中 EN
登录 注册账户

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达，利用大语言模型自动生成交叉领域文献分析简报。

登录 注册账户
01.
arXiv (CS.AI) 2026-06-24

LLMs Prompted for Legal Context Object More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context

作者:
Anastasiia Kucherenko↗Fran\c{c}ois Brouchoud↗Dimitri Percia David↗Andrei Kucharavy↗

arXiv:2606.24585v1 Announce Type: new Abstract: While the validity of LLMs' use in the legal context remains subject to ethical and legal debate, legal professionals are already experimenting with personal LLMs, if only for translation and reformulation. However, even such a seemingly innocuous use can introduce biases through case processing speed if LLM assistants selectively refuse assistance on certain topics. To better anticipate such biases, we investigate several modern small LLMs that are most likely to be used as on-device assistants, to assess the impact of overrefusal on legal prompts. Surprisingly, we find that authority-style prefixes (``you are acting as an assistant of the national supreme court'', ``[...] defense lawyer'') systematically increase refusal rates by 2–20x over the no-prefix baseline, while a known role-play jailbreak prefix shows mixed effects, sharply increasing refusals in some models and barely shifting them in others. The finding suggests that small on-prem deployable LLMs are unstable under contextual framings that a real institutional user might naturally introduce, and further investigation is essential to minimize opportunities for bias.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.CV) 2026-06-17

A geometric and deep learning reproducible pipeline for monitoring floating anthropogenic debris in urban rivers using in situ cameras

作者:
Gauthier Grimmer↗Romain Wenger↗Cl\'ement Flint↗Germain Forestier↗Gilles Rixhon↗Valentin Chardon↗

The proliferation of floating anthropogenic debris in rivers has emerged as a pressing environmental concern, exerting a detrimental influence on biodiversity, water quality, and human activities such as navigation and recreation. The present study proposes a novel methodological framework for the monitoring the aforementioned waste, utilising fixed, in-situ cameras. This study provides two key contributions: (i) the continuous quantification and monitoring of floating debris using deep learning and (ii) the identification of the most suitable deep learning model in terms of accuracy and inference speed under complex environmental conditions. These models are tested in a range of environmental conditions and learning configurations, including experiments on biases related to data leakage. Furthermore, a geometric model is implemented to estimate the actual size of detected objects from a 2D image. This model takes advantage of both intrinsic and extrinsic characteristics of the camera. The findings of this study underscore the significance of the dataset constitution protocol, particularly with respect to the integration of negative images and the consideration of temporal leakage. In conclusion, the feasibility of metric object estimation using projective geometry coupled with regression corrections is demonstrated. This approach paves the way for the development of robust, low-cost, automated monitoring systems for urban aquatic environments.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.AI) 2026-06-16

Discrete optimal transport is a strong audio adversarial attack

作者:
Anton Selitskiy↗Akib Shahriyar↗Jishnuraj Prakasan↗

arXiv:2509.14959v3 Announce Type: replace-cross Abstract: In this paper, we investigate discrete optimal transport (DOT) as a black-box attack against modern automatic speaker verification (ASV) and anti-spoofing countermeasure (CM) systems. Our attack operates as a post-processing distribution-alignment step. Frame-level WavLM embeddings of generated speech (or another person speech) are aligned to an unpaired bona fide speech pool using entropic optimal transport and a top-k barycentric projection, followed by neural vocoding. Unlike gradient-based attacks, the proposed method requires no access to model parameters, gradients, or training data. Experiments on ASVspoof2019 and ASVspoof5 demonstrate that DOT attack substantially increases CM EER and substantially degrades ASV performance across multiple spoofing attacks. The attack transfers across datasets and remains effective after CM fine-tuning. Analysis using speaker similarity, Fréchet Audio Distance, and visualization of embedding distributions suggests that DOT succeeds by shifting source speech toward bona fide regions of the representation space rather than by maximizing speaker similarity. These results indicate that optimal-transport-based distribution alignment represents a previously underexplored attack vector for contemporary ASV and anti-spoofing systems.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.CL) 2026-06-15

EiCAP: Beyond Fluency, Probing and Improving Emotional Intelligence in LLMs via Psychologically Grounded Multi-Turn Dialogue

作者:
Nizi Nazar↗Pardis Sadat Zahraei↗Dilek Hakkani-T\"ur↗Natasa Milic-Frayling↗Ehsaneddin Asgari↗

Large Language Models increasingly serve in emotionally sensitive roles, including mental health support, education, and crisis response, yet they lack a principled framework for assessing or improving Emotional Intelligence (EI). We introduce EiCAP, a unified, psychologically grounded six-layer EI taxonomy operationalized into two complementary resources. EiCAP-Bench is a multi-turn, one-vs-three forced-choice evaluation suite with 3,174 probes across 24 subcategories and cross-turn dependencies that reflect real conversational EI demands. EiCAP-SFT is a 152,820-dialogue supervision corpus aligned to the same taxonomy, enabling controlled, interpretable fine-tuning. Two key findings emerge. First, generic conversational supervised fine-tuning does not confer EI: fine-tuning on UltraChat yields no significant gain in any of the 24 subcategories, with a macro score of 24.6%, near the chance level of 25%. Second, applying EI-grounded LoRA, using approximately 0.8% of parameters, directly to Qwen-2.5-7B-Base achieves significant gains in all 24 subcategories, reaching a macro score of 75.33%, a gain of 51.7 percentage points over Base and 37.1 percentage points over Instruct. Crucially, an ablation shows that the UltraChat pre-stage is counterproductive, reducing performance by 21.4 percentage points: direct EI-grounded training is both necessary and sufficient.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.CV) 2026-06-24

Trimming the Long-Tail of Visual World Modeling Evaluation

作者:
Bingxuan Li↗Yining Hong↗Cheng Qian↗Hyeonjeong Ha↗Jiateng Liu↗Zhenhailong Wang↗Yue Guo↗Yunzhu Li↗Heng Ji↗

Physical interactions follow a long-tailed distribution: a set of common and regular interactions dominates human experience and visual data, while a broad spectrum of rare and irregular interactions remains underrepresented. Although recent visual world models, including image and video generation models, achieve impressive realism on existing benchmarks, they primarily focus on simulating common physical interactions. This raises a central question: Do current visual world models internalize and generalize physical principles? In this work, we introduce Tailor-Bench, a benchmark that challenges world models to simulate irregular physical interactions. To enable systematic evaluation, we design three scenario modes that progressively challenge model reasoning: Regular scenarios reflect common tool-task pairs, Unconventional scenarios replace conventional tools with attribute-compatible substitutes to test affordance generalization, and Impossible scenarios introduce attribute-violating tools to probe constraint awareness. Additionally, we design two complementary settings under a unified evaluation protocol: predictive generation requires inferring outcomes without guidance, while descriptive generation specifies the target outcome for faithful realization. Our experimental results reveal a clear long-tail gap in physical world modeling: performance degrades from Regular to Unconventional and Impossible scenarios, indicating limited generalization beyond common interactions. Failure analysis further shows that models rely on superficial visual patterns: image models fail to realize correct state changes, while video models further suffer from temporal inconsistencies.

阅读与讨论 → 访问原文 →
06.
arXiv (CS.AI) 2026-06-19

Human-AI Agent Interaction in a Business Context

作者:
Kathrin Paimann↗Elizangela Valarini↗Sebastian Juhl↗

arXiv:2606.18716v1 Announce Type: cross Abstract: As AI agents are increasingly integrated into core business processes, understanding and designing effective interaction patterns between humans and AI agents becomes crucial for value creation. This study identifies and evaluates principles and criteria for a positive User Experience (UX) with AI agents, along with methods for its measurement. We identify user expectations and needs to facilitate adoption, build trust, and support user-centered decision-making by development teams. Using a mixed-methods approach that combines qualitative and quantitative techniques, we explore interaction patterns between humans and AI agents. The findings from this exploratory research serve as the basis to develop a survey experiment which evaluates the effectiveness of specific design elements on a larger scale. This foundational research contributes to the development of more intuitive and effective human-AI agent interactions in business settings.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.CV) 2026-06-18

Confidence is Not Reliability: Rethinking MC Dropout in Brain Tumour Segmentation

作者:
Xin Ci Wong↗Duygu Sarikaya↗Kieran Zucker↗Marc De Kamps↗Nishant Ravikumar↗

Glioma segmentation in multiparametric MRI is a critical component of treatment planning. A segmentation model that fails silently on treatment-critical sub-regions represents a patient safety risk that overlap-based metrics such as Dice scores cannot expose. We ask whether voxel-level uncertainty estimation via Monte Carlo (MC) Dropout can reliably identify segmentation errors in clinically critical sub-regions, and whether calibration failure modes are detectable from standard reporting metrics alone. In an empirical two-model case study on 126 BraTS21 patients, we evaluate a high-performance pretrained SegResNet and a locally trained UNet with residual units (UNet-Res). MC dropout preserved segmentation accuracy ($|\Delta Dice|$ $

阅读与讨论 → 访问原文 →
08.
arXiv (CS.CL) 2026-06-24

Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations

作者:
Dani Roytburg↗Matthew Bozoukov↗Matthew Nguyen↗Jou Barzdukas↗Mackenzie Puig-Hall↗Narmeen Oozeer↗

Recent research has shown that large language models (LLMs) favor their own outputs when acting as judges, undermining the integrity of automated post-training and evaluation workflows. However, it is difficult to disentangle which behaviors are explained by narcissism versus experimental confounds. Specifically, LLM evaluators may deliver self-preferring verdicts when comparing responses to questions they fail on; these verdicts may not depend on the identity of the author, but on evaluator quality. We correct this by directly comparing the judge's voting distribution in cases where it evaluates itself versus another model. This evaluator quality baseline reveals that only 51% of examples in previous findings retain statistical significance against this null hypothesis, covering 89.6% of total self-preference probability mass. Finally, we compare the entropy of voting distributions, suggesting uncertainty-driven overlap, and show that our procedure enables more careful documentation against the backdrop of judge-bias research.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.CL) 2026-06-24

Blockwise Policy-Drift Gating for On-Policy Distillation

作者:
Liwen Zheng↗Haiyun Jiang↗

On-policy distillation (OPD) trains a student policy using teacher signals computed on trajectories sampled by the student itself. Recent work shows that sampled-token OPD can be fragile on long-horizon reasoning tasks and that local teacher-support matching is a simple and effective repair. This paper introduces blockwise policy-drift gating, a lightweight student-only old-current drift controller for OPD under rollout reuse. The method computes log-probability shifts between the behavior student and the current student on the sampled token path, aggregates these shifts over fixed blocks or spans, and uses the resulting detached, mean-normalized gates to reweight OPD position losses. It does not change teacher targets, teacher top-K supports, or the rollout policy. In a six-variant Qwen3 math reasoning benchmark with a uniform 200-step training budget for all trained variants, we use pass@8 as the primary problem-level solve-rate metric. Fixed 64-token block gating improves sampled-token OPD mean pass@8 from 0.4978 to 0.5160 across AIME24, AIME25, MATH500, and AMC23. On Teacher-TopK/LSM, Block64 gives the best four-benchmark mean pass@8 among trained students. The results identify local old-current policy drift as a practical control signal for reused OPD rollouts and motivate block-level gating as a simple default for improving solve-rate robustness.

阅读与讨论 → 访问原文 →
10.
arXiv (quant-ph) 2026-06-11

PHASE: Pauli Hierarchical Assembly on Subdivided Elements for Quantum-Compatible Operator Synthesis

作者:
Tillman Philo↗Caglar Oskay↗

arXiv:2606.11478v1 Announce Type: new Abstract: Efficiently decomposing finite element stiffness matrices into the Pauli basis is challenging due to the exponential growth of Pauli strings with problem size. A naive Pauli expansion requires $\Theta(8^{\lceil \log_2 N \rceil})$ operations, where $N$ denotes the number of degrees of freedom, rendering direct decomposition infeasible for large systems. Existing approaches exploit algebraic sparsity or operator structure but do not incorporate the geometric organization intrinsic to finite element discretizations, and consequently exhibit poor scaling for stiffness matrices. To address this problem, we introduce PHASE, a hierarchical, geometry-aware Pauli decomposition algorithm that leverages recursive mesh partitioning to organize element contributions across multiple spatial scales. PHASE employs a hybrid strategy that combines full- and reduced-space Tensorized Pauli Decomposition with Fast Walsh-Hadamard Transform-based aggregation to assemble global Pauli coefficients efficiently. We show that this approach yields a dimension-dependent reduction in the exponential scaling exponent of Pauli assembly asymptotic complexity relative to existing methods, reducing the cost from $2^{2{\lceil \log_2 N \rceil}}$ to $2^{\gamma_d{\lceil \log_2 N \rceil}}$ with $\gamma_d < 2$ under standard mesh regularity and balanced partition assumptions. These results substantially improve the feasibility of quantum-compatible operator synthesis for large-scale finite element models.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.AI) 2026-06-11

Are LLMs Bad at Moral Reasoning?

作者:
Menghang Zhu↗Seth Lazar↗

arXiv:2606.11635v1 Announce Type: cross Abstract: For highly capable AI systems to operate safely in dynamic, open-ended environments, they must be able to identify, understand, and respond to moral reasons for action, and constrain their behaviour accordingly. A growing body of research aims to evaluate this capacity – moral competence – in today's most capable AI systems, recently reaching broadly pessimistic conclusions. One of the most ambitious such papers collects gold-standard human-authored rubrics for evaluating moral reasoning in 1,000 cases, and benchmarks frontier AI models against those rubrics, with underwhelming results. In this paper, we argue that the MoReBench dataset can be redeployed to give a much more optimistic picture of LLMs' moral reasoning (an essential part of moral competence). We show that if, instead of scoring LLMs' responses to these cases against these rubrics, we instead give the LLMs the same task given to humans – to generate scoring rubrics for the moral analysis of particular cases – the rubrics they generate are both better calibrated to the human rubrics than their open-ended responses, and, where they differ, plausibly reflect nothing more than the vast dimensionality of most moral problems, as well as highlighting some human departures from the "rubric for creating rubrics". Taking these points into consideration, the MoReBench dataset suggests that LLMs are significantly more capable at moral reasoning than was previously believed.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.AI) 2026-06-11

TAHOE: Text-to-SQL with Automated Hint Optimization from Experience

作者:
Zhiyi Chen↗Jie Song↗Peng Li↗

arXiv:2606.12387v1 Announce Type: cross Abstract: Large Language Models (LLMs) have democratized database access through Text-to-SQL, but moving from prototypes to production remains difficult. Real deployments must handle strict SQL dialects, massive schemas, and evolving user preferences, while supervised fine-tuning is costly and rigid and agentic test-time scaling is expensive. We present Tahoe, a system that treats prompt optimization as a dynamic data management problem. Tahoe uses an error-driven hint learning pipeline across Development and Deployment to consolidate debugging traces into a structured Hint Bank. Compiler feedback is distilled into reusable Syntax Hints for dialect-specific rules, while execution and user feedback are converted into Semantic Hints for schema- and user-specific logic. Tahoe further introduces a Strategy Layer that models conflicting user intents as competing strategies under shared natural-language triggers, with recency signals and post-learning attribution statistics that summarize empirical success, harm, inertness, and support. At inference time, Tahoe retrieves relevant hints and guides the LLM through Logic Planning followed by SQL Synthesis. We implement and evaluate the development-phase workflow, leaving deployment-time human-feedback updates for future work. On Spider 2.0-Snow, Tahoe substantially improves Text-to-SQL without updating model parameters. On 113 supervised Spider 2.0-Snow-0212 examples using GPT-5.5, Tahoe raises pass rate from 61.95 percent to 79.42 percent and pass-at-4 from 72.57 percent to 87.61 percent, achieves 100 percent Snowflake syntax pass rate, and reduces average compiler-feedback critic rounds from 2.79 to 0.12 per sampled candidate. The same Hint Bank also transfers to weaker backbones, including a 19.7 percentage-point pass-rate gain on Doubao-2.0-lite.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.AI) 2026-06-12

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems

作者:
Jiaqi Luo↗Jiarun Dai↗Zhile Chen↗Jia Xu↗Weibing Wang↗Yawen Duan↗Brian Tse↗Geng Hong↗Xudong Pan↗Yuan Zhang↗Min Yang↗

arXiv:2606.13079v1 Announce Type: cross Abstract: Nowadays, the autonomous execution of cyberattacks capable of causing substantial real-world harm is widely regarded as one of the critical red lines that frontier AI systems must not cross. Within this broader red-line scenario, autonomous penetration represents a core enabling capability and subtask: the ability of LLM-powered AI systems to independently conduct adversarial operations against a target server without human intervention, identify and exploit vulnerabilities, and obtain unauthorized access or control. A growing body of work has sought to assess the autonomous penetration capabilities of AI systems. However, existing evaluations often employ opaque methodologies, rely on unrealistic or overly simplified penetration-testing scenarios, or provide LLMs with excessive prior knowledge and task-specific guidance, and cannot accurately capture the extent to which modern AI systems can autonomously perform this core capability within broader high-impact cyberattack scenarios. To address these limitations, we construct a new autonomous penetration evaluation framework consisting of two components: target servers and agent scaffolding. Specifically, on the target-server side, we design two levels of target environments based on the number of secure services without known vulnerabilities deployed alongside a vulnerable service: Tier~1 (one secure service) and Tier~2 (three secure services), resulting in a total of 300 target servers. Meanwhile, the agent scaffolding adopts a general-purpose agent architecture equipped with a set of general-purpose cybersecurity tools, without any target-specific prior knowledge. We evaluate 19 open-weight and proprietary LLMs, and find that current models achieve penetration success rates ranging from 10.7% to 69.3%. Moreover, we observe that autonomous penetration capability continues to improve alongside advances in overall model capability.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.AI) 2026-06-16

Closing the Auto-Research Loop: An AI Co-Scientist for Production Search Ranking

作者:
Liwei Wu↗Cho-Jui Hsieh↗

arXiv:2603.22376v2 Announce Type: replace-cross Abstract: We present an AI Co-Scientist framework that closes the research loop for the production search-ranking system of a large online travel platform – pairing LLM agents with direct cloud-compute access so that idea generation, code implementation, GPU experimentation, and result analysis iterate end-to-end with a human scientist in the loop. The framework uses a hybrid agent architecture: single-LLM agents handle routine work, while multi-LLM consensus (GPT-5.2, Gemini Pro 3, Claude Opus 4.5) is invoked for higher-stakes decisions. On the production ranking task, a human-designed transformer baseline (V2) yielded $+0.118\%$ over a pre-transformer baseline (V1); the AI Co-Scientist's automated loop on top of V2 contributed an additional $+0.083\%$, for a combined $+0.201\%$ offline gain delivered in roughly one extra week of wall-clock time (single-run numbers; statistical limits discussed in the paper). The most useful AI proposals – unified long-sequence layouts, slot-type embeddings, and multi-phase learning-rate schedules – are standard practice in NLP and Vision but were absent from our production stack, suggesting that LLM agents can serve as cross-disciplinary connectors for ranking teams. We also report deployment context, negative results, and lessons learned.

阅读与讨论 → 访问原文 →
16.
arXiv (math.PR) 2026-06-15

On a stochastic phase-field model of cell motility with singular diffusion

作者:
Amjad Saef↗Wilhelm Stannat↗

arXiv:2601.05881v2 Announce Type: replace Abstract: We study existence of solutions in the variational sense for a class of stochastic phase-field models describing moving boundary problems. The models consist of stochastic reaction-diffusion equations with singular diffusion forced by a phase-field. We investigate both the case of an independently evolving phase-field and of coupled phase-field evolution driven by a viscous Hamilton-Jacobi equation. Such systems are used in the modelling of single-cell chemotaxis, where the contour of the cell shape corresponds to a level set of the phase-field. The technical challenge lies in the singularities at zero level sets of the phase-field. For large classes of initial data, we establish global existence of probabilistically weak solutions in $L^2$-spaces with weights which compensate for the singularities.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.CV) 2026-06-16

MMDiff: Extending Diffusion Transformers for Multi-Modal Generation

作者:
Yagmur Akarken↗Orest Kupyn↗Christian Rupprecht↗

Diffusion transformers have demonstrated remarkable generative capabilities, yet the rich perceptual representations computed across their denoising trajectory are discarded once the content is rendered. We present MMDiff, a framework that transforms a frozen diffusion transformer into a multi-modal generative system that jointly produces images alongside any combination of dense perceptual modalities using lightweight decoder heads. Our central finding is that perceptual information is temporally distributed along the denoising trajectory, and that multi-timestep feature fusion with spatially varying aggregation weights is essential, improving semantic segmentation results by up to 28.7% mIoU over single-timestep extraction. We further adopt concept-driven attention extraction for interpretable spatial guidance, and show that frozen diffusion features are competitive with and complementary to state-of-the-art encoders such as DINOv3. By training only lightweight decoder heads on a frozen backbone, we achieve strong performance in semantic segmentation, salient object detection, and depth estimation, and demonstrate that this framework enables effective synthetic data generation at scale.

阅读与讨论 → 访问原文 →
18.
arXiv (math.PR) 2026-06-19

The central heat trace on large compact classical groups

作者:
Thibaut Lemoine↗Myl\`ene Ma\"ida↗

arXiv:2511.08288v2 Announce Type: replace-cross Abstract: We study the large-$N$ asymptotics of the central trace of the heat kernel on compact classical groups. For every classical family $G_N\subset \mathrm{GL}_N(\C)$, we prove a full large-$N$ asymptotic expansion, using a highest weights/partitions correspondence adapted to the large-rank regime, under which the eigenvalues of the Laplace–Beltrami operator stabilize as observables in the algebra of shifted symmetric functions. Then, we prove a random surface representation of the trace in terms of ramified coverings of the torus. We provide two independent applications: an explicit large-rank counting law for the Casimir spectrum, with exponential Hardy–Ramanujan-type growth in contrast with the polynomial behavior of Weyl's law at fixed rank, and a rigorous probabilistic formulation of the Yang–Mills/Hurwitz duality on a two-dimensional torus initiated by Gross and Taylor, completing a previous work of the authors. We also extend this duality to a Yang–Mills/Gromov–Witten duality by expressing the coefficients of the central heat trace as explicit functionals of the generating function of Gromov–Witten invariants.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.AI) 2026-06-19

Analyzing the Narration Gap in LLM-Solver Loops

作者:
Zunchen Huang↗Songgaojun Deng↗

arXiv:2606.19588v1 Announce Type: new Abstract: Formal tools such as SAT and SMT solvers are increasingly embedded in language model reasoning pipelines when a safety or security critical question can be formulated in logic. Unlike chain of thought whose steps are sampled from the model distribution without formal guarantee, a solver produces a sound and independently verifiable answer. However, the soundness guarantee can be lost in the interaction between the solver and the model. The hybrid pipeline has three components: formalizing the question, deciding it, and narrating the result. Prior work has studied the formalization and decision, but not narration, which is the step that turns a formal tool's output into the user answer. To fill the narration gap, we first model the LLM-solver loop as a verified decision procedure. We further evaluate five open-sourced models under prompt injection, and we find certificate gating makes the solver verdict sound, while an adversary can invert a verified conclusion across phrasings and channels. We study the mitigation through hardened prompt that reduces injection significantly but cannot eliminate it and still suffers under adaptive attack. Combining the formal analysis and empirical studies, we show in the LLM-solver loop, robustness does not reach to the answer that the user finally reads.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.AI) 2026-06-16

Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking

作者:
Jiwan Chung↗JiHyuk Byun↗Vibhav Vineet↗Seon Joo Kim↗

arXiv:2606.15673v1 Announce Type: new Abstract: Web agents act through long interaction sequences, yet existing benchmarks evaluate only terminal success, discarding all process information and offering little guidance on improvement. In this work, we conduct a process-level analysis of web agents. We introduce WebStep, a benchmark of 1,800 task instances with controlled difficulty and automatic semantic state tracking. Each website exposes a deterministic semantic MDP alongside the GUI: the agent operates on the interface, while the environment records high-level states and transitions in the background, enabling fine-grained analysis without manual annotation. Based on the semantic trajectory, we first show that process metrics reveal differences invisible to outcome evaluation: three agents whose success rates cluster within 31-33% diverge in exploration reach versus execution accuracy. Then, decomposing by skill characterizes the nature of these differences, exposing opposite per-skill rankings hidden within the same website: e.g., on Housing, OpenAI CUA outperforms Qwen3.5 by 23.7% on commit actions yet underperforms it by 15.6% on filtering, pinpointing a concrete skill to improve even within a domain. Bifurcation analysis further localizes the decisive error that loses the task and shows that this error is agent-specific rather than shared. Finally, these differences widen as tasks grow harder: success rate is similar on easy tasks but separates sharply as exploration becomes more demanding. Our process-level analysis opens a new avenue in web agent evaluation, providing fine-grained and actionable insight into where and how each agent should be improved.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.CL) 2026-06-18

IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages

作者:
Sakshi Joshi↗Dhruv Subhash Rathi↗Sanskar Singh↗Eldho Ittan George↗R J Hari↗Kaushal Bhogale↗Mitesh M. Khapra↗

AudioLLMs enable speech recognition conditioned on textual prompts such as domain descriptions or entity lists. However, it remains unclear whether these models genuinely utilise such context or rely on parametric knowledge learned during pretraining. Existing benchmarks cannot answer this question because they evaluate transcription under fixed prompting conditions and rarely include explicit contextual inputs. We introduce IndicContextEval, a 56-hour multilingual benchmark of natural speech from 555 speakers across 8 Indian languages and 23 professional domains. We design a 7-level prompting framework that progressively introduces contextual signals, including metadata, natural-language descriptions, entity lists in English and native script, and adversarial prompts with incorrect entities. Evaluating five models reveals substantial differences in context utilisation behaviour, highlighting the need for explicit evaluation of contextual grounding in AudioLLMs.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.AI) 2026-06-15

HierSVA: A Data Synthesis Pipeline, Dataset, and Benchmark for LLM-Driven Hierarchical Hardware Formal Verification

作者:
Maohua Nie↗Jiang Zhu↗Jingqun Zhang↗Zhichen Zeng↗Jiayi Wang↗Sibo Zhang↗Jialin Wang↗C. -J. Richard Shi↗

arXiv:2606.13706v1 Announce Type: cross Abstract: We present HierSVA, an integrated suite that combines a pipeline, dataset, and benchmark for LLM-driven hierarchical hardware formal verification. HierSVA-SP pairs an RTL preprocessing toolchain with an LLM-in-the-loop formal verification flow to produce reference SystemVerilog Assertions (SVA) on hierarchical RTL. Applying it to BaseJump STL yields HierSVA-DS, a dataset of 342 modules, with hierarchy metadata and depths 0–9, accompanied by a deep subset of 28 module-bug pairs with natural-language specifications and bug variants. HierSVA-B decomposes assertion quality into six metric axes: syntax correctness, assertion proof success rate, vacuity, specification faithfulness, mutation coverage, and formal core coverage. Applying HierSVA-B to twelve recent LLMs reveals three findings. First, the module-level compile rate is 67.1\%; among generated assertions in evaluable runs, 82.1\% prove non-vacuously, but the corresponding assertion sets detect only 70.2\% of eligible injected faults and cover 36.2\% of the formal core. Second, on 211 evaluable model–module entries in the deep subset, assertion sets flag buggy RTL with 0.87 recall, but 40\% of predicted-buggy outcomes are false positives on correct RTL, limiting precision to 0.60. Third, agentic mode improves S1-style provability and strength metrics, but gains plateau and oscillate. Codes and artifacts are available at \href{https://github.com/HierSVAAnon/HierSVACodeAndArtifacts}{https://github.com/HierSVAAnon/HierSVACodeAndArtifacts}. Dataset is available at \href{https://huggingface.co/datasets/AnonymousHierSVA/HierSVA}{https://huggingface.co/datasets/AnonymousHierSVA/HierSVA}.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.CV) 2026-06-12

GetNetUPAM: Ecologically Informed Nested Cross-Validation and Noise-Robust Attention for Marine Bioacoustic Monitoring

作者:
Nicholas R. Rasmussen↗Rodrigue Rizk↗Longwei Wang↗KC Santosh↗

Deploying reliable bioacoustic monitoring systems requires models that generalize under high-noise, low-SNR conditions and evaluation protocols that expose deployment-relevant failure modes, gaps largely unaddressed in current UPAM practice. Intrinsic noise, variable propagation, and mixed biological and anthropogenic sources induce distribution shifts that conventional models and single-split evaluations obscure, inflating performance and masking instability. We introduce GetNetUPAM, a hierarchical nested cross-validation framework that uses the nested stage to quantify model stability rather than tune for inflated hold-out scores. By partitioning data into site-year blocks, GetNetUPAM preserves ecological heterogeneity and forces each outer fold to represent a distinct environmental regime, preventing overfitting to localized noise or sensor artifacts. Inner stratified folds measure generalization across the full UPAM signal distribution, enforcing strict separation between model development and the outer held-out deployment condition. Using GetNetUPAM, we evaluate the Adaptive Resolution Pooling and Attention Network (ARPA-N), a CNN architecture for irregular spectrogram dimensions. ARPA-N integrates CBAM spatial attention as a learned noise suppressor, producing attention maps that localize true call structure and avoid the global, non-biological cues exploited by standard CNNs on long-window data. Under GetNetUPAM, ARPA-N generalizes robustly across diverse environmental regimes. In the zero-training support Balleny Islands region, it reduces false positives per hour by over an order of magnitude (approximately 10x) at fixed 90 percent recall, yielding consistently improved metrics across folds. These advances provide a reproducible benchmark and move UPAM toward scalable, deployment-reliable ecological monitoring.

阅读与讨论 → 访问原文 →
24.
arXiv (math.PR) 2026-06-18

Metastability for the Curie-Weiss-Potts model with unbounded random interactions

作者:
Johan L. A. Dubbeldam↗Vicente Lenz Burnier↗Elena Pulvirenti↗Martin Slowik↗

arXiv:2505.11260v2 Announce Type: replace Abstract: We analyse the metastable behaviour of the disordered Curie–Weiss–Potts (DCWP) model subject to a Glauber dynamics. The model is a randomly disordered version of the mean-field $q$-spin Potts model (CWP), where the interaction coefficients between spins are general independent random variables. These random variables are chosen to have fixed mean (for simplicity taken to be $1$) and well defined cumulant generating function, with a fixed distribution not depending on the number of particles. The system evolves as a discrete-time Markov chain with single spin flip Metropolis dynamics at finite inverse temperature $\beta$. We provide a comparison of the metastable behaviour of the CWP and DCWP models, when $N \to \infty$. First, we establish the metastability of the CWP model and, using this result, prove metastability for the DCWP model (with high probability). We then determine the ratio between the metastable transition time for the DCWP model and the corresponding time for the CWP model. Specifically, we derive the asymptotic tail behavior and moments of this ratio. Our proof combines the potential-theoretic approach to metastability with concentration of measure techniques, the latter adapted to our specific context.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.AI) 2026-06-18

Forecasting what Matters: Decision-Focused RL for Controlled EV Charging with Unknown Departure Times

作者:
Giuseppe Gabriele↗Fabio Pavirani↗Seyed Soroush Karimi Madahi↗Chris Develder↗

arXiv:2606.19199v1 Announce Type: cross Abstract: The recent growth of EV adoption poses challenges for power systems, including increased peak demand and potential grid instability. Smart control of EV charging – e.g., based on reinforcement learning (RL) – can alleviate these issues by learning temporal and contextual patterns from historical data. Yet, in real-world scenarios, key features, such as departure time, often are unavailable. This, in turn, makes it harder for an RL agent to learn and execute an effective charging policy. To mitigate this uncertainty, a trained forecaster can approximate the unknown features from available data. However, since these forecasting models are typically trained for accuracy (rather than their impact on a downstream agent's decision quality), their errors may propagate and hinder the overall performance of a controller that is using the forecasts. To avoid this, we propose a decision-focused RL (DF-RL) framework in which the forecaster is trained end-to-end, i.e., with feedback from the charging policy actions taken by the RL agent. Such joint training of both the forecaster and controller ultimately results in higher-quality actions: our proposed DF-RL method yields superior charging decisions compared to other baselines, achieving up to a 14% improvement in total reward and a 55% reduction of unsupplied energy (i.e., charging that failed to happen because the EV already left), relative to the RL method without departure time forecasting.

阅读与讨论 → 访问原文 →