# Research Papers — 2026-06 · bundle page 12 of 260 > Full-text markdown of papers #551–600 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/12 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/11.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/13.md) ### Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG Authors: Naihao Deng, Yilun Zhu, Joan Nwatu, Clayton Scott, Rada Mihalcea Published: 2026-06-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.30989v1 Warning: This paper contains several toxic and offensive statements. While reasoning generally improves fairness in recent large language models (LLMs), failures persist. In this work, we identify a failure mode, deductive stereotyping, in which models apply population-level statistical regularities to individual cases, producing logically coherent yet socially biased inferences. We provide a statistical interpretation of this phenomenon. To steer models toward fairness-aware reasoning, we propose a reasoning-time injection framework. We further introduce Fair-GCG to systematically discover effective injection phrases. Injection phrases discovered by Fair-GCG improve performance across multiple fairness benchmarks, generalize from smaller to larger LLMs, improves reasoning-level fairness, reduces bias in open-ended generation, and transfer to real-world fairness-sensitive tasks. --- ### Counterfactual Fragility Certificates: Exposing High-Confidence Brittleness under Structured Evidence Failure Authors: Filippo Cenacchi, Longbing Cao, Runze Yang Published: 2026-06-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.00366v1 High test accuracy and good aggregate calibration do not show whether an individual prediction is structurally supported by its evidence. In tabular decision systems, failures often occur when a feature family becomes unavailable, delayed, noisy, stale, or low-trust while the model remains highly confident. Existing calibration, uncertainty, selective-prediction, explanation, and perturbation methods provide scalar scores or attribution maps, but not a recomputable audit object answering: under a declared evidence-failure protocol, what trajectory makes this prediction lose support? We introduce Counterfactual Fragility Certificates (CFC), a model-agnostic protocol-level audit certificate-not a formal robustness certificate-that maps each prediction into an ordered evidence-failure trajectory summarized by greedy flip budget, normalized margin-collapse area, degradation thresholds, and fragility dominance score. Across seven tabular benchmarks and strong linear, tree-based, boosting, and neural baselines, CFC-FDS identifies independently brittle high-confidence cases with 0.915 AUROC, improving over the strongest non-certificate score by +0.405. The advantage persists across perturbation, permutation-importance, group-SHAP, baseline-choice, seed-variance, budgeted-review, and naturalistic field-unavailability checks. Under a 20% review budget, CFC-FDS captures 88.9% of brittle high-confidence cases, compared with 31.8-37.4% for confidence and energy scores. We also evaluate fragility-aware regularization and brittleness-aware temperature correction as secondary uses. CFC provides a concrete reliability framework for exposing high-confidence brittleness missed by ordinary score-centric evaluation. --- ### Leveraging Generative AI to Design Accessible Interactive Visualizations for Undergraduate Mathematics: A Six-Phase Workflow Authors: Mahesh Sunkula, Kuan-Hua Chen Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28601v1 Interactive visualizations support conceptual understanding in undergraduate mathematics, but building them has required programming expertise most instructors lack. Using a design-based research approach, we develop, deploy, and evaluate a six-phase workflow (Foundation, Customization, Mathematical Depth, Application, Accessibility, Pedagogical Control) that uses generative AI to build WCAG~2.2 Level~AA compliant visualizations without programming. The six phases structure every prompt, scaffold the AI's code generation, and define where human verification is applied. We ask whether the structure reliably yields correct and accessible tools, whether it runs both backward (reverse-engineering prompts from a finished tool) and forward (generating a tool from a plain-language idea), and what verification each phase requires. Across four deployed tools spanning calculus, multivariable calculus, and differential equations, we evaluate mathematical correctness against closed forms, accessibility through automated and manual screen-reader testing, and the errors that recurred. The structure produces structurally complete first-pass tools, but human verification remains mandatory at every phase: each output must be checked for mathematical correctness, accessibility, and pedagogical fit before the next phase begins. The workflow is platform-independent and serves both instructors and students. --- ### Towards Interpretable Depression Detection: Linking Acoustic Features to DSM-5 Indicators Authors: Jonas Länzlinger, Katharina O. E. Müller, Burkhard Stiller, Bruno Rodrigues Published: 2026-06-29 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2608.26148v1 Depression affects millions worldwide, yet diagnosis relies on subjective self-reports that may miss authentic behavior. This paper presents an approach linking speech acoustics to DSM-5 depressive-behavior indicators through a transparent Linkage Framework. Unlike black-box models, the framework explicitly maps acoustic features (pitch variability, pauses, speech tempo) to clinical indicators, enabling interpretable, indicator-level outputs. The system runs locally on commodity hardware (HW) to preserve privacy. Preliminary evaluation on DAIC-WOZ shows directionally consistent associations between acoustic features and DSM-5 indicators for psychomotor change and concentration difficulty, supporting the design rationale. Future work will validate on longitudinal datasets and extend multimodal integration while maintaining edge constraints. --- ### CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models Authors: Yucheng Zhou, Peng Luo, Qianning Wang, Chengzhong Xu, Jianbing Shen Published: 2026-06-29 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2608.26147v1 Large Language Models (LLMs) have shown strong potential for medical reasoning, yet the scarcity and cost of expert-annotated data constrain their progress. While reinforcement learning offers a scalable alternative, standard outcome-based methods in medicine often suffer from autoregressive credit assignment failure and gradient variance explosion. This leads to the "Right Answer, Wrong Reason" trap, where models inadvertently reinforce spurious correlations and dataset shortcuts rather than valid clinical deduction. In this work, we propose Causally-Aligned Reasoning Exploration (CARE), a theoretically grounded framework for intrinsic experience curation. CARE is built upon two rigorous conditions for high-quality training trajectories: Causal Sufficiency, which utilizes an agreement-based self-verification mechanism to mimic $do$-calculus interventions and effectively debias gradients; and Proximal Learnability, which employs dynamic entropy bounds to select experiences within the model's zone of proximal development for variance-bounded optimization. These rigorously filtered experiences are optimized via a dual-stream objective that combines on-policy group-relative exploration with difficulty-weighted experience replay. Extensive experiments on diverse medical multimodal and text-only benchmarks demonstrate that CARE consistently outperforms other strong competitors, substantially reducing correct-but-inconsistent reasoning and improving training stability. --- ### Infrared Hotspot-Guided Early Warning of Lithium-Ion Battery Thermal Runaway Under Mechanical Abuse Authors: Syed Sajid Ullah, Salman Khan, Muhammad Zunair Zamir Published: 2026-06-29 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2608.20383v1 Mechanical abuse can trigger thermal runaway (TR) in lithium-ion batteries through localized heat generation before sensor signals become decisive. This paper proposes a two-stage early-warning approach that estimates localized thermal instability from infrared hotspot dynamics and then fuses this instability score with mechanical, electrical, thermal, and image-intensity features for a 20-frame warning horizon. Evaluation uses repeated experiment-wise three-fold validation, with out-of-fold Stage-I scores during Stage-II training to prevent stacked-model optimism. Hotspot dynamics alone achieve Stage-I ROC-AUC 0.945, and the two-stage classifier reaches Stage-II ROC-AUC 0.908, exceeding direct multimodal fusion while preserving an interpretable intermediate instability signal. Thermal gradient rise precedes voltage-based detection by 40 frames (4 seconds) on average, enabling earlier battery management system intervention. Lead-time analysis at a fixed 0.5 threshold yields a 14.8-frame mean lead time. --- ### Decoupled Vision-Language System for Multimodal Understanding and Generation Authors: Yifan Xu, Baochen Xiong, Xiaoshan Yang, Donglin Di, Yaowei Wang, Changsheng Xu Published: 2026-06-29 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2608.20382v1 We introduce a new architecture design for multimodal large language models (MLLMs), Libra, capable of both multimodal understanding and generation. Libra architecture contains one vision system and one language system, connected by cross-modal bridges. This design decouples self-modal modeling and cross-modal interaction, enabling each modality to learn its unique representations while maintaining effective cross-modal comprehension. The decoupling is mainly achieved in a switch attention module and a switch FFN module, which dynamically routes the computation flow for self-modal modeling and cross-modal interaction scenarios. We evaluate the effectiveness in two important settings: \textbf{Libra-1} for the understanding-only image-to-text setting, and \textbf{Libra-2} for unified image-to-text understanding and text-to-image generation. In addition to the architecture design, we discuss various improvements on tokenization, positional encoding, and supervision. Experiments demonstrate that the dedicated Libra design enables mutual improvements on multimodal understanding and generation, achieving strong performance on both understanding and generation benchmarks. --- ### EditPPT: Faithful Long-Deck Slide Editing via Structured Tool-Using Multi-Agent with Dual-Modal Validators Authors: Jiheon Kim, Kyudan Jung, Jaegul Choo Published: 2026-06-29 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.20381v1 Automating slide editing requires simultaneously satisfying modification accuracy, preservation fidelity, and robustness to deck length. Existing LLM-based systems often fail on real-world presentation files because they rely on idealized intermediate representations or open-ended code generation, which are prone to cascading errors in long decks. We introduce EditPPT, a multi-agent framework that reformulates slide editing as a constrained tool-selection problem. By executing localized shape-level operations through the native PowerPoint COM interface, EditPPT narrows the LLM action space while preserving the application-resolved structure of user-authored decks. By separating validation across modalities, our dual-modal validation provides more robust assessment of both instruction fidelity and visual quality. We also present DeckEdit-Bench, a benchmark with 28 human-authored decks, 582 slides, and 183 editing prompts across short, medium, and long deck tiers. Experiments show that EditPPT achieves a 99.5% execution rate, 88.7% slide-targeting F1, 82.5% instruction following, and 91.5% object preservation overall, while maintaining strong performance on long decks. Our code and benchmark are available at https://anonymous.4open.science/r/EditPPT-0E27/ --- ### Interpretable Information-Decomposed Brain Graph Learning for fMRI-based Disease Diagnosis Authors: Dengyi Zhao, Zhiheng Zhou, Zihan Wang, Guiying Yan, Xingqin Qi Published: 2026-06-29 Categories: q-bio.NC, cs.LG arXiv: https://arxiv.org/abs/2608.20380v1 Resting-state functional magnetic resonance imaging (rs-fMRI) has enabled non-invasive mapping of functional brain interactions for computer-aided diagnosis, yet most existing approaches reduce inter-regional relationships to correlation-based edge weights. Such representations capture co-fluctuation strength but obscure how information is shared across brain regions. Because brain disorders may disrupt not only connectivity strength but also the organization of redundancy, uniqueness and synergy, traditional functional connectivity may miss disease-relevant information structures. Here we introduce IID-GCN, an interpretable graph learning framework that decomposes rs-fMRI interactions into redundancy, uniqueness and synergy graphs using partial entropy decomposition. These information-specific graphs separately characterize shared, region-specific and jointly emergent components of brain activity. A multi-channel graph convolutional network then integrates the decomposed graphs through edge recalibration, cross-information interaction, ROI-attention readout and channel-attentive fusion. Across three datasets, IID-GCN consistently captures complementary diagnostic information beyond traditional functional connectivity. The learned information profiles reveal disorder-specific patterns of altered redundancy, uniqueness and synergy, suggesting that brain diseases reshape functional information organization rather than merely changing connection strength. These results establish information-decomposed brain graphs as an interpretable representation for rs-fMRI-based diagnosis. Our code is available at https://github.com/Zdy12/IID-GCN. --- ### Accurate Decoding of Natural Sentences from Non-Invasive Brain Recordings Authors: Mingfang Zhang, Jarod Lévy, Cedric Rommel, Jérémy Rapin, Corentin Bel, Julie Bonnaire, Daniel Nieto, Pierre Bourdillon, Svetlana Pinet, Stéphane d'Ascoli, Thomas Moreau, Jean-Rémi King Published: 2026-06-29 Categories: cs.CL, cs.AI, cs.LG, eess.SP, q-bio.NC arXiv: https://arxiv.org/abs/2608.18114v1 Restoring communication for people who have lost the ability to speak or move after a brain injury is a major challenge. While intracranial implants now enable high-performing brain-computer-interfaces, non-invasive alternatives are still lagging behind. Here, we present Brain2Qwerty v2, a model that can decode the production of natural sentences solely from real-time magnetoencephalography (MEG) recordings. By collecting 22,000 sentences typed by nine subjects, each recorded for 10 hours, our model leverages character, word and sentence-level representations to achieve an average word error rate (WER) of 39%. For our best participant, the model accurately decodes half of the sentences with one word error or less. Critically, decoding accuracy log-linearly improves with data volume, suggesting that the performance gap with intracranial approaches could be partially bridged through data scaling. We show that AI enables this performance in three main ways: the substitution of hand-crafted pipelines for event detection with deep learning, the finetuning of large language models to extract semantic representations, and the deployment of AI agents to iteratively refine our decoding pipeline via automated code development. Together, these results show that non-invasive brain-to-text decoding starts to operate at a level of accuracy previously thought exclusive to surgical implants, opening a path toward safe and efficient brain-computer-interfaces. --- ### Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study Authors: Pengcheng Xu Published: 2026-06-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.13568v1 Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal, instant, and zero-setup, but noisy: it cannot tell a definition from a call from a comment. Semantic retrieval via the Language Server Protocol (LSP) is precise and typed, but needs a running, indexed server and pays a per-symbol round-trip. The claim that semantic retrieval is more token-efficient is, we find, asserted almost everywhere and measured almost nowhere: no public source isolates the LSP-vs-lexical token delta for an agent at equal task-success. This paper formalizes the question with one metric (tokens-to-success), specifies a five-arm ablation isolating semantic retrieval from confounds, maps three pre-stated failure modes onto measurable variables, and reports a preliminary study (Python and TypeScript repos; Claude Opus 4.8, Sonnet 4.6, Haiku 4.5). The answer is conditional and usually negative. On symbol-named localization the LSP costs tokens (+6% to +118%) and the agent ignores it when free. On reference-completeness it buys precision but not token savings and cannot raise the recall ceiling set by agent thoroughness; it saves tokens only for the weakest model. Tool choice is task-dependent: models default to grep on localization (0-6% semantic use) but reach for the LSP about half the time on reference tasks, unprompted. On edits scored by real test execution the gap is starkest: grep solves multi-file renames perfectly, a location-only LSP fails three-quarters of them by missing a call site, and even a complete, index-warmed, text-enriched LSP (each reference's line inline, as production LSP-MCP servers do) recovers most of the gap but cannot close it, since a rename must touch comments and strings that semantic references exclude. The implication is not LSP-always but an adaptive router keyed on task class, model capability, and lexical noise. --- ### How sensitive do we want AI to be? Socio-communicative competencies of large language models in healthcare Authors: Dorothee Amelung, Andrew M. Bean, Sabine C. Herpertz, Felix H. Krones, Guy Parsons, Adam Mahdi, Isabella Schneider Published: 2026-06-29 Categories: cs.HC, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2608.07511v1 Background. Effective clinical practice relies heavily on the socio-communicative skills of medical professionals. Large language models (LLMs) have been proposed for tasks such as triaging patients, report drafting or translating medical jargon to support informed decision-making. These applications require both factual and social competence. This study evaluates dialogues between LLMs and participants to assess the current state of socio-communicative competencies displayed in LLM-generated texts. Methods. We extracted a subset of extended dialogues from the HELP-Med dataset, comprising 1800 conversation transcripts of interactions between human participants seeking medical information and three different LLMs, GPT 4o, Llama 3 and Command R+. Two experts coded the transcripts for demonstrations of socio-communicative behaviours (non-hostility, sensitivity, structuring, non-intrusiveness) using the IC-MD instrument, originally designed to evaluate interactional competencies in medical student admissions. Results. The LLMs in our study showed strength in non-hostility, mixed results in sensitivity and non-intrusiveness and performed poorly in structuring. Conclusion. Current LLMs lack the consistent and reliable socio-communicative skills needed for safe and effective use as healthcare advisors. While existing frameworks for assessing interactional competencies may support the development of more socially responsive LLMs, they will require adaptation to account for the differences in desirable behaviour between humans and LLMs. --- ### World Simulator: Queer Erotica and the Absurdity of AI Video Models That Promise the World Authors: Adam Cole, Mick Grierson Published: 2026-06-29 Categories: cs.MM, cs.CV, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2608.07510v1 Increasingly, AI video models are marketed as "world simulators," suggesting their ability to model infinite realities. Despite such claims, these models systematically exclude significant aspects of embodied human experience, particularly sexuality. World Simulator is a video installation exploring the poetic friction between these universal claims and the models' inherent blindness. To do so, the work feeds explicit gay erotica into an AI video-to-video pipeline. Lacking the training data to recognize these images, the system hallucinates surreal alternatives, transforming intimate acts into banal scenes of kitchen appliances, strange architectures, and abstract flesh. By visualizing the limits of synthetic knowledge, the work challenges the hubris of the "world simulator" label, asking how a system, trained primarily on large filtered video datasets, can claim to simulate the world while remaining structurally blind to the body. Beyond this critique, we question the value of simulation itself, asking what forms of sensual representation might offer more expansive, life-affirming possibilities. --- ### PIVOT: Preference-based Intervention Vectors for Pedagogical Tutor Steering Authors: Fares Fawzi, Jiaxu Zhao, Tanya Nazaretsky, Tanja Käser Published: 2026-06-29 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2608.07509v1 LLMs are increasingly used for conversational tutoring, but effective tutoring requires more than correct answers. Tutors must choose when to scaffold reasoning, hint, give feedback, explain, or invite reflection. Existing prompting and training methods improve pedagogical alignment, but lack reliable inference-time control over pedagogical strategies. We introduce PIVOT, an activation-steering framework that learns preference-based intervention vectors online for frozen LLM tutors. PIVOT uses a seven-category tutor-move taxonomy and a generate-label-optimise loop, where a human-validated LLM judge identifies target and confusable non-target moves to construct preference pairs for multi-layer residual-stream steering. Across held-out and out-of-domain tutoring data, PIVOT controls tutor moves while preserving relevance and fluency, and its directions can be scaled, transferred, and composed at inference time. In a user study with 30 teachers, 73.3% of participants preferred steered conversations over neutral baseline interactions using the same prompt, and rated the controls as clear, usable, and pedagogically meaningful. --- ### Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap Authors: Tianyu Ding, Aditya Nannapaneni, Bingfan Liu, Ling Zhang Published: 2026-06-29 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.05179v1 Large language model (LLM) agents are increasingly used across the scientific research lifecycle: ideation, literature search, experiment design and execution, analysis, manuscript drafting, and review. End-to-end AI scientist systems can now produce paper-like manuscripts, but their claims are often harder to verify than their code is to run. This survey studies that gap in computational AI/ML research, where code, benchmarks, experiments, and write-ups are most visible. We screen 125 candidate works and include 35, with full-text coding of 26 entries: 24 runnable systems and two study or position papers. We code seven audit dimensions: lifecycle stage, autonomy level, evaluation method, released artifacts, human-in-the-loop points, novelty verification, and result-selection disclosure. The main pattern is that code release is now common, but reproducibility-grade and claim-verification artifacts remain much less common. In the 24 runnable systems, 83 percent release code, while 38 percent release seeds or execution traces and 38 percent report any novelty-verification method. Among nine closed-loop L4 systems, seven are mechanical reruns and one is author-claimed without an external check; no LLM-era system in the corpus demonstrates an externally validated in-loop oracle under our coding rule. We contribute a coded corpus, a lifecycle-by-autonomy map, an auditability-gap analysis, and a reviewer-facing reporting checklist. The survey argues that the field's central bottleneck is no longer only whether agents can complete research tasks, but whether reviewers can verify the claims those agents produce. --- ### CITBench: A Comprehensive Benchmark for Interactive Tabular Data Processing with LLMs Authors: Zihan Nan, Yang Gu, Wei Liu, Xi Yan, Zhou Liu, Hao Liang, Wentao Zhang Published: 2026-06-29 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2608.00018v1 Tabular data processing is central to data work, and LLM-based assistants have recently shown promising capabilities in supporting such tasks. However, existing benchmarks primarily focus on table reasoning under single-turn, fully specified instructions, underrepresenting complex table processing that unfolds through multi-turn interactions with evolving user requirements. To bridge this gap, we introduce CITBench, a comprehensive benchmark for evaluating LLMs on interactive tabular data processing. CITBench features a comprehensive taxonomy across four high-level categories--table matching, cleaning, augmentation, and transformation--spanning 18 task types and 1,296 instances curated from datasets across diverse domains. The benchmark supports both offline and online evaluation, where the online setting models multi-turn interactions under constrained operation procedures and structured task scripts, capturing key potential behavioral characteristics of user-in-the-loop tabular data processing. We evaluate a broad suite of open-source and closed-source LLMs on CITBench, revealing a consistent trend: while current models perform well on simple tables and rules, their performance degrades significantly with increasing table complexity, tighter rule dependencies, and noisy multi-turn interaction simulations. These results highlight persistent challenges in understanding, planning, and table-structure awareness for LLMs in extended interactive data processing scenarios. --- ### Memory Reward Inflation in Self-Improving LLM Agents Authors: Mohammad Asadolahi, Amir Amini, Samira Talebi, Amirfarhad Farhadi, Azadeh Zamanifar Published: 2026-06-29 Categories: cs.AI, cs.CE arXiv: https://arxiv.org/abs/2608.00017v1 Self-improving LLM agents increasingly learn from experience without updating any weights. Each episode is stored in an external memory, scored, and retrieved for similar future tasks to shape later behavior. Viewed through a reward lens, the stored score is a proxy reward for an implicit, non-parametric policy. Each retrieved episode then becomes a policy-improvement step whose reliability hinges on how that score is produced. In deployment, ground-truth labels are unavailable, so the stored reward is at best an LLM assessment. This substitution creates a failure mode, the *Echo Gap*, across the memory-based self-improving agents and model families studied. Incorrect episodes receive inflated rewards; thus, the agent preferentially reuses the very mistakes it has most confident in. Because the error compounds through memory rather than averaging out and the confirming judge's errors remain correlated with the original self-grading bias, so it cannot identify which memories are overvalued. The missing property is formalized as the *Error-Independence Assumption* (EIA), which we prove is a *necessary* condition for correcting the inflation, not merely a description of a good verifier: a usable signal must track truth *and* decorrelate its error from the memory bias, and the recoverable payoff is a closed-form function of exactly those two quantities. We further show the inflation compounds not only when retrieval ranks by the stored score but also under plain similarity retrieval which is the regime the deployed agent uses. Finally, the answer-free de-inflation algorithm LUCID delivers a consistent end-to-end gain on the BIRD text-to-SQL benchmark. It raises execution accuracy to $56.9\%$, above both a Memento-style self-graded agent ($54.0\%$, a $+2.9$-point mean gain across seeds) and a memory-less agent of identical architecture ($52.4\%$). --- ### Retrieval, not hallucinations, will be the limiting factor for LLM-based clinical AI tools Authors: Kirk Roberts, Steven Bedrick, Kurt Miller, William R. Hersh, Hongfang Liu Published: 2026-06-29 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2607.24793v1 Discussions around large language model (LLM) errors in clinical artificial intelligence (AI) generally center around precision errors like hallucinations. This perspective, targeting both clinicians and AI researchers, seeks to shift that discussion to recall errors, particularly in retrieval of patient-level data needed for many clinical AI tools. The perspective outlines types of errors and mitigation strategies, describes research directions in LLMs and retrieval, and provides an overview of retrieval evaluation. --- ### Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language Models Authors: Xingyu Mou, Zijin Huang, Tianze Zhang, Yuxin Ma, Lanning Wei, Zengfeng Huang, Da Zheng, Lun Du Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22663v2 Block diffusion is the dominant approach for scaling discrete diffusion language models (dLLMs), as fixed-size blocks preserve parallel decoding while keeping quadratic attention costs tractable. Yet blockwise generation creates a structural weakness: tokens near a block boundary lack future cross-block context, and errors in finalized blocks become irreversible context for later generation. We call this the block boundary problem. Measuring predictions with and without later-block context shows that boundary sensitivity rises sharply: on AIME 2025, mean self-containedness divergence (SCD) in the last quarter of a block is 61.3 times that in the first quarter. We propose Multi-Block Editing (MBE), which revises decoded tokens using cross-block context. Training-Free MBE reopens a full-attention window over selected blocks without parameter updates. To address the mismatch between block-diffusion training and MBE inference, Multi-Block Edit SFT introduces bidirectional attention masks and progressively enlarges the editing span. We also extend SGLang with a multi-shape CUDA Graph pool and fine-grained KV-cache control for efficient variable-length editing. Experiments on LLaDA2.1-Mini across 12 benchmarks show broad, consistent gains. Training-Free MBE improves or matches standard decoding on every benchmark. Full MBE raises the 12-benchmark average from 61.45 to 64.24, with gains of up to 13.33 points on AIME 2025, while retaining 87.3--96.7% of standard-decoding end-to-end throughput across four datasets. --- ### CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data Authors: Peiguang Li, Yongwei Zhou, Juncheng Diao, Yuchun Fan, Jian Yang, Jianxiao Yang, Zhongda Su, Shuguang Jiao, Xiao Wei, Zhiye Zou, Gan Dong, Zhizhao Zeng et al. Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22662v1 Open-web corpora curated via highly selective filters, such as FineWeb-Edu and DCLM, constitute the core of LLM pretraining data and have significantly advanced LLM performance. However, these pipelines typically rely on singular optimization objectives, which inevitably narrows distributional diversity and marginalizes long-tail knowledge, thereby restricting data coverage and underutilizing the vast potential of the open web. To address this limitation, we propose a novel curation paradigm that shifts from linear pruning to the joint optimization of quality, redundancy, and diversity. This framework synergizes dual-track cleaning (rule-based and model-driven) with hybrid deduplication (n-gram and semantic), while employing a multi-objective sampler to balance informational quality with distributional breadth. Applying this framework to Common Crawl, we construct CuraWeb, a 2T-token English corpus. Unlike existing resources, CuraWeb establishes an industrial-grade standard for data curation by recovering a more holistic data distribution with enhanced diversity and minimal redundancy, achieving broader coverage of long-tail knowledge across diverse domains. Experimental evaluations at the 3B scale demonstrate that CuraWeb significantly outperforms state-of-the-art baselines, yielding an average performance gain of 1.8\% across a wide range of benchmarks, particularly in knowledge-intensive and reasoning tasks. --- ### TRE: Training-Free Hallucination Detection for Diffusion Language Models Authors: Pengcheng Weng, Yanyu Qian, Yue Tan, Yixin Liu Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22661v1 Diffusion large language models (D-LLMs) have recently gained increasing attention, yet their reliability is significantly hindered by the hallucination problem. Existing hallucination detection approaches for D-LLMs mainly follow a training-based paradigm, relying on data-driven training to optimize the detector. Such reliance not only limits their generalizability across domains models but also incurs additional training cost and deployment overhead. To address these limitations, we propose TRE, a training-free hallucination detection metric for D-LLMs. TRE is a parameter-free and single-run metric that estimates hallucination risk directly from the entropy signals of a single generation, without requiring any detector training or repeated sampling. TRE extracts entropy signals within the D-LLM decoding process along both the spatial and temporal dimensions. From a token-level spatial perspective, we focus on revealing tokens as the most informative carriers of uncertainty, capturing where uncertainty is actively committed. From a diffusion step-level temporal perspective, we empirically identify the dominance of late-step entropy and hence aggregate these signals with a simple linear weighting scheme to obtain TRE. Extensive experiments on multiple D-LLMs and QA datasets demonstrate that TRE achieves competitive performance, while enjoying strong generalizability, efficiency, and robustness. --- ### Beyond Single-Dimensional Compression: The Compound Sparsity Frontier of Large Language Models Authors: Chao Han, Haozhe Hu, Xiaoyu Shen Published: 2026-06-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.18280v1 Large language models (LLMs) are often compressed through static parameter pruning or dynamic token-level computation, yet aggressive sparsification can trigger rapid performance degradation beyond an essential sparsity boundary. This work asks \emph{whether combining these two mechanisms can delay such degradation by distributing the compression burden}. We study a minimalist compound sparsity framework that first applies low-rank approximation and channel pruning to obtain a statically compressed backbone, and then introduces lightweight routers for per-token dynamic layer skipping. This design enables independent control of parameter sparsity and token-level computation sparsity. Experiments across language understanding and modeling benchmarks show that compound sparsity consistently outperforms single-mechanism compression under the same total sparsity, delaying the decay point on understanding tasks and preserving stronger modeling performance. Further analysis reveals cross-dimensional interference between parameter pruning and token skipping, and shows that near-balanced allocation is most effective under a fixed sparsity budget. These results demonstrate that compound compression provides a practical way to improve LLM compression, while revealing a broader cross-dimensional sparsity boundary that ultimately limits further compression. Code will be available at https://github.com/EIT-NLP/LLM-Pruning. --- ### Beyond Output-Space Calibration: Spectral Evidence Bundling for Selective Reliability Estimation in Time-Series Classification Authors: Filippo Cenacchi, Longbing Cao, Runze Yang Published: 2026-06-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.18279v1 Post-hoc calibration for time-series classification usually remaps output scores, but deployment decisions such as trust, abstention, and review depend on whether a confident prediction is supported by the current temporal signal. We address three time-series reliability gaps: identical confidence values can hide different temporal support, average calibration can miss false high-confidence errors, and output-space recalibration offers limited input-linked auditability. We introduce a validation-gated fixed-label reliability policy that keeps the backbone prediction unchanged while estimating whether it should be trusted. The method combines output-side cues with whole-sample spectral descriptors, including band energy, entropy, peak dominance, period support, and phase stability, to form a scalar reliability estimate and diagnostic band-level evidence. A validation gate enables spectral conditioning only when correctness ranking improves without breaching FalseConf@0.9 or AURC tolerances; otherwise it reverts to the safer output-space baseline. Across eight heterogeneous UCR/UEA datasets, eight time-series backbone families, and standard recalibrators, the unconstrained method improves fixed-label selective-reliability metrics on the matched evaluation subset, raising Corr-AURC from 0.693 to 0.779. The validation-gated policy further improves Corr-AURC to 0.786 and reduces FalseConf@0.9 to 0.094. These results suggest that reliability estimation for time-series classifiers benefits from bundling output confidence with spectral evidence, while validation gating prevents unsupported spectral conditioning. --- ### FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration Authors: Filippo Cenacchi, Longbing Cao, Runze Yang Published: 2026-06-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.18278v1 Calibration is usually evaluated in aggregate, but the most dangerous failures are often local: predictions that remain highly confident despite being wrong. We study this failure mode as false-confidence concentration, the extent to which confident errors occupy compact, discoverable regions of prediction space. We introduce FALCON-Discover, a post-hoc, model-agnostic framework that ranks predictions using discrepancy signals from confidence, local support, neighborhood agreement, and perturbation stability. Across seven binary tabular datasets, four seeds, five-fold cross-fitting, and strong learners including XGBoost and CatBoost, we find that false-confidence concentration is recurrent but regime-dependent. At the main confidence threshold, discrepancy-based ranking substantially outperforms the strongest validation-selected calibration or trust-scoring baseline in the strongest regimes, while raw confidence recovers little dangerous-error mass. The best detector varies across datasets: learned discrepancy is strongest when multiple cues must be combined, whereas stability-centered ranking works best when local decisional fragility dominates. These results show that dangerous overconfidence is better treated as a family-level discovery problem than as a single-score calibration problem, and motivate calibration strategies that explicitly target regions where confidence, support, and stability diverge. --- ### Preference-based Antibody Expression Ranking: Scaling with Large-scale Weak Supervision Authors: Josh Qixuan Sun, Morteza Babaie, Wenyang Hou, Mark Crowley, David Young Published: 2026-06-29 Categories: cs.LG, cs.CE, q-bio.QM arXiv: https://arxiv.org/abs/2607.16263v1 Antibody expression ranking is a critical task in antibody design, yet its modelling is severely hindered by the scarcity of labeled experimental data. To address this, we propose a unified preference-based learning framework that integrates scarce quantitative expression data with large-scale weak positive supervision from immunization data. We adapt Direct Preference Optimization (DPO) to protein language models by introducing a union-masked log-likelihood approximation and IMGT-based alignment, enabling efficient training on variable-length sequences. Evaluating on a diverse internal dataset of 1254 labeled sequences and 4 million unlabeled camelid-derived antibodies, we show that our method consistently outperforms baselines on most metrics. Our results demonstrate that preference learning can effectively learn from weak supervision, providing a scalable solution for antibody expressibility optimization in data-constrained settings. Project page: https://kisoji-biotechnology-inc.github.io/Preference-Expression-Ranking/. --- ### Structure of the Circular-Dyadic Convolution Error Authors: Ben Fauber, Alireza Moradzadeh Published: 2026-06-29 Categories: cs.LG, cs.AI, math.NA arXiv: https://arxiv.org/abs/2607.15293v1 Dyadic and circular convolution can both be computed in $O(N\log N)$ time using the Hadamard transform and the FFT-computed discrete Fourier transform (DFT), respectively. The Hadamard transform is preferable for its real-valued sign flips, yet its substitution for the DFT introduces algebraic error. We present three complementary results that characterize this error. First, we identify exact error cancellation: two input and two output positions are universally error-free, and no reordering of the output can eliminate this error. Second, the error operator is nearly full rank, while its null space has only logarithmic dimension. Third, the expected error is governed by a single alignment scalar, with a closed-form expression obtained by averaging over random filters. In general, the substitution error asymptotically doubles the output energy, except for filters in the universal zero-error subspace, which incur no error. Collectively, these results show that the substitution error is structured, predictable, and governed by alignment. --- ### SPINE: Bridging the Cyber-Physical Gap with Agentic AI Authors: Minkyu Ham, Dongho Kim, Chan Lee, Min Jun Kim, Yixi Zhang, Jiayi Wang, Han Liu Published: 2026-06-29 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2607.13049v2 Foundation models give robots powerful high-level reasoning, yet turning that intelligence into reliable physical action remains difficult: roboticists must still align device drivers, network interfaces, sensors, controllers, and safety constraints for each platform. This often-overlooked integration layer acts as the robot's spinal cord, translating high-level intent into coordinated physical behavior, and remains a primary bottleneck for scalable Embodied AI. Hence, we propose SPINE (Scalable Physical Integration with ageNtic Expertise), an agentic framework for systematically debugging and deploying bimanual robots for teleoperation. SPINE centers on two subagent-driven workflows: a profile builder that compiles robot-specific context and a debugger that uses that context to iterate through diagnosis, repair, and validation until teleoperation succeeds. Across two bimanual robot platforms and 12 debugging scenarios, novice-operated SPINE achieved more complete and efficient recovery than human operators using Claude Code. On DOBOT X-Trainer, SPINE improved success from 76% to 100% and reduced mean time-to-teleoperation by 30\%; on AgileX PiPER, SPINE also achieved 100\% success and reduced mean time-to-teleoperation by 38%. These results show that structured agentic debugging can address a key cyber-physical integration bottleneck in real-world robot deployment. --- ### SPINE: Bridging the Cyber-Physical Gap with Agentic AI Authors: Minkyu Ham, Dongho Kim, Chan Lee, Jiayi Wang, Min Jun Kim, Yixi Zhang, Guo Ye, Jihai Zhao, Soyeon Park, Han Liu Published: 2026-06-29 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2607.13049v1 Foundation models have given robots a sophisticated brain for complex decision-making, yet deploying that intelligence into a physical platform still demands tedious, expert-driven calibration. This deployment gap, the robot's spinal cord, remains a primary bottleneck to scalable Embodied AI. Hence, we propose SPINE (Scalable Physical Integration with ageNtic Expertise): an agentic framework for systematically debugging and deploying bimanual robots with minimal robotics expertise. SPINE's harness comprises two orchestrated multi-agent workflows: a profile builder that creates robot-specific context, and a debugger that cycles through diagnosis, repair, and validation until teleoperation works. Across seven DOBOT X-Trainer debugging scenarios, a robotics novice using SPINE outperformed human operators using Claude Code with the same reference materials, but without SPINE's structured workflow, improving operationalization success from 75% to 100% and reducing mean time-to-teleoperation from 16 min 45 s to 13 min 47 s. On AgileX PiPER, a distinct ROS/CAN bimanual arm, SPINE resolved all 10 implanted bugs, versus 9 out of 10 for the expert baseline, in nearly the same amount of time. Together, these results show that SPINE can transfer across bimanual platforms, reduce dependence on expert calibration, and move embodied AI closer to scalable real-world deployment. --- ### Coordinate Singularities Break Conformal Coverage for Gaze and Head Pose Authors: Mohammadreza Jamalifard, Yaxiong Lei, Parastoo Azizinezhad, Javier Andreu-Perez Published: 2026-06-29 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2607.02565v1 Conformal prediction provides distribution-free reliability guarantees for vision systems, but these guarantees depend on how prediction errors are measured in the output space. Many vision tasks produce outputs on curved spaces (e.g. gaze directions on the sphere or 3D head rotations), yet intermediate prediction heads, residuals, uncertainty estimates, or conformal scores are often defined in flat coordinate charts such as yaw-pitch or Euler angles. We show that this scoring choice introduces systematic geometric distortion near coordinate singularities (large pitch angles on the sphere and poses approaching gimbal lock in 3D rotations). Across four datasets (ETH-XGaze, Gaze360, BIWI, AFLW2000-3D), slice-conditional coverage at a nominal 90% target drops by 30-50 percentage points in these regions, falling to 38.9% on ETH-XGaze and 42.0% on Gaze360 at gaze pitch above 70 degrees, and to 57.5% on BIWI and 55.2% on AFLW2000-3D at head pose pitch above 60 degrees near gimbal lock, despite marginal coverage remaining near 90%. We prove that this is structural. Scalar thresholding changes the size of chart-coordinate prediction sets but leaves their distorted axis ratios unchanged. To diagnose this hidden failure mode, we show that a simple geometric quantity, the Riemannian volume density, strongly correlates with where coverage collapse occurs. Finally, we show that coordinate-free geodesic scoring removes this distortion. It requires no retraining and adds negligible computational cost. --- ### From Raw Segmentations to Simulation-Ready Cardiac Meshes: An Automated Framework for Anatomical Reconstruction and Virtual Cohort Generation Authors: Francesco Fabbri, Martino Andrea Scarpolini, Paolo Ciancarella, Francesco Tudisco, Roberto Verzicco, Alessandro Ricci, Francesco Viola Published: 2026-06-29 Categories: cs.CV, cs.AI, q-bio.TO arXiv: https://arxiv.org/abs/2607.02564v1 Computational models of the human heart are widely used to study electromechanical and fluid-dynamical cardiac function and to support applications such as in silico clinical trials. However, most studies remain limited to single or patient-specific anatomies, restricting the inclusion of population-level variability required for uncertainty quantification. A key challenge is translating medical-image segmentations, which may contain artifacts, mesh defects or disjoint domains, into topologically coherent geometries suitable for multiphysics simulations. In this work, we present a semi-automatic pipeline that converts CT-based segmentations into simulation-ready cardiac meshes within a few minutes while preserving anatomical and topological consistency. Building on modern deep learning segmentation methods, the framework incorporates a template-based registration stage to regularize artifacts and enforce mesh-quality constraints. A Chamfer-distance morphing strategy deforms a high-quality template toward each segmented heart, matching individual chambers while preserving topology. The resulting meshes are watertight, isotopological, and endowed with consistent point-to-point correspondence. The pipeline is validated on 58 healthy cardiac CT scans, including all cardiac chambers and proximal vessel segments. The resulting meshes can be represented in a unified shape space, enabling the construction of a statistical shape model of the heart and major vessels. Principal Component Analysis shows that a low-dimensional latent space efficiently captures population variability, while Gaussian Mixture Modeling enables synthetic anatomy generation. Overall, the proposed framework (released open-source) provides a pathway from raw segmentations to simulation-ready cardiac geometries, enabling anatomically consistent virtual cohorts for large-scale in silico studies. --- ### Fast approximation and learning of binary classification tasks in o-minimal structures using ReLU neural networks Authors: Clemens Kinn, Philipp Petersen Published: 2026-06-29 Categories: math.LO, cs.LG, math.FA arXiv: https://arxiv.org/abs/2607.01266v1 We study binary classification problems whose decision sets are given by definable sets in o-minimal expansions of the real field. Motivated by cell decomposition of definable sets, we introduce traceable sets as a classical proxy for definable decision regions and analyze their approximation by ReLU neural networks. Under uniform bounds on the number of connected components and suitable $C^m$ extensions for the boundary functions, we prove that characteristic functions of traceable subsets of $(-1/2,1/2)^n$ can be approximated in $L^p$ to accuracy $\varepsilon>0$ by ReLU neural networks of size $\mathcal{O}(\varepsilon^{-p(n-1)/m})$, with depth independent of $\varepsilon$ and polynomially bounded weights. This establishes quantitative approximation rates for certain definable collections in o-minimal structures using ReLU neural networks. The same approach also yields the stated approximation rates for a subclass of definable maps $(-1/2,1/2)^n \to \mathbb{R}$. We then combine the approximation capabilities with entropy estimates for ReLU neural network classes to obtain statistical learning rates for empirical risk minimization with hinge loss. For $N$ uniformly distributed samples, the resulting classifiers achieve expected misclassification error of order $N^{-m/(m+pn-p)}$ up to an arbitrarily small polynomial loss. --- ### Prompting GPT-5 on Scrum Certification Questions: An Empirical Accuracy Study Authors: Mirko Perkusich, Danyllo Albuquerque, João Paiva, Robson Vilar, Emanuel Dantas, Ademar França de Sousa Neto, Rohit Gheyi, Kyller Gorgônio, Angelo Perkusich Published: 2026-06-29 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.00049v1 Large Language Models (LLMs) are increasingly used in Agile Software Development for documentation, coaching, and training. As practitioners adopt these tools to prepare for certifications such as Professional Scrum Master (PSM), a key question is whether LLMs can reliably reason about Scrum, a framework with normative, well-defined rules described in the Scrum Guide (2020). This paper examines how different prompt techniques affect the factual accuracy of LLM responses to Scrum certification-style questions. A dataset of 993 validated PSM-aligned questions was answered by GPT-5 using three techniques: zero-shot, chain-of-thought, and with-source citation. All prompts achieved certification-level accuracy above 85\%, with the citation-based variant performing best (89.1\%) and yielding the lowest error rate. Correct answers concentrated in well-defined topics, such as \emph{Definition of Done}, Events, and Product Backlog Management, and in single-answer multiple-choice items, while multi-select questions and more interpretive areas, such as Scrum Team and Product Value, were less stable. Among questions where at least one prompt failed (16.2\%), errors clustered into misalignment with the Scrum Guide (28\%), content outside its scope (34\%), and outdated or biased interpretations (38\%). Overall, prompt techniques produced modest but consistent improvements, particularly in reducing misinterpretation and version drift, supporting more reliable use of LLMs in Agile learning and certification preparation. --- ### Comparing Large Language Models on Scrum Certification-Style Questions: Accuracy, Stability, and Error Patterns Authors: Robson Alves Vilar, Emanuel Dantas Filho, Ademar França de Sousa Neto, Mirko Perkusich, Danyllo Wagner Albuquerque, João Paiva, Kyller Gorgônio, Angelo Perkusich Published: 2026-06-29 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.00048v1 Large Language Models (LLMs) are increasingly used in exam- and certification-style question answering tasks, where their ability to retrieve, interpret, and apply domain-specific knowledge can be systematically assessed. In Software Engineering, such settings are particularly relevant when questions depend on strict adherence to normative definitions, roles, artifacts, and rules. This paper evaluates the performance of three contemporary LLMs, \textit{GPT-5 mini}, \textit{Gemini 3 Flash}, and \textit{DeepSeek Chat 3.2}, in answering 993 Scrum certification-style questions aligned with the Professional Scrum Master I (PSM I) assessment format. We evaluated the models under three prompting strategies (\textit{zero-shot}, \textit{chain-of-thought}, and \textit{source-grounded}), with repeated executions to assess intra-model stability. We also analyzed performance across Scrum topics and question formats, complemented by a qualitative analysis of recurring error patterns in incorrect answers. Results revealed clear differences among models, with Gemini 3 Flash achieving the highest accuracy, followed by GPT-5 mini and DeepSeek Chat 3.2, while intra-model variability remained low across all conditions. By question format, the models achieved the highest accuracy on single-answer multiple-choice items, whereas multi-select and True/False questions were more error-prone. By topic, performance was more consistent in normatively explicit areas such as Artifacts, Empiricism, and Product Value, but more fragile in Scrum Values, Self-Managing Teams, and Stakeholders \& Customers. The qualitative analysis showed that errors were systematic rather than random, involving overgeneralization, restrictive wording, compound distractors, and conflicts between common market interpretations and strict Scrum definitions. --- ### Vertigo Vertigo: Reconstructing a Cinematic Ideal through its Predictive AI Double Authors: Adam Cole, Mick Grierson Published: 2026-06-29 Categories: cs.MM, cs.CV, cs.GR arXiv: https://arxiv.org/abs/2607.00047v2 Vertigo Vertigo is a scene-for-scene AI reconstruction of Hitchcock's Vertigo (1958), generated from only 2.78% of the original film's frames. Using this sparse set of keyframe anchors, we perform first-last frame interpolation via a large video diffusion model to predict the intervening sequences. Vertigo is itself a film about the obsessive reconstruction of an artificial ideal; Vertigo Vertigo extends this logic to the material of the film, treating the canonical text as a probe for the normative conventions of classical cinema encoded within generative systems. Evaluated through computational analysis and critical feedback from media theorists (Lev Manovich, Shane Denson, Kevin L. Ferguson), the artifact demonstrates remarkable structural fidelity: 73.1% of frames are recognizable as plausible renditions of Vertigo and only 3.6% fail catastrophically. This fidelity suggests that cinematic norms are deeply compressed within the model's latent priors. Aesthetically, the reconstruction is rendered as an unstable overlay between the original film and its predictive shadow, fueling a persistent doubt in the viewer's perception of authenticity -- a 21st-century vertigo. The work argues that generative media is not a paradigm shift from cinema but an acceleration of its logic of desire and false authenticity, extending from classical Hollywood through to the predictive media environments now reshaping contemporary perception. --- ### Destination-Labeled Self-Looping Systems with Dwell: Intrinsic Characterization, Realization Cost, and Recognition Authors: Reda Belaiche Published: 2026-06-29 Categories: cs.FL, cs.AI, cs.CL, cs.LO arXiv: https://arxiv.org/abs/2607.00044v1 We study a finite-state symbolic controller for systems in which the admissible visible transitions are fixed in advance and each visible state carries a minimum dwell requirement. The resulting model, which we call a destination-labeled self-looping system with dwell (DLSL system), records the visible graph together with local decision maps; dwell memory appears only after phase expansion. The main structural issue is that, once dwell is imposed, the current visible state no longer determines whether a departure is allowed. This leads to the converse problem: which deterministic transducers arise as phase-expanded realizations of DLSL systems over a fixed visible graph? We show that the answer is exactly the class of fiber-linear graph-respecting transducers. Under natural reachability and realizable-departure assumptions, equivalent accessible realizations over the same visible graph are isomorphic; in particular, the visible transduction determines the dwell vector and the local decision maps. We also prove that any graph-preserving deterministic realization enforcing dwell values $(d_i)$ requires exactly $\sum_i d_i$ control states. Finally, we give an $O(|Q||Ω|)$ recognition and reconstruction procedure, and extend the analysis to an edge-entry variant in which transitions may enter interior phases of successor fibers. --- ### ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis Authors: Eagl Huang Published: 2026-06-29 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.00041v1 Multi-agent LLM systems can decompose software-engineering work into planning, generation, validation, and repair, but a narrower systems problem remains: before any governed shared mutation is applied, a system must decide which concurrently formed write intents may proceed in parallel, which require deterministic composition or serialization, and which must take a fail-closed path. We address this problem with the AI-Atomic-Framework (ATM), a specification-grounded governance substrate for software agents operating within a single governance domain. ATM binds task intent, repository scope, write admission, validation, and evidence obligations into one governance chain. A Content Identifier (CID) broker serves as the shared-mutation admission subsystem. Adapter-guided atomization maps write intents to semantic atoms and bounded regions; when persistent atom-map coverage is incomplete, virtual atoms provide temporary auditable governance units for conservative comparison and routing. Governed shared writes are ultimately applied by a neutral steward rather than directly by proposing agents. Evaluation combines controlled, field, adoption, and extension evidence, including a 12-scenario deterministic design matrix, three archived runner cases, ATM-AdmissionBench, three archived same-file boundary cases, a three-week external-adopter study, and an operational recovery-routing benchmark. The results support feasibility, auditability, and bounded recoverability within the observed single-domain settings, but do not claim broad comparative superiority or cross-clone governance. --- ### Measuring Judgment Quality in Natural-Language Explanations: Evidence from Forecasting Tournaments Authors: Christopher W. Karvetski, Sheldon S. Huang, Simas Kučinskas, Nadja Flechner, Jingyu Hu, Philip Tetlock, Ezra Karger Published: 2026-06-29 Categories: cs.CL, econ.GN arXiv: https://arxiv.org/abs/2606.30987v1 Decision-makers routinely rely on expert judgments accompanied by written explanations, yet explanation quality is difficult to measure at scale. Forecasting tournaments offer a natural testing ground: probabilistic judgments are paired with natural-language rationales and scored against realized outcomes. We introduce Explanation Quality Markers (EQMs), a set of sixty theory-guided reasoning patterns scored by large language models (LLMs). In a pre-registered analysis of over 55,000 forecast-rationale pairs from a multiyear forecasting tournament, EQMs predict accuracy at both the forecast and forecaster levels, consistently outperforming pre-LLM text-analysis methods. More than 90% of statistically significant pattern-level EQM-accuracy correlations match our directional hypotheses. The signal is asymmetric: EQMs identify likely underperformers more reliably than they distinguish the very best forecasters. Benchmarked against traditional indicators of forecasting skill, EQMs are the strongest predictor at the forecast level and competitive at the forecaster level, though weaker than prior accuracy. Human ratings of rationale quality are less consistently correlated with accuracy and place disproportionate weight on rationale length. Results transfer to an independent forecasting study. EQMs provide a scalable, interpretable method for extracting judgment-relevant information from written explanations. --- ### When Regulation Has Memory: Hysteresis and Control Burden in Artificial Agency Authors: Veronique Ziegler Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30975v1 Adaptive agents are usually judged by what they do, but an agent can appear stable while the internal effort required to keep it stable is increasing. This hidden regulatory burden matters for artificial agents operating under noise, delay, or changing demands: two systems may reach similar internal states while one requires much more corrective control to get there. Here, we study whether that burden depends on history. Using a computational model of adaptive uncertainty regulation, we drive an artificial agent through a continuous change in its uncertainty target and then reverse the change without resetting the agent. This creates a simple test for carryover: does the controller respond only to the current target, or does the path by which the agent reached that target still matter? The simulations show a clear history-dependent effect. The adaptive gain required to regulate the agent forms a reproducible hysteresis loop, meaning that the same target can require different levels of control depending on whether the agent is moving toward or returning from a more demanding regime. The timing of regulation also matters. When stabilization is available before disturbance exposure, the agent generally requires less adaptive gain than when it can only recover after disturbance has already acted. The state-level coherence measure also shows path dependence, but the timing effect is much clearer in regulatory gain. The main difference is therefore not that anticipatory regulation produces a completely different state. Rather, it reaches comparable regulated behavior with lower modeled control demand. These results suggest that adaptive agents should be evaluated not only by whether they remain organized, but by how much regulation they must recruit to do so. --- ### From Propositional to Perceptual Asymmetry: Extending Frictive Policy Optimization to Asymmetric Partial Information Dialogue Authors: Yifan Zhu, Kyeongmin Rim, James Pustejovsky Published: 2026-06-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.30973v1 Frictive Policy Optimization (FPO; Pustejovsky et al., 2025) treats friction in collaborative dialogue -- misalignment, misunderstanding, repair -- as an epistemic signal essential to common-ground construction, rather than noise to be minimized. However, FPO and its implementations assume shared perceptual contexts, where friction arises from differently interpreted propositions over the same scene, which we define as propositional asymmetry. We extend FPO to perceptual asymmetry, where participants hold asymmetric partial information and the same referring expression yields different denotations depending on whose information state grounds the reference. We evaluate this through cross-corpora analysis and LLM probing on referentially asymmetric dialogue tasks, primarily the HCRC MapTask (Anderson et al., 1991). We find that FPO's friction functional is empirically valid only when evaluated from within each participant's information horizon: different landmark configurations produce qualitatively distinct grounding failure modes, with a small class of ambiguous configurations driving a disproportionate share of misunderstandings through trajectories that appear successful but silently diverge. The LLM probe confirms that having the "right perspective" matters more than having all perspectives: the informed single viewpoint outperforms omniscient access to both participants' contexts. We propose two annotation refinements: subtype decomposition of pending grounding states and accommodation-aware alignment classification. --- ### Behavioral Governance for Autonomous AI Agents: The AgentBound Framework Authors: Anuj Kaul, Qianlong Lan, Pranay Gupta Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30970v2 Autonomous AI agents increasingly perform consequential actions on behalf of human principals, including financial transactions, external communications, and enterprise workflows. Existing agent infrastructure relies on identity federation and delegated authorization to authenticate workloads and control resource access, but it cannot determine whether an authorized action should be executed under the current behavioral and operational context. We present AgentBound, a runtime governance framework that provides verifiable behavioral oversight for autonomous AI agents. AgentBound evaluates each proposed action using three independent authorities: delegated authorization, owner-signed behavioral constitutions, and site action contracts. Their judgments are conservatively composed through a formal decision model to determine whether an action should be permitted, reviewed, or denied before execution. To provide accountability, AgentBound generates cryptographically verifiable governance receipts that bind every action to the exact delegation, policy, and semantic artifacts governing the decision, enabling independent replay verification and policy provenance. The framework also introduces standing delegation for long-running agents, allowing periodic workloads to operate under continuously refreshed governance policies while preserving revocability and bounded authority. We present the formal foundation, system architecture, governance receipt protocol, and AgentBound-Bench, a benchmark framework for evaluating governance correctness, authority composition, and accountability. Rather than replacing model alignment, AgentBound complements it by providing a deterministic governance layer between authorization and execution, transforming governance from a process that must be trusted into one that can be independently verified. --- ### PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising Authors: Koorosh Roohi, Javad Rajabi, Andrew Fleet, Babak Taati Published: 2026-06-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.30968v1 Photomosaics are large images whose local regions are seen as independent tiles while their overall arrangement forms a coherent scene. Generating them at high resolution, with every tile convincing in its own right, is computationally expensive, since the canvas must hold many detailed tiles at once. We present PhotoQuilt, a training-free framework that generates photomosaics at arbitrary resolution. Diffusion models struggle to satisfy both scales at once, as direct high-resolution generation is costly and tends toward one smooth image rather than a mosaic, while patch-based tiling keeps local detail but loses global structure. PhotoQuilt resolves this with a bootstrapped tiled denoising procedure. We first produce a global composition at low resolution to fix the layout, then upscale it in latent space and re-inject noise to restore generative capacity. Denoising proceeds within fixed tiles, so each forms its own image while the shared global structure holds them in one layout. Because tile generation is handled separately, PhotoQuilt scales to large canvases without quadratic attention cost. Experiments show that PhotoQuilt outperforms current baselines on both global structure and local realism. --- ### HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation Authors: Arshia Rafieioskouei, Tzu-Han Hsu, Matthew Lucas, Borzoo Bonakdarpour Published: 2026-06-29 Categories: cs.AI, cs.LO, cs.MA arXiv: https://arxiv.org/abs/2606.30966v1 Formal specification is a powerful tool to guide the learning process and provides significant advantages over reward shaping: (1) mathematical rigor; (2) expressiveness to specify objectives and constraints, and (3) the ability to define tactics to achieve objectives. However, these benefits remain largely unexplored in the context of Multi-Agent Reinforcement Learning (MARL). This paper introduces HyPOLE, a novel framework for MARL under partial observability, where learning is guided by the expressive power of the so-called hyperproperties and, in particular, the temporal logic HyperLTL. We integrate Centralized Training for Decentralized Execution (CTDE) techniques with HyPOLE to synthesize decentralized policies, and our evaluation on SMAC, MessySMAC, and WildFire benchmark demonstrates clear advantages over baselines. --- ### Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair Authors: Mohammad Nour Al Awad, Sergey Ivanov Published: 2026-06-29 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2606.30963v1 Repository-grounded automated repair is often reported as a single end-to-end capability, which hides distinct failure modes such as poor file targeting, incorrect patch synthesis, and failed iterative debugging. We present Loc2Repair, a modular evaluation framework for controlled analysis of repository-grounded repair pipelines, and use it to isolate file-level issue localization as an upstream variable. Loc2Repair decouples localization and repair under a shared runtime, artifact schema, and evaluation harness, allowing researchers to combine different localization models and repair backbones under matched conditions. Using three repair backbones on SWE-bench Verified, we compare baseline repair without explicit localization, repair guided by predicted localization from two localizers, and repair guided by gold modified-file sets. Explicit localization consistently improves resolved rate across all backbones: pooled performance increases from 44.7% for baseline repair to 48.9% and 49.1% with predicted localization, and to 52.4% with gold localization. Localization also reduces mean elapsed time overall: in pooled paired analysis, mean elapsed time decreases by 100.94 s and 52.25 s for the two predicted-localization settings, and by 154.45 s with gold guidance, although token effects remain heterogeneous across models. Overall, Loc2Repair shows file-level localization is a consistent repair lever, improving effectiveness and mean latency in pooled analysis, while gold-guided failures expose headroom beyond localization. --- ### ElemeNet: Multiscale Molecular Machine Learning with Uncertainty Quantification Across the Periodic Table Authors: Jacob W. Toney, Samir Darouich, Yiran Wang, Aaron G. Garrison, Johannes Kästner, Heather J. Kulik Published: 2026-06-29 Categories: physics.chem-ph, cs.LG arXiv: https://arxiv.org/abs/2606.30961v1 Advances in deep learning architectures and representations have enabled ML-driven chemical property prediction, but state-of-the-art (SOTA) models have remained largely confined to independent codebases and lack support for diverse chemical species. This work introduces ElemeNet, a unified, general-purpose software package for molecular machine learning. The ElemeNet software package enables the training of advanced ML models for diverse properties and datasets with an enlarged range of elemental compositions. We define molecular representations compatible with elements 1-100, supporting diverse organometallic and biological systems in addition to organic chemistry already well-served by the Chemprop ML toolkit. As well as more common atom-, bond-, and molecule-level predictions, we introduce moiety predictions. We also natively define optional conditioning on charge and spin states. Advanced E(3)-equivariant and transformer architectures are supported, as well as classical 2D models, with all classes including built-in uncertainty quantification through deterministic and statistical measures. We benchmark our protocols for ML model training against representative datasets from organic, inorganic, coordination, and biological chemistry, achieving competitive and SOTA performance relative to literature baselines and favorable scaling to millions of molecules. The entire workflow is exposed through a concise command-line interface, lowering the barrier to entry for non-expert users. We anticipate ElemeNet will empower non-computational researchers to leverage modern deep learning methods across the chemical and physical sciences. --- ### Exponential-Family Tensor Completion via Nonconvex Dual Total-Variation Regularization Authors: Wenfei Cao, Yang Chen, Qibin Zhao, Jinglai Li, Andrzej Cichocki Published: 2026-06-29 Categories: stat.ME, math.OC, math.ST, stat.ML arXiv: https://arxiv.org/abs/2606.30958v1 With the emergence of various tensor data, tensor completion from partial measurements has attracted widespread attention in data science and signal processing. Total Variation (TV) has been widely used as an effective regularization technique for tensor completion; however, theoretical studies on TV regularization in this context remain limited. In this work, we present a rigorous theoretical analysis of TV regularization for tensor completion. Specifically, we consider tensor completion under exponential-family noise, which generalizes the standard settings such as Gaussian and Poisson tensor completion. To handle exponential-family tensor completion, we propose a family of dual-TV (DTV) regularizers based on the transformed L1 function, which simultaneously capture sparsity and low-rank structures in the gradient tensor. Moreover, we establish the theoretical upper bounds on the recovery error of the proposed estimator. In certain cases, these upper bounds can attain the convergence order of $\mathcal{O}\big( n_3 r_t\big(\max_{k} s_k^2\big) \log\big((n_1+n_2)n_3\big) /n \big)$, and the minimax lower bound analysis is further presented to show that the upper-bounds can approach the lower bound with the gap of order $\mathcal{O}(\max_k s_k^2/max(n_1, n_2))$ up to a logarithmic factor. Finally, multiple groups of experiments on synthetic, image and video tensor data sets are conducted to support our theoretical results and demonstrate the effectiveness of our method. --- ### Linguistic Distancing on Social Media: Indicators of Emotion Regulation Across Age Groups Authors: Daniela Teodorescu, Saif M. Mohammad, Alona Fyshe Published: 2026-06-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.30957v1 Managing our emotional responses to events is key to emotional well-being, a process referred to as emotion regulation in psychology. Previous work has established that the degree to which we distance events is a type of emotion regulation. When we psychologically distance from events there can be markers in our language. These markers have been referred to as linguistic distancing. We build upon a previous metric to operationalize linguistic distancing, and explore how it changes across the lifespan. We explore this systematically by analyzing large amounts of social media text, a venue where people express their emotions. By investigating how distancing varies across age groups we can better understand how emotion regulation varies with age and provide initial benchmarks on social media data. We provide additional evidence further strengthening the hypothesis that linguistic distancing occurs in proportionally more instances with age. These findings align with past work in psychology which indicate improved well-being with older age. Better understanding how linguistic distancing changes with age is important because it functions as a marker of well-being and can inform effective health interventions. We provide a foundation for further exploring emotion regulation through linguistic distancing in text data. --- ### Neuro-Bayesian-Symbolic Residual Attention Shallow Network: Explainable Deep Learning for Cybersecurity Risk Assessment Authors: Nicolaie Popescu-Bodorin, Madeleine Togher Published: 2026-06-29 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.30953v1 We introduce the Neuro-Bayesian-Symbolic Residual Attention Shallow Network (NBS-RASN), a hybrid neural architecture for explainable cybersecurity risk assessment in open-source ecosystems. Unlike deep models that trade interpretability for accuracy, our shallow network encodes domain knowledge, causal reasoning, and expert judgment as differentiable components. It uses 80 interpretable neurons across 12 layers, including a gatekeeper that enforces five epistemological axioms - precision, causality, falsifiability, transparency, and completeness - as hard constraints before propagation. Despite limited depth, the network exhibits deep-learning traits via residual attention and feedback loops, learning complex risk patterns without becoming a black box. It produces fully decomposable scores: a deterministic weighted component plus an expert adjustment, with each adjustment traceable to named amplifiers (blast radius, propagation speed, structural nature, default exposure, exploitation pattern, institutional criticality). We validate on 20 open-source projects covering all OWASP Top 10:2025 categories and language risk classes, achieving confidence scores of 0.79-0.97, and show that explainability is guaranteed by design, not by a training algorithm. This challenges the assumption that deep learning requires deep networks, proving that shallow networks with deep reasoning can outperform opaque models in high-stakes cybersecurity, where interpretability is essential. --- ### Learning Where to Look: A Reinforcement Learning Framework for Robust Micro-Ultrasound Prostate Cancer Detection Authors: Mohammad Mahdi Abootorabi, Sina Namazi, Armin Saadat, Lyuyang Wang, Obed Dzikunu, Paul F. R. Wilson, Zhuoxin Guo, Brian Wodlinger, Parvin Mousavi, Purang Abolmaesumi Published: 2026-06-29 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.30951v1 Micro-ultrasound ($μ$US) is a new, emerging, and promising imaging modality for prostate cancer (PCa) detection, but accurate identification of suspicious tissue remains highly dependent on clinical experience, leading to substantial inter-observer variability. Machine-learning assistance can reduce this variability; however, training reliable deep models is challenging because supervision is sparse and noisy -- typically limited to core-level histopathology outcomes (e.g., cancer grade and its percentage in a biopsy core) without pixel-level lesion annotations and under severe class imbalance. We introduce Prost-RL, which reframes $μ$US PCa detection as a spatially aware, policy-driven inference problem by learning where to look before decoding. Prost-RL integrates a lightweight reinforcement-learning policy into a foundation-model encoder-decoder to generate interpretable spatial attention maps that act as soft prompts for both cancer-likelihood heatmap prediction and image-level classification. We further propose Adaptive Policy Optimization (APO) to stabilize hybrid supervised-RL training and a noise-robust objective combining symmetric cross-entropy with negative-entropy regularization to mitigate weak-label noise and encourage sharp localization. On a cohort of 6,607 biopsy cores from 693 patients across five clinical sites, Prost-RL achieves $79.0\pm3.5$ AUROC with $64.6\pm6.3$% sensitivity at 80% specificity for core-level detection (+2.1 AUROC and +4.5 sensitivity points over the strongest baseline), and $79.3\pm5.8$ AUROC for clinically significant cancer classification. The learned policy highlights biopsy-aligned regions, providing transparent, spatially grounded evidence alongside quantitative risk predictions. Code is available at: https://github.com/DeepRCL/Prost-RL. --- ### AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance Authors: Yang Zou, Zijian Ding, Yizhou Sun, Jason Cong Published: 2026-06-29 Categories: cs.AI, cs.AR arXiv: https://arxiv.org/abs/2606.30949v2 High-Level Synthesis (HLS) provides a fast path from concepts to silicon, but converting real-world software into synthesizable HLS code remains challenging due to restrictive language support and the gap between software and hardware programming practices. Existing automated and LLM-based refactoring approaches partially address this problem, yet they often lack flexibility, struggle to scale, and incur high computational costs. We introduce AgRefactor, an LLM-based multi-agent workflow for refactoring software into HLS-compatible programs. AgRefactor incorporates a self-evolving memory system that accumulates and retrieves factual and strategic knowledge across tasks, improving robustness and efficiency on unseen programs. To reduce cost and enhance scalability, it integrates automated refactoring tools, enabling agents to balance LLM-driven rewrites with efficient tool-based transformations. On 9 out of 11 challenging real-world benchmarks, which are 5-10x longer than the most complex cases studied in prior work, AgRefactor outperforms or matches the state-of-the-art automated refactoring tool and a strong LLM-based baseline built on the same framework backbone. Further agentic performance optimization yields a 6.51x geometric mean speedup over the SoTA pragma tuning tool and a 1.20x speedup over optimized open-source designs with less than 20% extra resources. AgRefactor is fully-automated and open-sourced. --- ### AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance Authors: Yang Zou, Zijian Ding, Yizhou Sun, Jason Cong Published: 2026-06-29 Categories: cs.AI, cs.AR arXiv: https://arxiv.org/abs/2606.30949v1 High-Level Synthesis (HLS) provides a fast path from concepts to silicon, but converting real-world software into synthesizable HLS code remains challenging due to restrictive language support and the gap between software and hardware programming practices. Existing automated and LLM-based refactoring approaches partially address this problem, yet they often lack flexibility, struggle to scale, and incur high computational costs. We introduce AgRefactor, an LLM-based multi-agent workflow for refactoring software into HLS-compatible programs. AgRefactor incorporates a self-evolving memory system that accumulates and retrieves factual and strategic knowledge across tasks, improving robustness and efficiency on unseen programs. To reduce cost and enhance scalability, it integrates automated refactoring tools, enabling agents to balance LLM-driven rewrites with efficient tool-based transformations. On 9 out of 11 challenging real-world benchmarks, which are 5-10x longer than the most complex cases studied in prior work, AgRefactor outperforms or matches the state-of-the-art automated refactoring tool and a strong LLM-based baseline built on the same framework backbone. Further agentic performance optimization yields a 6.51x geometric mean speedup over the SoTA pragma tuning tool and a 1.20x speedup over optimized open-source designs with less than 20% extra resources. AgRefactor is fully-automated and open-sourced. ---