探索全球前沿学术脉络

01.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13925

Sorries Are Not the Hard Part: An Expert-Review Case Study of a Semi-Autonomous Formalization

作者:

Vasily Ilin↗Brian Nugent↗

arXiv:2606.13925v1 Announce Type: new Abstract: Large language models can often close proof gaps in interactive theorem provers, but a verified theorem is not the same thing as a reusable library contribution. We study this distinction through a detailed case study: a semi-autonomous formalization of Grothendieck's vanishing theorem. The initial version compiles with no sorries, but an expert review found serious problems in definitions, theorem generality, file organization, and the API. We then ran a review-driven refactor and compression process and obtained a second expert review. The before-and-after comparison shows a sharp split: agents adapted well to local, mechanically checkable feedback, but remained weak at choosing definitions and designing APIs. We argue that autoformalization should be evaluated not only by closed sorries, but by whether the resulting formalization survives expert review.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.10642

PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models

作者:

Emma Kasteleyn↗Timo Maier↗Axel Lauer↗Veronika Eyring↗Pierre Gentine↗Ana Lucic↗

arXiv:2606.10642v2 Announce Type: replace Abstract: Machine learning weather prediction (MLWP) models have achieved impressive forecasting performance at a small fraction of the computational costs required for traditional physics-based methods. However, they are primarily (1) data-driven and (2) evaluated using pixel-wide error metrics (e.g., RMSE), so there are no guarantees that their forecasts are consistent with known physical laws. We introduce PhysMetrics$.$Weather, an evaluation framework that assesses the physical realism of MLWP models across three types of metrics: conservation, spectral, and dynamical. By quantifying physical realism, this tool guides the development of physics-informed architectures and helps evaluate whether MLWP models are reliable for operational use. Our framework is available on Github at https://github.com/Emmakast/PhysMetrics.Weather.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13349

From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent

作者:

Haishuo Fang↗Yue Feng↗Iryna Gurevych↗

Large language models (LLMs) have shown promise in automating scientific peer review. However, existing approaches often struggle to generate in-depth reviews supported by concrete evidence. We argue that a key limitation is the lack of flexibility to proactively investigate suspicious parts of a paper based on accumulated evidence, as human reviewers do. In this paper, we explore how to enable an LLM-based review agent to perform such proactive investigation. We find that this can be naturally formulated as a Markov Decision Process (MDP), and propose ProReviewer, a scientific peer review agent that proactively reviews a paper guided by a maintained, structured review log. The structured review log serves as a workspace for the agent to track evidence and intermediate findings collected during review. Experiments show that ProReviewer with an 8B backbone, trained by supervised fine-tuning and optimized by reinforcement learning, achieves the highest average score across five quality dimensions, outperforming prompt-based methods with much larger frontier LLMs by up to 39% and the strongest fine-tuned baseline by 16% relatively. It also attains the highest win rates against baselines in human evaluation.

阅读与讨论 → 访问原文 →

04.

medRxiv (Medicine) 2026-06-18 DOI: HASH:c71c21826f565dbdc5b5c752c4b75e1a

Automated Airways Characterization and Assessment of Cystic Fibrosis from CT Imaging

作者:

Chong Chie↗J. A. K. H↗Cooper↗M. L↗Persohn↗S. A↗Burton↗C. P↗Salama↗Territo↗P. R↗

Background Advancements in medical imaging have enabled non-invasive diagnosis and staging of cystic fibrosis (CF) using CT scans, revealing dilated airways, an increased number of visible airways, and airway generation splits in these patients. However, manual characterization of airways remains time-consuming and challenging due to the numerous structural changes, thereby limiting clinical feasibility. This study aims to develop an automated algorithm to characterize airways from segmented lung CT scans and apply this to a retrospective population. This approach reduces the time required to analyze images and obtain disease-staging results. Methods This framework consists of two stages. The first stage extracts and skeletonizes the airway tree from lung CTs, while the second stage measures lung features, including airway volumes, branch counts, generation splits, diameters, and cross-sectional areas. This permits comprehensive characterization for use in clinical assessment. Results The airways analysis was performed on 169 CT volumes ranging in age from 6 to 18 years of age, revealing substantial differences in detected airway branches, generation splits, and normalized airway volume between the control and CF groups. The framework also measures airway diameters and cross-sectional areas, revealing an increase in the number of small airways in cystic fibrosis patients, due to early bronchiectasis. These findings align with previous research and demonstrate the framework's ability to accurately quantify airway changes in patients with CF. Discussion The framework extracts entire airway trees, facilitating measurements of volume, branch count, diameters, and cross-sectional areas, which change with CF severity and/or treatment. However, partial lung atelectasis can limit the accuracy of airway detection in moderate-to-severe cases. Funding NIA U54 AG054345 and NIA R21 AG07857501

阅读与讨论 → 访问原文 →

05.

medRxiv (Medicine) 2026-06-17 DOI: HASH:91e4e28b33e66a1a760ee15a8237b090

A non-invasive liquid biopsy resolves the diagnostic blind spot in chronic kidney disease

作者:

Nishimura↗Harita↗Hirakawa↗Takizawa↗Fujishiro↗Ogawa↗Kajiho↗Kanda↗Kushima↗Omori↗Hamasaki↗Gotoh↗…

Chronic kidney disease is a major global health burden, and its early detection is critical for delaying progression to kidney failure using recently developed targeted therapies. However, current diagnostic screening relies heavily on blood markers that are confounded by muscle mass, and on urine tests that frequently miss structural damage occurring without protein leakage. This creates a critical diagnostic blind spot that hinders timely intervention. Here we show a non-invasive liquid biopsy platform that quantifies a specific protein marker, MUC1, on urinary extracellular vesicles to accurately assess renal parenchymal integrity. By bypassing the systemic metabolic noise of traditional blood tests, our assay provides a remarkably stable, person-specific functional signature. Following extensive validation across diverse cohorts, our longitudinal analysis demonstrated that the discrepancy between this novel urine-based readout and standard blood tests unmasks hidden renal vulnerability, successfully predicting rapid functional decline. By comprehensively evaluating both tubular and glomerular integrity from a single spot urine sample, these findings establish a completely non-invasive, highly scalable prescreening tool that resolves the diagnostic blind spot, enabling broader early detection strategies and ushering in a new era of proactive risk management.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2604.10242

MedVeriSeg: Teaching LISA-Like Medical Segmentation Models to Verify Query Validity Without Extra Training

作者:

Qinyue Tong↗Xiaozhen Wang↗Ziqian Lu↗Jun Liu↗Yunlong Yu↗Zheming Lu↗

Despite recent progress in text-prompt-based medical image segmentation, existing LISA-like MLLM-based methods typically generate masks regardless of whether the target specified in the query is present, leading to hallucinated segmentation. In this work, we propose MedVeriSeg, a training-free query verification framework that enables LISA-like medical segmentation models to reject false segmentation queries. MedVeriSeg first quantifies the response quality between the [SEG] token and image features through a Similarity Response Quality Scoring Module. To further improve robustness, it employs a Lightweight Routed Multi-Agent Verification Module, which fuses quantitative score evidence with qualitative agent evidence to comprehensively verify the validity of the query. To support systematic evaluation, we construct MedVeriSeg-Bench, a benchmark designed for query verification in medical image segmentation. Experimental results demonstrate that MedVeriSeg effectively identifies false segmentation queries and reduces hallucinated segmentation, while maintaining a high acceptance rate for valid queries, thereby largely preserving the segmentation utility of LISA-like medical segmentation models.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15441

Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment

作者:

Lipeng He↗Yihan Wang↗Jiawen Zhang↗N. Asokan↗

arXiv:2606.15441v1 Announce Type: cross Abstract: Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses report near-zero attack success rate on static benchmarks, yet recent adaptive evaluations show that these results collapse once the attacker is allowed to optimize against the deployed defense. In this work, we trace this collapse to two failure modes. First, existing defense methods are confined to recognizing specific attack patterns, rather than assessing whether the intent of every embedded instruction is relevant to the user task. Second, training-based defenses, which otherwise offer the strongest safety-utility trade-off, assemble their adversarial examples from a handful of hand-crafted templates, and the resulting defender fails to generalize outside that narrow strategy distribution. To address these gaps, we propose RETA, a training-based method that grounds defense decisions on the user tasks rather than attacker-controlled data. At each tool-output step, the defender undertakes chain-of-thought reasoning verifying that its actions are consistent with the user task. Leveraging red-teaming, a simulated attacker synthesizes adversarial training data and receives a dictionary-learning diversity reward, achieving broad coverage of injection-reformulation strategies. Together, these allow the defender to be optimized via multi-objective reinforcement learning and achieve better safety-utility trade-off. Across six black-box adaptive attacks, RETA keeps every per-attack ASR below 10%, with average ASR of 2.92% and 3.75% on the two target models, while preserving most utility under attack and on clean inputs.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.12120

A Riemannian Approach to Low-Rank Optimal Transport

作者:

Pratik Jawanpuria↗Bamdev Mishra↗

arXiv:2606.12120v1 Announce Type: new Abstract: Low-rank optimal transport (OT) mitigates the quadratic scaling of classical solvers, yet existing approaches rely heavily on first-order mirror-descent updates that require careful hyperparameter tuning and ignore the optimization landscape's curvature. To address these limitations, we propose a unified Riemannian geometric framework for low-rank OT, modeling balanced and unbalanced rank-$r$ positive factored couplings as novel smooth embedded submanifolds of the positive orthant. By equipping these manifolds with the Fisher-Rao product metric, we derive tractable formulations for Riemannian projectors, retractions, and Hessian-vector products. Our cost-agnostic framework seamlessly extends to linear OT, Gromov-Wasserstein (GW), fused GW, and their unbalanced counterparts. For balanced OT, our geometric ingredients are computed via efficient conjugate-gradient and iterative Bregman updates. For the unbalanced OT, our operations elegantly reduce to closed-form scalings, completely eliminating inner iterative loops. In both regimes, per-iteration complexity scales linearly with dataset size, and we provide a rank-sufficiency certificate for global optimality verification. Extensive experiments across a range of problem sizes demonstrate that our regularization-free first- and second-order solvers achieve faster convergence and superior performance over existing state-of-the-art low-rank OT solvers.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2410.16089

Multi-Sensor Fusion for UAV Classification Based on Feature Maps of Image and Radar Data

作者:

Nikos Sakellariou↗Antonios Lalas↗Konstantinos Votis↗Dimitrios Tzovaras↗

arXiv:2410.16089v2 Announce Type: replace Abstract: The unique cost, flexibility, speed, and efficiency of modern UAVs make them an attractive choice in many applications in contemporary society. This, however, causes an ever-increasing number of reported malicious or accidental incidents, rendering the need for the development of UAV detection and classification mechanisms essential. We propose a methodology for developing a system that fuses already processed multi-sensor data into a new Deep Neural Network to increase its classification accuracy towards UAV detection. The DNN model fuses high-level features extracted from individual object detection and classification models associated with thermal, optronic, and radar data. Additionally, emphasis is given to the model's Convolutional Neural Network (CNN) based architecture that combines the features of the three sensor modalities by stacking the extracted image features of the thermal and optronic sensor achieving higher classification accuracy than each sensor alone.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13556

Is It You or Your Environment? A Bayesian Inference Framework for Genomically-Anchored Personalized Physiological Interpretation

作者:

Aruna Dey↗Suraj Biswas↗

arXiv:2606.13556v1 Announce Type: new Abstract: Personalized health AI systems face a fundamental cold-start problem: machine learning models for physiological interpretation require weeks of individual behavioral data before they can distinguish constitutional variation from environmentally driven deviation. We propose a solution grounded in causal inference and Bayesian prior design. An individual's genomic profile serves as an exogenous genetic anchor – a domain-informed, personalized prior that is fixed at conception, immune to reverse causation, and available before a single behavioral observation is collected. The anchor initializes a Bayesian belief state over an individual's physiological set point G-hat = mu + sum(beta_i * g_i), where beta_i are GWAS-derived effect sizes and g_i are risk-allele counts. Each incoming physiological measurement P produces a non-constitutional deviation delta = P - G-hat that separates the signal attributable to environment and state from the constitutionally fixed baseline. As behavioral data accrue, the prior decays according to G-hat_t = w(t)*G-hat_genomic + [1-w(t)]*P-bar_t, transitioning from genome-dominated to empirical-baseline-dominated inference. The same observed HRV of 55 ms generates a suppression hypothesis for a person whose prior predicts 80 ms, and an enhancement hypothesis for a person whose prior predicts 30 ms – a reversal impossible without a personalized anchor. We develop this architecture across six physiological domains, grading genomic priors by evidence strength, distinguishing robustly replicated anchors (FTO, FADS1/2, FKBP5) from contested candidate genes (SLC6A4, MAOA, DRD2). We address the inference boundary between association, Mendelian randomization, and individual token causation, and define four constraints for deployment: evidence-graded priors, dynamic decay, ancestry-matched effect sizes, and attribution rather than deterministic output.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.20303

GEN-Guard: Correcting Generalization Failures for Deployable Federated Surgical AI

作者:

Julia Alekseenko↗Pietro Mascagni↗AISafeChole Consortium↗Nicolas Padoy↗

Federated Learning (FL) in surgical video AI enables collaborative model training without sharing sensitive data. However, standard evaluation practices - selecting the "best" global model based only on validation data from participating hospitals - can lead to suboptimal deployment choices. We identify this critical failure mode as performance leakage, where the selected model overfits internal federation data and fails to generalize to unseen institutions. We propose GEN-Guard, a practical post-hoc framework to detect and correct generalization failures in federated surgical AI. It integrates Generalization Detection via Client-Blocked Evaluation (CBE), which validates performance on isolated client distributions to prevent performance leakage, and Generalization Correction through Disagreement-Aware Distillation (DAD), which learns adaptive feature-level corrections for cross-institutional robustness. Both components operate after standard FL convergence while providing robust support for zero-shot adaptation to unseen environments. We first quantify the severity of performance leakage, observing Model Selection Failures (MSFs) exceeding 80% under standard evaluation. GEN-Guard is evaluated on two multi-center clinical challenges: surgical phase recognition in laparoscopic cholecystectomy and polyp segmentation in colonoscopy. Across both datasets, GEN-Guard consistently corrects these failures, improving in-federation F1 scores by up to 2 points, unseen-institution performance by up to 3 points, and worst-case institutional performance by 3-9 points. Performance leakage represents a systematic and previously under-recognized risk in federated surgical AI. GEN-Guard provides a practical solution for detecting and correcting such failures. By improving cross-institutional robustness and zero-shot generalization, it strengthens the reliability of FL for real-world surgical deployment.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20068

Process-Verified Reinforcement Learning for Theorem Proving via Lean

作者:

Minsu Kim↗Se-Young Yun↗

arXiv:2606.20068v1 Announce Type: new Abstract: While reinforcement learning from verifiable rewards (RLVR) typically has relied on a single binary verification signal, symbolic proof assistants in formal reasoning offer rich, fine-grained structured feedback. This gap between structured processes and unstructured rewards highlights the importance of feedback that is both dense and sound. In this work, we demonstrate that the Lean proof assistant itself can serve as a symbolic process oracle, supplying both outcome-level and fine-grained tactic-level verified feedback during training. Proof attempts are parsed into tactic sequences, and Lean's elaboration marks both locally sound steps and the earliest failing step, yielding dense, verifier-grounded credit signals rooted in type theory. We incorporate these structured rewards into a GRPO-style reinforcement learning objective with first-error propagation and first-token credit methods that balances outcome- and process-level advantages. Experiments with STP-Lean and DeepSeek-Prover-V1.5 show that tactic-level supervision outperforms outcome-only baselines in most settings, delivering improvements on benchmarks such as MiniF2F and ProofNet. Beyond empirical gains, our study highlights a broader perspective: symbolic proof assistants are not only verifiers at evaluation time, but can also act as process-level reward oracles during training. This opens a path toward reinforcement learning frameworks that combine the scalability of language models with the reliability of symbolic verification for formal reasoning.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2602.04789

Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention

作者:

Chengtao Lv↗Yumeng Shi↗Yushi Huang↗Ruihao Gong↗Shen Ren↗Wenya Wang↗

Advanced autoregressive (AR) video generation models have improved visual fidelity and interactivity, but the quadratic complexity of attention remains a primary bottleneck for efficient deployment. While existing sparse attention solutions have shown promise on bidirectional models, we identify that applying these solutions to AR models leads to considerable performance degradation for two reasons: isolated consideration of chunk generation and insufficient utilization of past informative context. Motivated by these observations, we propose \textsc{Light Forcing}, the first sparse attention solution tailored for AR video generation models. It incorporates a Chunk-Aware Growth mechanism to quantitatively estimate the contribution of each chunk, which determines their sparsity allocation. This progressive sparsity increase strategy enables the current chunk to inherit prior knowledge in earlier chunks during generation. Additionally, we introduce a Hierarchical Sparse Attention to capture informative historical and local context in a coarse-to-fine manner. Such two-level mask selection strategy (i.e., frame and block level) can adaptively handle diverse attention patterns. Extensive experiments demonstrate that our method outperforms existing sparse attention in quality (e.g., 84.5 on VBench) and efficiency (e.g., $1.2{\sim}1.3\times$ end-to-end speedup). Combined with other efficient solutions, \textsc{Light Forcing} further achieves a $2.0{\sim}3.0\times$ end-to-end speedup across diverse GPUs (e.g., 27.4\,FPS on RTX 5090 and 33.9\,FPS on H100). Code is released via this \href{https://github.com/chengtao-lv/LightForcing}{link}.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20107

Quantile of Means: A Bonus-Free Ensemble Method for Minimax Optimal Reinforcement Learning

作者:

Asaf Cassel↗Aviv Rosenberg↗

arXiv:2606.20107v1 Announce Type: new Abstract: Optimal Reinforcement Learning (RL) algorithms typically rely on carefully constructed count-based uncertainty estimates to drive exploration. Although theoretically sound, such estimates are hard to compute in practical settings and therefore offer limited insight for designing exploration heuristics. Meanwhile, ensembling has emerged as a practical approach, but remains without theoretical justification. Building on a recent ensemble-based method for Multi-Armed Bandits, we propose a quantile-based ensemble method for finite-horizon Markov Decision Processes (MDPs). Our simple count-free approach achieves optimal variance-dependent regret bounds, providing theoretical grounding for ensemble-based exploration in RL.

阅读与讨论 → 访问原文 →

15.

arXiv (math.PR) 2026-06-16 DOI: arXiv:2606.15178

The distribution of the de Moivre experiment

作者:

Hac\`ene Belbachir↗Hamza Zeggada↗

arXiv:2606.15178v1 Announce Type: new Abstract: In this paper, we focus on de Moivre random experience which allows us to introduce the $ s- $Bernoulli distribution and the bi$ ^s $nomial distribution. We present some probabilistic properties such as the expectation, the variance, the skewness and kurtosis coefficients, the moments and the generating functions. Then we establish that for $ s\in\mathbb{N} $, the bi$ ^s $nomial distribution converges to a limiting Poisson and normal distributions when $ n\rightarrow\infty. $

阅读与讨论 → 访问原文 →

16.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2604.03146

Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization

作者:

Chiheb Yaakoubi↗Cosme Louart↗Malik Tiomoko↗Zhenyu Liao↗

arXiv:2604.03146v3 Announce Type: replace-cross Abstract: We study high-dimensional convex empirical risk minimization (ERM) under general non-Gaussian data designs. By heuristically extending the Convex Gaussian Min-Max Theorem (CGMT) to non-Gaussian settings, we derive an asymptotic min-max characterization of key statistics, enabling approximation of the mean $\mu_{\hat{\theta}}$ and covariance $C_{\hat{\theta}}$ of the ERM estimator $\hat{\theta}$. Specifically, under a concentration assumption on the data matrix and standard regularity conditions on the loss and regularizer, we show that for a test covariate $x$ independent of the training data, the projection $\hat{\theta}^\top x$ approximately follows the convolution of the generally non-Gaussian distribution of $\mu_{\hat{\theta}}^\top x$ with an independent centered Gaussian variable of variance $\mathrm{tr}(C_{\hat{\theta}} \mathbb{E}[xx^\top])$. This result clarifies the scope and limits of Gaussian universality for ERMs. Additionally, we prove that any $\mathcal{C}^2$ regularizer is asymptotically equivalent to a quadratic form determined solely by its Hessian at zero and gradient at $\mu_{\hat{\theta}}$. Numerical simulations across diverse losses and models are provided to validate our theoretical predictions and qualitative insights.

阅读与讨论 → 访问原文 →

17.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2606.14422

Jones-matrix analysis of phase accumulation in a linear-optical multi-pass interferometer

作者:

Byoung S. Ham↗

arXiv:2606.14422v1 Announce Type: new Abstract: Quantum information science has traditionally relied on nonclassical resources, such as entangled photon pairs and squeezed states, to achieve measurement performance beyond classical limits. Here, we revisit the multi-pass photonic scheme reported in Nature 450, 393 (2007) to clarify the physical origin of the observed superresolution and the associated claim of supersensitivity. Using a rigorous Jones-matrix formalism, we show that the round-trip evolution of the HQMQ linear optics unit is equivalent to the product of two reflections in polarization space, resulting in an effective rotation operator. This equivalence reveals that the accumulated phase arises from coherent polarization-state rotation on the Poincare'e sphere. The resulting phase accumulation is interpreted geometrically as a progressive realignment of the polarization state during successive forward and backward propagations. To validate the theoretical model, a classical-wave implementation is experimentally conducted, analyzed, and compared with the corresponding Jones-matrix solution. Finally, the scaling behavior of the Fisher information is analyzed to examine the origin of the claimed supersensitivity. The results are further compared with a recently developed coherence de Broglie wavelength framework, which achieves identical superresolution through repeated coherent interactions in a cascaded interferometeric architecture.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16988

Agent trajectories as programs: fingerprinting and programming coding-agent behavior

作者:

Hamidah Oderinwale↗

arXiv:2606.16988v1 Announce Type: cross Abstract: Benchmark scores tell you what an agent got right; they do not tell you how it got there. In this work, we introduce methods for comparing agents procedurally in different contexts, where the model, tasks, and approaches vary. We compare ten agents and find that they are identifiable by their behavioral habits, which we define as fingerprints: a probe over these procedural signatures attributes an unseen trajectory to the correct agent at 85.7% accuracy, controlling for leakage across tasks. We develop procedural representations for agent problem-solving procedures with an emergent vocabulary induction technique that is meant to be maximally compressive to avoid surface-level variation while being expressive enough to unveil the quirks of the models' patterns. We apply our framework to the software engineering evaluation dataset SWE-Bench to study the structural distinctness of agent trajectories and find that behavior is most similar between models from similar release periods and those that are distilled from one another (e.g., a distilled student model and its teacher have a Jensen-Shannon divergence of 0.25, about half the distance between other model pairs). As more models saturate evaluations, we believe that it will be important to probe model behavior along more holistic dimensions than success rates alone. We introduce ProcGrep, a library for auditing and evaluating agents for how they approach tasks at a procedural level given their traces in a top-down fashion. We believe this work has a range of applications to help developers work with and program coding agents, such as task-aware model routing, agent monitoring, and finer-grained cost analysis.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2605.20531

Pseudo-Formalization for Automatic Proof Verification

作者:

Slim Barkallah↗Luke Bailey↗Kaiyue Wen↗Mohammed Abouzaid↗Tengyu Ma↗

arXiv:2605.20531v2 Announce Type: replace-cross Abstract: Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning. Fully formal proofs, in languages like Lean, are easy to verify because they are unambiguous and modular. Most proofs, particularly those written by AI systems, have neither property, and translating them into formal languages remains challenging in many frontier math settings. We propose Pseudo-Formalization (PF), a proof format that captures the modularity and precision of formal proofs while retaining the flexibility of natural language. A Pseudo-Formal proof is decomposed into self-contained modules, each stating its premises, conclusion, and proof in natural language. To verify the correctness of a regular natural language proof, an LLM translates it to Pseudo-Formal and then verifies each module independently, an algorithm we call Block Verification (BV). We evaluate PF+BV on two benchmarks spanning olympiad and research-level mathematics, where it pareto-dominates LLM-as-judge baselines on error-finding precision and recall. To support future work, we release our research-level proof verification benchmark ArxivMathGradingBench.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11688

Goal-Autopilot: A Verifiable Anti-Fabrication Firewall for Unattended Long-Horizon Agents

作者:

Youwang Deng↗

Long-horizon LLM agents are not trusted to run unattended: with no human watching, they confidently report success they never verified. We treat honesty – bounding what an agent may claim at termination – as a first-class metric for unattended autonomy, distinct from capability. We present Autopilot, an execution model that makes silent fabricated success structurally impossible rather than merely rarer. Autopilot externalizes all working state into a durable, gated finite-state machine that a scheduler advances one stateless tick at a time; a hard floor forbids any terminal "done" claim whose falsifiable gate did not actually execute and pass. We prove a No-False-Success theorem – under gate soundness, floor enforcement, and plan coverage, termination implies the goal holds – whose only trust points are empirically measurable, and show the worst case degrades to an honest stall, never a fabricated success. Because each tick rehydrates only the state machine, per-step context cost is constant in the horizon. Across a 3,150-cell paired corpus (70 tasks $\times$ 3 systems $\times$ 3 models $\times$ 5 seeds, including 50 SWE-bench Lite tasks across 11 OSS repos), Autopilot fabricates on 0.95% of cells [95% CI 0.38–1.62] while Reflexion and StateFlow baselines fabricate on 8.10% [6.48–9.81] and 25.05% [22.48–27.62] respectively. The headline contrast lives in the hard regime: on SWE-bench Lite, the firewall reduces fabrication from 33.7% (StateFlow) to 0.67%, a paired difference of $-33.07$ pp [95% CI $-36.53, -29.73$]. The mechanism is the gate, not the model: all ten Autopilot fabrications come from the strongest model, while two weaker mid-tier models never fabricate across 700 paired cells. The firewall trades coverage for honesty by design – an honest stall is recoverable; a confident wrong output shipped downstream is not.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13676

Modality Forcing for Scalable Spatial Generation

作者:

Bardienus Pieter Duisterhof↗Deva Ramanan↗Jeffrey Ichnowski↗Justin Johnson↗Keunhong Park↗

Text-to-image (T2I) models contain rich spatial priors. Synthesizing photorealistic, cluttered scenes requires an understanding of geometry, including perspective and relative scale. Prior works adapt T2I models to leverage this prior for depth prediction, but they require dense depth data and involve complex recipes. We propose Modality Forcing, a simple, scalable post-training recipe for joint image-depth generation using a single DiT trained on sparse depth data. Modality Forcing enables conditional and joint generation of image and depth in any permutation by assigning separate noise levels per modality. Per-modality decoders let us train on sparse, real-world depth and achieve strong, generalizable depth prediction. We further show that Modality Forcing inherits the scalability of T2I pre-training: by training a set of T2I models from scratch (370M to 3.3B parameters), we find that larger models trained on more image data produce more accurate depth. Our strongest model is competitive with state-of-the-art monocular depth estimators and reduces AbsRel by 57% relative to existing joint image-depth generative models. These results provide strong evidence that image generation is a scalable pre-training objective for spatial perception. https://modality-forcing.github.io/

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11835

Designing AI-Supported Focus Groups: A Role x Modality Playbook

作者:

Zhiqing Wang↗Steven Dow↗

arXiv:2606.11835v1 Announce Type: cross Abstract: Collecting participants' lived experiences is central to design research. Focus groups are uniquely valuable because participants not only share individual accounts but also respond to one another, surfacing comparison, disagreement, and collective sensemaking. However, focus groups are resource-intensive and highly sensitive to facilitation: moderators must probe for specificity, balance participation, manage topic flow, and sustain psychological safety, and subtle facilitation choices can shape what becomes salient. Recent HCI work and commercial meeting tools show that generative AI can scaffold live conversation through prompting, turn regulation, thematic mapping, and real-time summarization. Yet UXR teams lack a clear map of what these capabilities mean in focus groups and what methodological risks they introduce. We synthesize AI supports for live conversation and translate them into a focus-group-specific playbook organized by AI role (tool, co-host, host) and modality (text, voice, embodied).We synthesize prior work on AI-supported live conversation and propose a focus-group-specific playbook of AI supports organized by role (tool, co-host, host) and modality (text, voice, embodied). We characterize interactional trade-offs and identify open questions for evaluating AI-supported focus groups as methodological configurations.

阅读与讨论 → 访问原文 →

23.

arXiv (quant-ph) 2026-06-19 DOI: arXiv:2606.19430

Solving Nonequilibrium Dynamics via Influence Matrix Bootstrap: Floquet-PXP Model

作者:

Xiao-Yang Yang↗He-Ran Wang↗Zhong Wang↗

arXiv:2606.19430v1 Announce Type: new Abstract: Studies of integrable systems have profoundly deepened the fundamental understanding of quantum many-body physics. While equilibrium properties such as ground states and thermodynamics can often be characterized efficiently, accurately characterizing nonequilibrium integrable dynamics remains a significant challenge. Here, we address this problem in the "Rule 201" quantum cellular automaton, an integrable Trotterization of the PXP Hamiltonian. Using the tensor-network approach of the influence matrix, we develop local conditions called generalized zipper conditions that allow exact solutions of local dynamics. We also introduce a numerical bootstrap method for solving influence matrices with finite but relatively large bond dimensions. This uncovers a rich landscape of nonequilibrium behavior exhibiting initial-state dependence. As an example, we investigate the fate of persistent oscillating dynamics under local non-integrable perturbations, and present analytical results for non-thermal relaxation constrained by conservation laws. We also obtain numerically exact results for entanglement growth across a broad class of initial states. Furthermore, from an information-theoretic perspective, we identify a refined structure of multitime correlations termed the hidden Markov order: the memory encoded in the dynamics separates into finite-length and long-range distributed components, which becomes transparent in an exact split-index matrix-product-state representation of the influence matrix. Our approach enables unified investigations of nonthermalizing and thermalizing regimes of nonequilibrium dynamics within a single analytically tractable model, and can be tested experimentally in state-of-the-art quantum simulators such as Rydberg atom arrays.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2605.08827

Mental Health AI Safety Claims Must Preserve Temporal Evidence

作者:

Srimonti Dutta↗Ratna Kandala↗

arXiv:2605.08827v2 Announce Type: replace Abstract: The safety of mental health AI is often judged at the wrong temporal scale. Current evaluations typically score isolated responses, endpoint outcomes, or aggregate dialogue quality, while clinically consequential failures may arise from the order and accumulation of interactions themselves, including delayed escalation, repeated reinforcement, dependency formation, failed repair, and gradual deterioration across turns. This paper argues that this mismatch is not merely a limitation of evaluation coverage but a source of invalid safety conclusions. We introduce Temporal Safety Non-Identifiability, a formal account of why safety properties that depend on sequence, timing, accumulation, or recovery cannot be certified by protocols that discard those features. From this formalization, we develop SCOPE (Safety Claims Over Preserved Evidence) as a general principle for aligning safety claims with the evidence an evaluation actually retains, and instantiate it as SCOPE-MH, a mental-health instantiation of this reporting standard. We operationalize SCOPE-MH through a proof-of-concept on the AnnoMI dataset of expert-annotated motivational interviewing conversations, which reveals mechanisms of failure that per-turn behavior scoring does not represent. We propose SCOPE-MH as a diagnostic complement to existing evaluation infrastructure and argue that evaluation preserving temporal evidence is necessary, not optional, for safety-critical mental health AI deployment.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2507.07574

Beyond the Linear Separability Ceiling: Aligning Representations in VLMs

作者:

Enrico Vompa↗Tanel Tammet↗Mohit Vaishnav↗

A challenge in advancing Visual-Language Models (VLMs) is determining whether their failures on abstract reasoning tasks, such as Bongard problems, stem from flawed perception or faulty top-down reasoning. To disentangle these factors, we introduce a diagnostic framework centered on the Linear Separability Ceiling (LSC), the performance achievable by a linear classifier on a VLM's raw visual embeddings. Applying this framework to state-of-the-art VLMs, we uncover a pervasive ''alignment gap'', where most models fail to generatively outperform the linear separability of their representations. We find that the few models surpassing this ceiling do so via two mechanisms: by further refining visual representations into a more linearly separable format or by executing non-linear decision logic. We demonstrate that this bottleneck is not a fundamental limitation but a solvable visual alignment issue. Our method augments standard next-token prediction with a contrastive objective to restructure the visual manifold into a more one-dimensionally linear geometry, improving image-to-image comparison and enabling models to significantly surpass the LSC on abstract compositional reasoning tasks.

阅读与讨论 → 访问原文 →