探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-22 DOI: HASH:f9d6691f8aac92f15c53341c5a819564

The direct economic impact of surgical non-response in orthopaedic hip, knee, and spine surgery for osteoarthritis: a cost-utility analysis

作者:

Rampersaud↗Y. R↗Perruccio↗A. V↗Collett↗Sundararajan↗Du↗J. T↗Montoya↗Power↗J. D↗Canizares↗…

Background Annually, nearly 2 million hip, knee, and spinal inpatient surgeries are performed in Canada and the US for osteoarthritis (OA), costing over $37 billion in hospital expenditures. However, 15-30% of patients experience limited or no improvement, resulting in poor value for money. This study evaluated the one-year cost-utility of joint and spine procedures for OA by comparing non-responders to responders, considering various responder definitions. Methods Individual micro-costing data were collected for 1,175 elective hip, knee, and spine patients enrolled in the Longitudinal Evaluation in the Arthritis Program - Osteoarthritis (LEAP-OA) between 2014 and 2018. Quality-adjusted life years (QALYs) were derived using the SF-6D utility index. One-year incremental cost-utility ratios (ICURs) were calculated from the hospital perspective. Results Responder rates varied by definition, ranging from 78%-94% for hip replacements, 64%-90% for knee replacements, 60%-64% for spine fusions, and 50%-68% for spine decompressions. Corresponding ICURs were: $45,956-$51,773/QALY for responders versus $108,593-$485,762/QALY for non-responders for hip replacements; $54,831-$71,151/QALY for responders versus $200,486-$1,203,596/QALY for non-responders for knee replacements; $65,980-$74,422/QALY for responders versus $262,039-$729,686/QALY for non-responders for spine fusions; and $29,947-$42,168/QALY for responders versus $63,195-$662,586/QALY for non-responders for spine decompressions. Conclusions While surgical response rates were highly dependent on the responder definition, ICURs for non-responders were significantly higher than those for responders across all definitions. Beyond the negative impact on patients, there is a compelling economic argument for investment in improved pre-operative identification of patients at risk of surgical non-response. Such efforts could enable more personalized, value-based care pathways and reduce the provision of low-value surgical interventions.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2604.14906

Unraveling the Mechanism of Drug Binding to SARS-CoV-2 RNA Pseudoknot with Thermodynamics-Driven Machine Learning

作者:

Mariia Ivonina↗Jakub Rydzewski↗

arXiv:2604.14906v3 Announce Type: replace-cross Abstract: The pseudoknot secondary structure in SARS-CoV-2 RNA is essential for regulating protein synthesis through $-$1 programmed ribosomal frameshifting ($-1$ PRF), a mechanism that allows the virus to generate both structural and non-structural proteins from overlapping reading frames. This pseudoknot exhibits both threaded and unthreaded long-lived topologies. The influence of ligand binding on its folding is a process critical for the development of $-$1 PRF small-molecule inhibitors. Understanding this process through unbiased molecular dynamics (MD) simulations can be facilitated by introducing collective variables (CVs) that capture the corresponding slowest dynamical modes. Here, we use spectral map (SM), a thermodynamics-driven machine learning technique, to learn such CVs directly from all-atom MD trajectories of the SARS-CoV-2 RNA pseudoknot in complex with the $-$1 PRF inhibitor merafloxacin and its two structural analogs in neutral and ionized forms. Free-energy landscapes (FELs) derived from the learned CVs indicate that ligand-induced destabilization is topology-selective. In the threaded pseudoknot, the inhibitors destabilize the S2 stem, while in the unthreaded pseudoknot, destabilization occurs in the S1 and S3 stems. Furthermore, the extent to which each ligand reshapes the FEL matches experimentally reported antiviral potency, whereas the protonation state qualitatively alters dynamics within the same RNA topology. Overall, our results show how pseudoknot topology, ligand type, and protonation state collectively influence the slow conformational dynamics of viral RNA and establish physiological protonation as a critical factor for modeling RNA-targeted drug action.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11417

Signed Compression Progress on a Sealed Audit is Goodhart-Resistant

作者:

Ayush Mittal↗Dhruv Gupta↗

arXiv:2606.11417v1 Announce Type: cross Abstract: Compression progress is a long-standing proposal for intrinsic motivation: reward an agent when its world model becomes better at predicting or compressing experience. The folk claim is that this reward is "credible" because it is paid only for learning. We make this precise and prove it. If intrinsic reward is the signed decrease of a fixed sealed-audit loss, r_t = E(theta_{t-1}) - E(theta_t), then cumulative reward telescopes exactly to endpoint audit improvement, so no policy can push reward up indefinitely while true audit performance stagnates or degrades. For finite audit panels the same result holds with a sharp false-positive budget: cumulative empirical reward is at most true audit improvement plus 2 Delta_n(F, delta), the uniform audit deviation of the model class. This is horizon-free: adaptivity over time costs nothing once the sealed panel uniformly controls the class. The theorem also identifies the failure modes: the guarantee disappears if progress is clipped, scored on the agent's own stream, exposed to a high-capacity model on a reusable panel, or applied to a neural class that makes Delta_n vacuous. We give a Lean 4 mechanization of the structural core (telescoping, the finite-audit bound, finite Gibbs, and the entropy floor) and an experiment suite on ARC-TGI grid-transformation generators with adaptive holdout attacks. Experiments confirm the theory: finite-audit deviation scales as n^{-0.527}; signed progress resists clip-farming, stream leakage, and noisy-TV curiosity; naive reusable audits are exploitable by black-box scalar feedback, while standard release defenses keep the attack below the 2 Delta_n threshold. Signed compression progress on a sealed audit is an accounting signal of genuine improvement.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18508

MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval

作者:

Amirhossein Abaskohi↗Raymond Li↗Gaetano Cimino↗Peter West↗Giuseppe Carenini↗Issam H. Laradji↗

Retrieval-augmented generation (RAG) systems depend critically on how documents are chunked and searched. Fine-grained chunks can improve retrieval precision but expand the search space, increasing latency and cost; larger chunks reduce the number of candidates but make dense similarity less reliable, as the representation for each chunk mixes multiple topics and introduces more semantic noise. This trade-off becomes especially limiting in deep research tasks, where retrieval must be both fast and precise across large, heterogeneous corpora. We introduce MCompassRAG, a metadata-guided retrieval framework that uses topic-level signals as a semantic compass for selecting relevant evidence. Instead of relying only on cosine similarity between queries and noisy chunk embeddings, MCompassRAG enriches chunk representations with topic metadata in the same embedding space and trains a lightweight retriever through LLM-teacher distillation. At inference time, MCompassRAG performs topic-aware retrieval without additional LLM calls, improving both efficiency and evidence quality. Across six complex retrieval benchmarks, MCompassRAG improves information efficiency (IE) by 8.24% on average with over 5 times lower latency than the strongest efficient RAG baselines. Code is available on https://github.com/AmirAbaskohi/MCompassRAG.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.04602

Parthenon Law: A Self-Evolving Legal-Agent Framework

作者:

Hejia Geng↗Leo Liu↗

arXiv:2606.04602v3 Announce Type: replace Abstract: As agents grow more capable, legal-domain LLM agents promise to turn document-heavy matters into reviewable work products – yet reliable deployment faces three obstacles: no large-scale evidence on how today's strongest model-and-harness combinations behave on end-to-end legal matters; no agent architecture adapted to the legal vertical, only general-purpose harnesses; and, in a setting that keeps shifting with new facts, authorities, and deadlines, no mechanism for systems to learn from their own outcomes. We address each. A large-scale empirical study on Harvey LAB – $12{,}510$ agent trajectories – shows that even frontier agents remain far from completing matters in a single pass: per-criterion accuracy climbs with stronger models while strict matter completion stalls. We then introduce \textsc{Parthenon}, a self-evolving legal-agent framework that factors Model, Harness, Agent roles, legal Knowledge, deterministic Tools, and procedural Skills into auditable surfaces for source traceability, date and number grounding, deliverable compliance, and issue closure. Finally, an anti-leakage learning loop converts scored failures into task-agnostic edits to skills, tools, and knowledge, letting the system improve with experience – as a firm refines its checklists and playbooks after each matter – without touching model weights. Across our large-scale empirical analysis, \textsc{Parthenon} substantially improves the performance of state-of-the-art models and harnesses on legal-matter tasks.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15176

Enabling Real-Time Point-of-Care Ultrasound Segmentation: A GPU-Free Deployment in Resource-Limited Settings

作者:

Weihao Gao↗

Ultrasound imaging is the most widely adopted medical modality globally due to its low cost and portability, yet artificial intelligence (AI) deployment remains constrained by reliance on GPU-accelerated models, creating a structural paradox where the cost of "intelligence" exceeds that of the imaging device itself. Here, we present the systematic adaptation and extensive evaluation of UltraSeg, an ultra-lightweight architecture originally developed for colonoscopic polyp segmentation, now engineered for point-of-care ultrasound (POCUS) across ten public datasets spanning six anatomical sites (breast, thyroid, kidney, carotid, fetal, and small-animal tumor). We systematically validate both variants in ultrasound domains: UltraSeg-130K (0.13M parameters) achieves 89.7 FPS on single-core CPUs and 34.8 FPS on a refurbished mobile device, while UltraSeg-500K (0.5M parameters) delivers 44.6 FPS on CPU and 16.1 FPS on mobile device. UltraSeg-500K matches or exceeds the Dice performance of the 31M-parameter UNet and approaches 105M-parameter TransUNet in average performance, with superior zero-shot cross-dataset generalization on external validation sets (UDIAT, DDTI). By enabling clinical-grade segmentation without GPU dependency, this work brings AI costs in line with ultrasound accessibility, making advanced diagnostics available in resource-limited settings.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2407.13053

E2Vec: Feature Embedding with Temporal Information for Analyzing Student Actions in E-Book Systems

作者:

Yuma Miyazaki↗Valdemar \v{S}v\'abensk\'y↗Yuta Taniguchi↗Fumiya Okubo↗Tsubasa Minematsu↗Atsushi Shimada↗

Digital textbook (e-book) systems record student interactions with textbooks as a sequence of events called EventStream data. In the past, researchers extracted meaningful features from EventStream, and utilized them as inputs for downstream tasks such as grade prediction and modeling of student behavior. Previous research evaluated models that mainly used statistical-based features derived from EventStream logs, such as the number of operation types or access frequencies. While these features are useful for providing certain insights, they lack temporal information that captures fine-grained differences in learning behaviors among different students. This study proposes E2Vec, a novel feature representation method based on word embeddings. The proposed method regards operation logs and their time intervals for each student as a string sequence of characters and generates a student vector of learning activity features that incorporates time information. We applied fastText to generate an embedding vector for each of 305 students in a dataset from two years of computer science courses. Then, we investigated the effectiveness of E2Vec in an at-risk detection task, demonstrating potential for generalizability and performance.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17463

WeaveLA: Event Driven Cross-Subtask Latent Memory Weaving for Repetitive Robot Manipulation

作者:

Shoujing Zhu↗Zhenyang Liu↗Fungmiu Wang↗Jiafeng Wang↗Bo Yue↗Guiliang Liu↗Simo Wu↗Xiangyang Xue↗Taiping Zeng↗

Vision-Language-Action (VLA) policies have achieved remarkable single-step manipulation, yet they remain brittle precisely where each stage depends on what was just completed. The core issue is structural: short-window VLAs lack an explicit channel for rouxting information across sub-task boundaries, and existing memory-augmented variants either write at every frame, retrieve from demonstration-time stages, or fire at sub-goal events without performing an explicit sub-task-to-sub-task hand-off into the action expert. We identify the sub-goal completion event as the natural temporal unit for cross-subtask memory hand-off, and present WeaveLA (Weave Latent memory for Vision-Language-Action policies), a cross-subtask memory interface that, on top of a frozen VLA backbone, compresses each completed segment into latent tokens via query-driven attention pooling and routes them directly into the action-generation path of the next sub-task. This event-triggered, action-side design preserves the base policy's short-window interface while adding a lightweight cross-subtask channel. Through stratified evaluation on RoboMME with a $\pi_{0.5}$ backbone, WeaveLA's gains land exactly where the channel is needed: on the hardest repetition slice (SwingXtimes, $N{=}3$), success rises from $0\%$ to $47.8\%$, while single-execution episodes remain unchanged. Per-episode paired analysis confirms the gains are confined to tasks whose causal structure requires cross-subtask information.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16000

GRACE-DS: a Guarded Reward-guided Agent Correction Environment in Data Science

作者:

Aleksandr Tsymbalov↗Danis Zaripov↗Artem Epifanov↗Anastasya Palienko↗

We introduce GRACE-DS, a Guarded Reward-guided Agent Correction Environment in Data Science for pre-deployment evaluation of LLM-powered AutoML agents. GRACE-DS is a set of evaluation metrics in an isolated environment that can be applied to tabular ML tasks specific to a particular organization. It exposes agents to realistic workflow stages, from planning and data inspection through feature engineering, model development, validation, and code repair to final submission, while hidden executable validators measure not only final predictive performance but also leakage avoidance, reproducibility, protocol validity, correction behavior, and reward alignment. The strongest structured regime, flexible iterative interaction (our approach), achieves higher end-to-end normalized hidden-test quality than single-shot generation, unstructured interaction, and restart-based baselines, while also improving protocol-valid completion. Validated across more than 7,000 episodes, these results establish GRACE-DS as a robust platform for assessing the capacity of LLM-based AutoML agents to execute machine learning workflows under production-like conditions and in accordance with organization-specific requirements.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2602.08597

An Attention Mechanism for Robust Multimodal Integration in a Global Workspace Architecture

作者:

Roland Bertin-Johannet↗Lara Scipio↗Leopold Mayti\'e↗Rufin VanRullen↗

arXiv:2602.08597v3 Announce Type: replace Abstract: Robust multimodal systems must remain effective when some modalities are noisy, degraded, or unreliable. Existing multimodal fusion methods often learn modality selection jointly with representation learning, making it difficult to determine whether robustness comes from the selector itself or from full end-to-end co-adaptation. Motivated by Global Workspace Theory (GWT), we study this question using a lightweight top-down modality selector operating on top of a frozen multimodal global workspace. We evaluate our method on two multimodal datasets of increasing complexity: Simple Shapes and MM-IMDb 1.0, under structured modality corruptions. The selector improves robustness while using far fewer trainable parameters than end-to-end attention baselines, and the learned selection strategy transfers better across downstream tasks, corruption regimes, and even to a previously unseen modality. Beyond explicit corruption settings, on the MM-IMDb 1.0 benchmark, we show that the same mechanism improves the global workspace over its no-attention counterpart and yields decent benchmark performance.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12854

Small LLMs for Biomedical Claim Verification: Cost-Effective Fine-Tuning, Structural Dataset Shortcuts, and Cross-Domain Generalization

作者:

Gaurav Kumar↗

Large Language Models such as GPT-4o and GPT-5 achieve strong zero-shot performance on biomedical claim verification, but cost and opacity limit scalable use. We fine-tune three small LLMs: Phi-3-mini (3.8B), Qwen2.5-3B, and Mistral-7B, via QLoRA on SciFact and HealthVer, providing the first study of QLoRA models against GPT-4o and fine-tuned BioLinkBERT encoders. Mistral-7B QLoRA surpasses both GPT-4o and GPT-5 (up to 12% F1 gain) at a fractional cost using just 1,008 training examples. We conduct extensive in-domain and cross-domain evaluation: models trained on SciFact tested on HealthVer and vice versa, at matched sizes to isolate dataset structure from data quantity. We identify a previously unreported structural artifact in SciFact that inflates in-domain scores, and show through bidirectional out-of-domain evaluation that training on structurally sound data enables robust cross-domain transfer. We plan to release all code and adapter checkpoints.

阅读与讨论 → 访问原文 →

12.

arXiv (math.PR) 2026-06-12 DOI: arXiv:2606.13575

Dimension-free Markov–Bernstein inequalities for product measures

作者:

Egor Kosov↗

arXiv:2606.13575v1 Announce Type: cross Abstract: We study dimension-free Markov–Bernstein inequalities for polynomials with respect to product probability measures. In the Gaussian case, for $p\ge4$, we prove that \[ \|\nabla f\|_{L^p(\gamma^n)} \le C(p)d^{\frac12+\theta_p} \|f\|_{L^p(\gamma^n)} \] for every polynomial $f$ of degree at most $d$, where $\theta_p\le \frac{2}{3p}$ and $\theta_p=0$ whenever $p$ is an even integer. Thus, for even integer exponents, we establish the sharp dependence on the degree conjectured by Eskenazis–Ivanisvili. For general $p\ge4$, the estimate improves upon their dimension-free inequality. We also obtain dimension-free Markov–Bernstein inequalities with sharp dependence on the degree for even integer exponents beyond the Gaussian setting. We first prove such estimates for the uniform distribution on the unit cube and then extend them to products of absolutely continuous measures with unimodal densities. Finally, we treat products of one-dimensional Freud measures with densities proportional to $e^{-|t|^{2m}}$.

阅读与讨论 → 访问原文 →

13.

medRxiv (Medicine) 2026-06-22 DOI: HASH:f937e1ca1a25fe6f05229a98b39eb22f

Understanding and Usefulness of Effect Size and Certainty of Evidence: A Cross-sectional Survey of Evidence-Based Practice Competencies Among Registered Dietitians

作者:

Ghosh↗N. R↗Neale↗E. P↗Hand↗R. K↗Ball↗G. D. C↗Riddle↗Klatt↗K. C↗Riviere↗…

Introduction: Understanding of absolute and relative estimates (i.e., effect size), and certainty of evidence corresponding to those estimates, is a fundamental evidence-based practice competency to promote informed clinical decision-making. While research has been conducted in the medical profession, there is no published research on these competencies in the nutrition and dietetics profession. Methods: Among registered dietitians, our main objectives were to assess (1) their understanding and perceived usefulness of three absolute and two relative estimate approaches to assess effect size, (2) their perceived usefulness of certainty of evidence, and (3) factors influencing their understanding and perceived usefulness. We conducted a web-based, cross-sectional survey among dietitians recruited from the Academy of Nutrition and Dietetics (United States). Participants received effect estimates based on hypothetical dietary interventions vs. usual diet for reducing myocardial infarction risk. Results: Of the 11,050 dietitians who received the survey link, 210 participated (2.0% response rate), and only completers (n=114) were included in the analysis. Participants demonstrated a similar understanding of the relative (27.6%) and absolute (27.5%) estimates, with Risk Difference (30.7% correct responses) being the best understood approach and Number Needed to Treat (24.6%) being the least. The understanding of five approaches was not different than random guessing (p>0.05). While perceived usefulness scores were similar between five approaches, they were highest when data was presented as Relative Risk [mean (SD): 4.82 (1.50)]. Dietitians rated the usefulness of certainty of evidence favorably [mean (SD): 5.07 (1.83), on a 7-point scale), and no factors were associated with correct understanding. Conclusion: Dietitians may have limited understanding of how to interpret effect sizes, a finding consistent with surveys of other health professionals. To optimize informed decision-making between dietitians and clients, dietetic programs and continuing education platforms should consider additional training on interpreting effect sizes and certainty of evidence for effect sizes.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14589

When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production LLM Agent Runtime

作者:

Wei Wu↗

arXiv:2606.14589v1 Announce Type: cross Abstract: LLM agent systems increasingly run as long-lived autonomous runtimes: scheduling jobs, calling tools, maintaining memory, and pushing results to humans. We present a longitudinal study of silent failures in one such system: a personal-assistant agent runtime in continuous production since March 2026, with roughly 40 scheduled jobs, 8 LLM providers, a tool-governance proxy, and a knowledge-base memory plane, defended by 4,286 unit tests and 827 governance checks. Over eight weeks we documented 22 incidents with full root-cause postmortems, in which one meta-pattern – a failure whose error signal never reaches a human in actionable form – manifested at least 28 times. We derive a five-class, mechanism-oriented taxonomy: (A) environment and platform quirks, (B) design-assumption mismatches, (C) error swallowing and dilution, (D) chained hallucination and fabrication, (E) operational omission and forensic blind spots. Class D is unique to LLM systems and the most dangerous: the system does not merely fail to report an error – the LLM transforms it into fluent, plausible narrative delivered to the user. We term this fail-plausible: gray failure's differential observability escalated – the observer is not just blind, it is convincingly lied to by the failure itself. Three findings: about 70% of silent failures were caught by human user-view observation, not tests or audits; a retrospective audit of 15 incidents found 0% ex-ante prevention but 87% regression blocking – audits are regression engines, not prediction engines; incident latency (13 hours to 60 days) tracks failure mechanism, not code complexity – the longest-lived failures lived in the seams between components, where no test runs. We describe the resulting defense framework and distill design principles for agent systems whose failures are loud, attributable, and boring. All postmortems and artifacts are public.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2506.17255

UltraSketchLLM: Sub-1-Bit LLM Compression via Sketch and Hardware-Friendly Operators

作者:

Sunan Zou↗Xueting Sun↗Ziyun Zhang↗Guojie Luo↗

arXiv:2506.17255v2 Announce Type: replace-cross Abstract: Large language models (LLMs) require larger GPU memory size these days, necessitating efficient and extreme weight compression methods. Existing compression methods are either theoretically limited by 1 bit per weight or face severe performance degradation and inefficiency. To deploy LLMs in resource-constrained scenarios, we introduce UltraSketchLLM, compressing LLMs with data sketch. It reduces peak GPU memory footprint with a high compression rate down to 0.5 bit per weight. Combined with hardware-friendly implementation, UltraSketchLLM keeps tolerable performance degradation and extremely low latency overhead with 14.9x speedup compared to naive sketch solution.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2603.12901

A theory of learning data statistics in diffusion models, from easy to hard

作者:

Lorenzo Bardone↗Claudia Merger↗Sebastian Goldt↗

arXiv:2603.12901v2 Announce Type: replace-cross Abstract: While diffusion models have emerged as a powerful class of generative models, their learning dynamics remain poorly understood. We address this issue first by empirically showing that standard diffusion models trained on natural images exhibit a distributional simplicity bias, learning simple, pair-wise input statistics before specializing to higher-order correlations. We reproduce this behaviour in simple denoisers trained on a minimal data model, the mixed cumulant model, where we precisely control both pair-wise and higher-order correlations of the inputs. We identify a scalar invariant of the model that governs the sample complexity of learning pair-wise and higher-order correlations that we call the diffusion information exponent, in analogy to related invariants in different learning paradigms. Using this invariant, we prove that the denoiser learns simple, pair-wise statistics of the inputs at linear sample complexity, while more complex higher-order statistics, such as the fourth cumulant, require at least cubic sample complexity. We also prove that the sample complexity of learning the fourth cumulant is linear if pair-wise and higher-order statistics share a correlated latent structure. Our work describes a key mechanism for how diffusion models can learn distributions of increasing complexity.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15822

TrustedARI: Towards Trust-Native Agentic Routing Infrastructure for Agentic AI

作者:

Qi Li↗Zhenhua Zou↗Shuo Li↗Mingwei Xu↗Zhuotao Liu↗

arXiv:2606.15822v1 Announce Type: new Abstract: AI agents increasingly access external models, tools, and services through Agentic Routing Infrastructure (ARI) to manage the overhead of heterogeneous interfaces and fragmented subscriptions. Yet, the architecture of ARI introduces fundamental trust risks: it obtains plaintext access to agent queries and service responses, while leaving agents unable to verify that their queries are routed to intended service providers or that requests and responses remain untampered. To address this problem, we present TrustedARI, the first trust-native agentic routing infrastructure for agentic AI. Architecturally, TrustedARI is built upon three core innovations: (i) an ARI-adapted three-party TLS handshake that enables the agent and ARI to jointly authenticate the service provider through role-specific distribution of TLS key materials; (ii) a privacy-preserving query-construction protocol that allows the agent and ARI to collaboratively construct well-formed queries without exposing their respective private inputs; and (iii) a verifiable billing protocol that supports fair usage-based settlement while preserving the integrity and confidentiality of service responses. We implemented and extensively evaluated a prototype of TrustedARI to validate its performance. Experiments confirm that TrustedARI is highly efficient: our ARI-adapted handshake protocol reduces communication overhead by 39.34% compared to the existing three-party TLS handshake. Furthermore, the privacy-preserving query-construction protocol imposes negligible overhead-averaging 0.19 seconds in computation time and 0.58 MB in communication costs-while the verifiable billing protocol speeds up proof generation by 28.20x. Crucially, TrustedARI is readily deployable without any modification to the service providers.

阅读与讨论 → 访问原文 →

18.

arXiv (quant-ph) 2026-06-17 DOI: arXiv:2606.17548

Kinematic properties of the Pauli equation

作者:

E. E. Perepelkin↗B. I. Sadovnikov↗N. G. Inozemtseva↗V. A. Svetovidov↗

arXiv:2606.17548v1 Announce Type: new Abstract: Based on the Wigner-Vlasov formalism, this paper investigates the kinematic properties of the Pauli equation. It is shown that the probability current associated with the Pauli equation can be represented as a superposition of two currents with certain expansion coefficients. Each of these currents corresponds to a particular component of the spinor. The expansion coefficients effectively serve as weighting functions that determine the probability contribution of the corresponding spinor component. Therefore, each spin projection corresponds to its own probability flux. A new system of the Hamilton-Jacobi equations and also a system of motion equations in electromagnetic fields are obtained, taking into account the interaction between the spin and the magnetic field. To illustrate how these equations can be applied we have investigated the quantum system kinematics in detail using an exact solution of the Pauli equation in the presence of a uniform magnetic field and an asymmetric quadratic potential.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2505.09655

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning

作者:

Xiwen Chen↗Wenhui Zhu↗Peijie Qiu↗Xuanzhao Dong↗Hao Wang↗Haiyu Wu↗Huayu Li↗Aristeidis Sotiras↗Yalin Wang↗Abolfazl Razi↗

Post-training LLMs with Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), has emerged as a paradigm for enhancing mathematical reasoning. However, standard GRPO relies on scalar correctness rewards that are often non-injective with respect to semantic content: distinct reasoning paths receive identical rewards. This leads to a Diversity-Quality Inconsistency, where the policy collapses into a narrow set of dominant modes while ignoring equally valid but structurally novel strategies. To bridge this gap, we propose Diversity-aware Reward Adjustment (DRA), a theoretically grounded framework that calibrates the reward signal using the semantic density of sampled groups. By leveraging Submodular Mutual Information (SMI), DRA implements an Inverse Propensity Scoring (IPS) mechanism that effectively de-biases the gradient estimation. This creates a repulsive force against redundancy, driving the policy to achieve better coverage of the high-reward landscape. Our method is plug-and-play and integrates seamlessly with GRPO variants. Empirical evaluations on five math benchmarks demonstrate that DRA-GRPO consistently outperforms strong baselines, achieving an average accuracy of 58.2% on DeepSeek-R1-Distill-Qwen-1.5B with only 7,000 training samples and $55 cost, highlighting the critical role of diversity calibration in data-efficient alignment. The code is available at https://github.com/xiwenc1/DRA-GRPO.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.20199

Evaluation of Image Matching for Art Skills Assessment

作者:

Asaad Alghamdi↗Michael Poor↗Trung-Nghia Le↗Tam V. Nguyen↗

While some individuals possess a natural talent for drawing, mastering this skill requires dedicated training and practice. Determining one's skill in the art of drawing requires proper comprehensive assessment. In this paper, we propose a method to measure drawing skill by by matching the hand-drawn image with the original template. Existing techniques often involve complex processes. However, advancements in computer vision allow us to train computers to perform these comparisons at a human-like level, thereby resolving the tedious and overwhelming traditional process. Using computer vision applications, determining image similarity involves identifying the level of similarities in an image with a reference image. We have implemented and analyzed the SIFT feature and Siamese network to measure image similarity. Our results indicate that it is feasible to assess art skill levels. Through feature analysis, we found that SIFT-based key point matching provides a more effective means of detecting drawing skills.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.06523

Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory

作者:

Ruida Wang↗Jerry Huang↗Pengcheng Wang↗Xuanqing Liu↗Luyang Kong↗Tong Zhang↗

arXiv:2606.06523v2 Announce Type: replace Abstract: Equipping Large Language Models (LLMs) to execute reliable multi-step workflows has become a central challenge in artificial intelligence. Despite recent advances in LLMs' agentic capabilities, most agent systems still lack formal methods for specifying, verifying, and debugging their workflow and execution trajectories. This challenge mirrors a long-standing problem in mathematics, where the ambiguity of natural languages (NLs) motivates the development of formal languages (FLs). Inspired by this paradigm, we propose **Lean4Agent**, to the best of our knowledge, the first framework that uses Lean4, a dependent-type FL to model and verify agent behavior. **Lean4Agent** launches **FormalAgentLib**, an extensible Lean4 library for formally modeling and verifying agent workflows' semantic consistency under explicit assumptions, and enabling localization of execution-time failures revealed by trajectories. Building on **FormalAgentLib**, we further develop **LeanEvolve**, which applies results in **FormalAgentLib** to revise workflows to enhance its capability. Extensive experiments on a hard problem subset of SWE-Bench-Verified and a subset of ELAIP-Bench across 5 leading LLMs indicate that the verification-passing workflows outperform the failing ones by an average of **11.94%**, and **LeanEvolve** further improves SWE performance by **7.47%** on average. Furthermore, **Lean4Agent** establishes a foundation for a new field of using expressive dependent-type FL to formally model and verify agent behavior.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16524

Neural Bayesian Anomaly Mitigation: A Robust Loss that Doubles as an Unsupervised Contamination Classifier

作者:

S. A. K. Leeney↗W. J. Handley↗H. T. J. Bevins↗E. de Lera Acedo↗

arXiv:2606.16524v1 Announce Type: new Abstract: Engineered robust losses such as Huber, Student-$t$, and generalised cross-entropy make supervised models tolerant of contamination but cannot answer which observations are corrupted. We introduce Neural Bayesian Anomaly Mitigation (NBAM), a general-purpose drop-in loss derived from a Bayesian latent-switch mixture model: the marginal likelihood defines a robust supervised loss, and the associated posterior defines an unsupervised contamination classifier. Like Huber or Student-$t$, NBAM can replace the standard training loss in any supervised pipeline; unlike them, it additionally learns a structured contamination model and returns a calibrated per-sample contamination posterior. A learned input-dependent prior $\pi_\phi(x)$ captures the spatial locality of contamination, so that samples near known corruptions are more likely to be flagged, while an Occam penalty emerges automatically and regularises against over-flagging. On CIFAR-10 with asymmetric label contamination, NBAM recovers the structure of the corruption process without supervision: the contamination posterior separates clean from corrupted samples, and the learned anomaly head identifies the direction of every label-flip pair. Alongside these capabilities, NBAM outperforms the four robust-loss baselines considered here at contamination rates 0.2-0.6.

阅读与讨论 → 访问原文 →

23.

medRxiv (Medicine) 2026-06-11 DOI: HASH:1ca0b596491b006c73a0d32106621d33

Allostatic Load in Endometrial Cancer Disparities

作者:

Bey↗G. S↗Bowen↗M. B↗Wu↗Boykin↗Bernard↗Zhang↗Melendez↗Celestino↗Batsis↗J. A↗…

Background: Endometrial cancer incidence and mortality are increasing, particularly among Black women and for aggressive subtypes. Allostatic load (AL), a composite measure of physiologic dysregulation across metabolic, cardiovascular, and immune systems, varies by racial category and tumor subtype in other cancers. Endometrial cancer is strongly associated with obesity, and it is unknown whether AL scores maintain sufficient heterogeneity to evaluate differences across subgroups or with clinical outcomes. Objective: To describe the performance of AL scoring in endometrial cancer patients and examine associations with tumor characteristics (grade/histology) and survival outcomes. Methods: We evaluated AL among 398 participants newly diagnosed with endometrial cancer. AL score was calculated by assigning 1 point for each ''high-risk'' value (by clinical reference range or distribution-based) for 15 biologic variables for vital signs, anthropometrics, blood-based biomarkers, and medical comorbidities. Results: Distribution-based thresholds for variables were used to preserve heterogeneity in this obesity-dominant context. Overall, 68.7% of Black women had high AL compared to White (56.7%), Hispanic (56.7%), and other race (32.3%) women. Decision tree analyses revealed grade-dependent associations between AL and survival. For women with low-grade tumors, higher AL was associated with poorer overall survival. For high-grade tumors, intermediate AL ([≥]4,

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19595

IHBench: Evaluating Post-Interruption Recovery in Voice Agents with Structured Workflows

作者:

Ahmad Salimi↗Wentao Ma↗Yuzhi Tang↗Dongming Shen↗Mu Li↗Alex Smola↗

arXiv:2606.19595v1 Announce Type: cross Abstract: Voice agents deployed in structured workflows (customer service, healthcare scheduling, account management) must handle frequent user interruptions while maintaining progress through multi-step procedures. Existing benchmarks for speech-capable models focus on the timing of interruptions: barge-in detection, endpointing, and turn-taking dynamics. They leave unmeasured what happens after the interruption: does the agent resume the workflow at the correct step? Does it address the user's interjection? Does it avoid re-delivering content the user already heard? We introduce IHBench (Interruption Handling Benchmark), a benchmark that evaluates post-interruption recovery in voice agents executing state-machine-driven workflows across 10 enterprise domains. Six interruption types are injected at controlled points mid-utterance, with per-interruption evaluation rubrics generated alongside the data. Each interruption is scored on two axes: task fulfillment and recovery quality. We evaluate 27 audio-language model configurations from OpenAI, Google, and the open-weight community. Models vary widely, and recovery quality depends strongly on the interruption type. Across our experiments, closed-weight models are consistently more robust to interruptions than open-weight ones: they win far more often on task fulfillment, degrade roughly 3.3x more slowly as conversations grow longer, and show no audio-versus-text modality gap, whereas the open-weight models lose ground on all three. A human study validates the LLM judge against human annotators, and a cross-benchmark analysis against AudioMultiChallenge indicates that recovery quality is a largely distinct capability axis.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2605.09370

From Detection to Recovery: Operational Analysis on LLM Pre-training with 504 GPUs

作者:

Daemyung Kang↗Eunjin Hwang↗Hanjeong Lee↗HyeokJin Kim↗Hyunhoi Koo↗Jeongkyu Shin↗Jeongseok Kang↗Jihyun Kang↗Jinho Heo↗Joongi Kim↗Junbum Lee↗Jungseung Yang↗…

arXiv:2605.09370v5 Announce Type: replace-cross Abstract: Large-scale AI training is fundamentally a distributed systems problem, where hardware failures are routine operating conditions rather than rare exceptions, yet public operational evidence from production training clusters remains limited. This report presents an empirical analysis of a 63-node NVIDIA B200 production cluster (504 GPUs), using 55 days of Prometheus time-series data and 73 days of operational logs covering 224 multi-node training sessions. The environment is cross-organizational: five parties (SKT, Upstage, Lablup, NVIDIA Korea, VAST Data) share a unified monitoring pipeline. This enabled joint diagnosis of a 60-node-scale storage I/O bottleneck absent in 2-4-node tests, a production-scale phenomenon no single team could isolate alone. We perform three quantitative analyses yielding four findings. First, over 751 Prometheus metrics and 10 XID-identified GPU failures, no single metric is consistently dominant across failure types, motivating multi-signal detection. Second, 523 checkpoint events trace the save/load path from GPU VRAM to the NFS server: restart loading reaches 21.5% of maximum read bandwidth (700 GB/s) and save bursts 16.0% of maximum write bandwidth (250 GB/s), with NFS/RPC queueing and transport-layer backlog rising together. Third, across 224 sessions over 73 days, node exclusions concentrate so the top 3 of 63 nodes account for over 50%. Fourth, auto-retry chain analysis shows a 33.3% success rate over 12 chains (73 attempts), 2.7x the 12.5% manual rate, with a median retry interval of 11 minutes (IQR 10-11). All analyses are grounded in production infrastructure providing session-level workload management, GPU-centric scheduling, and unified observability.

阅读与讨论 → 访问原文 →