop Architecture Recovery and Phenotypic Trait Extraction Authors: Mrudul Mittal, Soumyashree Kar Published: 2026-08-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28343v1 High-throughput phenotyping depends on accurate 3D reconstruction of plants across growth stages, yet the development and evaluation of temporal completion methods are limited by the lack of datasets with complete geometric ground truth. To address this challenge, we introduce SynthCrop4D, a procedurally generated synthetic dataset of temporally evolving plant point clouds that provides controllable noise, occlusion, and complete plant geometry for benchmarking reconstruction methods. Using this dataset, we evaluate a two-stage pipeline that combines spatial denoising and temporal point cloud completion. First, a denoising module removes structural artifacts from raw laser-scanned point clouds. The resulting data are then processed by an Adaptive Temporal PoinTr model that reconstructs the current growth stage (t) using information from the previous stage (t-1), enabling recovery of regions missing due to self-occlusion. We evaluate the proposed framework on both SynthCrop4D and the real-world Pheno4D dataset (tomato and maize) under settings with and without denoising. Results show that denoising substantially improves reconstruction quality, with the best configuration achieving a Chamfer Distance of 0.0061 on SynthCrop4D (Temporal PoinTr + Mamba-DG) and an F-Score of 0.2080 on Pheno4D (Vanilla PoinTr + Mamba-DG). We further demonstrate the use of completed point clouds for phenotypic trait extraction, including plant height, canopy width, and convex hull volume, obtaining hull-volume MAEs of 0.021 on synthetic data and 0.343 on real data. Together, SynthCrop4D and the proposed pipeline provide a benchmark and methodology for temporal plant reconstruction and high-throughput crop phenotyping. --- ### Cross-Spectral Dense Correspondence for Multimodal Spectral Medical Imaging Authors: Eric L. Wisotzky, Jost Triller, Simon W. Härtl, Oliver T. Bruns, Peter Eisert, Anna Hilsmann Published: 2026-08-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.28341v1 Precise dense correspondence is a fundamental prerequisite for multimodal spectral imaging systems that fuse disparate wavelength ranges for subsequent analysis in medical and scientific imaging. Corresponding image points are often observed with non-overlapping spectral sensitivities, leading to wavelength-dependent contrast changes, intensity inversions, and appearance shifts for which dense ground truth is difficult to obtain and conventional RGB-based training data provides only limited supervision. We address this data gap by introducing a sensor-agnostic cross-spectral modulation protocol on established correspondence benchmarks with intensity input projection, and by proposing a synthetic cross-spectral correspondence benchmark simulating physically plausible radiometric differences. Evaluation on several modern dense correspondence backbones trained with our unified cross-spectral protocol showed substantial improvements under severe spectral mismatch while maintaining performance on standard RGB benchmarks. Ablation experiments show that view-dependent channel selection and nonlinear radiometric transformations provide complementary robustness, indicating that the primary limitation of existing models is not their structural matching capacity but the mismatch between training distribution and spectral characteristics of the target image pair. Qualitative evaluations on heterogeneous medical spectral acquisition systems demonstrate the practical relevance of the proposed training data augmentation protocol as an enabler for spatially coherent spectral fusion in HSI workflows. --- ### Abstract4D: A Large-Scale Dataset and Framework for Understanding the Visual Language of Abstract Art Authors: Haowei Zhang, Yuanpei Zhao, Ji-Zhe Zhou, Mao Li Published: 2026-08-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28339v1 Artificial intelligence can classify artistic styles and synthesize images, but it still lacks a model of the visual language that gives art meaning. Abstract painting minimizes object semantics and foregrounds structural cues, making it an ideal testbed for computational perception. We introduce \textbf{Abstract4D}, the largest dataset of abstract paintings to date: more than 120,000 images paired with rich metadata and multi-dimensional prompts that capture each work's perceptual attributes---\textit{form, color, texture, and composition}. Annotations are produced by a hybrid human--VLM pipeline for quality and consistency. Using Abstract4D, we (i) analyze the semantic structure of abstract art through large-scale embedding visualization, uncovering how perceptual relationships organize artistic meaning, and (ii) establish benchmark tasks for classification, cross-modal retrieval, and text-to-image generation to evaluate how AI models perceive and reproduce abstract visual language. Together, these analyses demonstrate how Abstract4D enables both exploration and quantitative assessment of AI's ability to represent and interpret abstract art. ---