探索全球前沿学术脉络

01.

Nature (Science) 2026-06-09 DOI: HASH:9bd37bb17efd613e53e8d0422d603555

Good recycling starts at home — and benefits the world

作者: 未知作者

New research supports the value of household-level waste separation. But policies must also carefully consider consumer behaviours to maximize the quality of material collected. New research supports the value of household-level waste separation. But policies must also carefully consider consumer behaviours to maximize the quality of material collected.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.20543

SSD: Spatially Speculative Decoding Accelerates Autoregressive Image Generation

作者:

Shilong Xiang↗Zirui Zhang↗Lijun Yu↗Chengzhi Mao↗

Autoregressive models excel in visual generation by treating images as 1D sequences of discrete tokens, mirroring language modeling. However, this flattening discards the intrinsic 2D spatial locality of visual signals, creating severe computational bottlenecks during inference. We introduce Spatially Speculative Decoding (SSD), a framework that aligns the predictive objective with the natural geometry of images. Rather than predicting only the immediate next token in a 1D sequence, our model simultaneously predicts the adjacent horizontal token and the token directly below it. By capitalizing on this 2D spatial correlation, spatially speculative decoding overcomes the memory wall in visual inference. Our approach accelerates autoregressive image generation by up to 13.3x while maintaining high fidelity on DPG-Bench and GenEval. Our results suggest that respecting the underlying geometry of vision unlocks massive computational efficiencies, paving the way for real-time, high-resolution autoregressive generative models.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2510.06647

Q-Learning with Fine-Grained Gap-Dependent Regret

作者:

Haochen Zhang↗Zhong Zheng↗Lingzhou Xue↗

arXiv:2510.06647v2 Announce Type: replace-cross Abstract: We study fine-grained gap-dependent regret bounds for model-free reinforcement learning in episodic tabular Markov Decision Processes. Existing model-free algorithms achieve minimax worst-case regret, but their gap-dependent bounds remain coarse and fail to fully capture the structure of suboptimality gaps. We address this limitation by establishing fine-grained gap-dependent regret bounds for both UCB-based and non-UCB-based algorithms. In the UCB-based setting, we develop a novel analytical framework that explicitly separates the analysis of optimal and suboptimal state-action pairs, yielding the first fine-grained regret upper bound for UCB-Hoeffding (Jin et al., 2018). To highlight the generality of this framework, we introduce ULCB-Hoeffding, a new UCB-based algorithm inspired by AMB (Xu et al.,2021) but with a simplified structure, which enjoys fine-grained regret guarantees and empirically outperforms AMB. In the non-UCB-based setting, we revisit the only known algorithm AMB, and identify two key issues in its algorithm design and analysis: improper truncation in the $Q$-updates and violation of the martingale difference condition in its concentration argument. We propose a refined version of AMB that addresses these issues, establishing the first rigorous fine-grained gap-dependent regret for a non-UCB-based method, with experiments demonstrating improved performance over AMB.

阅读与讨论 → 访问原文 →

04.

Nature Medicine 2026-06-15 DOI: HASH:42346eb9c9bf2e89d6ea6ea4f98d9ad6

Adaptive deep brain stimulation for dynamic gait control in Parkinson’s disease: a randomized feasibility trial

作者:

Kenneth H. Louie↗

A randomized crossover study of five patients with Parkinson’s disease (PD) demonstrates that gait-synchronized adaptive deep brain stimulation is feasible and safe, and reduces falls compared with continuous stimulation. Gait dysfunction in PD is a major source of disability and is often insufficiently treated by continuous deep brain stimulation (cDBS). Although adaptive DBS (aDBS) has shown efficacy for other motor symptoms using β-based, state-driven neural signals, gait is a dynamic, cyclical behavior that may require temporally precise modulation. Here we evaluated a behavior-contingent aDBS approach that synchronizes stimulation to gait phase. We reported a single-center, blinded, randomized, crossover study evaluating the feasibility of identifying patient-specific biomarkers to drive aDBS. The primary outcome was feasibility of successful identification of gait-phase biomarkers to implement aDBS. Five participants with PD undergoing pallidal DBS and subdural electrode paddle implantation were enrolled. We successfully identified personalized gait-phase biomarkers from cortical or pallidal field potentials in all five patients and embedded them into a bidirectional neurostimulator. During acute in-clinic testing, aDBS improved step variability and step symmetry versus cDBS. Three participants subsequently completed a double-blinded, multi-day crossover phase. In this setting, aDBS maintained general motor symptom control, reduced falls and yielded patient-specific gait improvements. No adverse events occurred and aDBS was well tolerated. These findings establish the feasibility of biomarker-driven, movement-synchronized neuromodulation and support the development of a larger randomized trial to determine clinical efficacy. ClinicalTrial.gov registration: NCT04675398 . A randomized crossover study shows that gait-phase-synchronized adaptive deep brain stimulation is feasible and safe, and reduces falls compared to continuous stimulation in Parkinson’s disease.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14507

Dense Coordinate-List Fine-Tuning Induces a Controllable Interference Surface in Vision-Language Models

作者:

Chenyu Zhou↗Qiliang Jiang↗Boguang Pan↗

arXiv:2606.14507v1 Announce Type: new Abstract: Fine-tuning vision-language models to emit dense coordinate lists improves visual grounding but also changes how models serialize, repeat, and terminate structured outputs. We study this behavior as a generation and control surface. In Gemma 4 12B, high-capacity q/k/v/o LoRA raises class-aware F1@0.3 from 0.007 to 0.448 while inducing repeated-tail pressure (duplicate rate 0.080, max repeat 23). A q/v rank sweep keeps max repeat at 21-22 across ranks 4-64, showing capacity persistence. The target signal is separable: object-level repeat-stop removes exact repeated records (duplicate rate 0.000, max repeat 1) while preserving F1 (0.494 to 0.490) and stricter F1@0.5 (0.381 to 0.385). Structure-axis probes localize the effect to bbox-coordinate object lists; dense non-bbox and spatial/count JSON remain repeat-clean, including under high-capacity adapters. Qwen3-VL-8B reproduces a clean controlled endpoint (F1@0.3 0.318, duplicate rate 0.000), and COCO 2017 reproduces acquisition plus duplicate pressure. Dense coordinate-list adaptation therefore creates a structure-bound, cross-family interference surface that can be measured and controlled.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.14885

Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion

作者:

Yi Lu↗Zhuofeng Li↗Ping Nie↗Haoxiang Zhang↗Yuyu Zhang↗Kai Zou↗Wenhu Chen↗Jimmy Lin↗Dongfu Jiang↗Yu Zhang↗

Agentic search over large corpora relies on retriever-mediated interfaces (e.g., BM25 or ColBERT) for scalable candidate discovery. While effective at ranking relevant documents, these interfaces expose evidence only as ranked results or bounded document views, limiting agents' ability to reorganize material and verify constraints across documents. Direct Corpus Interaction (DCI) addresses this limitation by exposing shell-executable corpus operations for flexible search, filtering, comparison, and verification. However, full-corpus terminal commands become slow and unstable as the corpus grows, degrading performance and efficiency. We introduce DR-DCI, a retriever-steered DCI framework that treats retrieval as an agent-callable action for expanding a local workspace. Rather than operating directly over the full corpus, the agent dynamically pulls relevant documents into an evolving workspace and conducts DCI operations within it. This design combines retriever-level recall with DCI-style precision: retrieval keeps exploration scalable, while DCI preserves the local operations needed for effective evidence resolution. Experiments show that DR-DCI is both effective and efficient across scales. On Browsecomp-Plus, DR-DCI reaches 71.2\% accuracy, improving over raw DCI and ablated variants by up to 8.3 points while reducing tool usage, wall time, and estimated cost. With workspace-preserving context reset, accuracy further improves to 73.3\%. In corpus-scaling experiments, DR-DCI remains effective from 100K to 10M documents, whereas raw DCI becomes unstable and BM25 performs substantially worse. DR-DCI also scales to a 20M-scale file-per-document Wiki-18 QA setting, achieving an average score of 63.0 across six benchmarks and outperforming retrieval-based and trained search-agent baselines. Ablation analysis further shows that ranked previews and inter-document DCI are key to performance.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2402.08128

Recursive Joint Simulation in Games

作者:

Vojtech Kovarik↗Caspar Oesterheld↗Vincent Conitzer↗

arXiv:2402.08128v3 Announce Type: replace Abstract: Game-theoretic dynamics between AI agents could differ from traditional human-human interactions in various ways. One such difference is that it may be possible to accurately simulate an AI agent, for example because its source code is known. Such an agent would then be fundamentally uncertain whether it is in the real world or in a simulation. Our aim is to explore ways of leveraging this possibility to achieve more cooperative outcomes in strategic settings. In this paper, we study an interaction between AI agents where the agents run a recursive joint simulation. That is, the agents first jointly observe a simulation of the situation they face. This simulation in turn recursively includes additional simulations (with a small chance of failure, to avoid infinite recursion), and the results of all these nested simulations are observed before an action is chosen. We show that the resulting interaction is strategically equivalent to an infinitely repeated version of the original game, allowing a direct transfer of existing results such as the various folk theorems. As evidence that the equivalence is robust, we show that it holds even when we relax some of the assumptions and that it also holds ``from the inside'' – meaning, for an agent that finds itself inside the game and has self-locating uncertainty.

阅读与讨论 → 访问原文 →

08.

arXiv (quant-ph) 2026-06-19 DOI: arXiv:2606.19310

Exclusion Statistics as a Thermodynamic Resource in Quantum Heat Engines

作者:

Sampurna Karmakar↗Aziz Hasan↗Sourin Das↗

arXiv:2606.19310v1 Announce Type: cross Abstract: The maximum power extractable from a quantum thermoelectric heat engine operating with free fermion carriers is bounded by the universal Whitney limit, $P_{fermion}^{\max} \simeq 0.0321\pi^2 k_B^2(T_L-T_R)^2/h$. We demonstrate that this bound is not fundamental to quantum heat engines but is instead an artifact of fermionic statistics. Within the nonlinear Landauer-B\"{u}ttiker framework, a bosonic working medium yields a strictly enhanced universal maximum power, $P_{boson}^{\max} = (\ln 2)^2\, k_B^2(T_L-T_R)^2/h$, exceeding the fermionic limit by a factor of $(\ln 2)^2/(0.0321\pi^2) \approx 1.52$. We propose magnon transport through a ferromagnetic spin chain as an experimentally viable bosonic realization. Incorporating Haldane fractional exclusion statistics with parameter $g$ provides a continuous interpolation between the bosonic ($g = 0$) and fermionic ($g = 1$) limits, revealing a monotonic enhancement of maximum power for $g < 1$ at reduced bias cost. These results establish quantum statistical exclusion as a previously unrecognized and independently tunable thermodynamic resource, opening performance regimes inaccessible to conventional carrier-engineering approaches.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13591

Multiagent Protocols with Aggregated Confidence Signals

作者:

Ali Elahi↗Barbara Di Eugenio↗

arXiv:2606.13591v1 Announce Type: new Abstract: Confidence is used for reliability, oversight, and a range of downstream decision tasks in Natural Language Processing (NLP), yet no existing method produces or evaluates a confidence for the output of a multiagent system. Prior work uses confidence within multiagent debate (MAD) to weight messages, trigger debate, or calibrate individual agents, but it never aggregates these into a single confidence for the system itself. We introduce three protocols that produce a final answer along with a single aggregated confidence by first transforming raw confidence signals to make them comparable across models, then combining them via soft voting or a probability fusion we call Bayesian fusion. This aggregated confidence is substantially more discriminative (AUARC) than that of the best single agent or the standard debate baselines, while correctness (F1-score) stays stable and recovers the losses MAD incurs on more ambiguous tasks. Analyzing two estimators, sequence probability and self-report, alongside parametric and non-parametric calibrators, we find that calibration improves F1 for both estimators while AUARC is less reliant on it. We evaluate six homogeneous and heterogeneous debating pairs per benchmark, across five benchmarks and four task types, spanning a range of model capabilities and sizes.

阅读与讨论 → 访问原文 →

10.

PLOS Computational Biology 2026-06-05 DOI: HASH:06fd5a830f633ecf602ccb5755184374

Heuristic multi-site optimization for protein sequence design using Masked Protein Language Models

作者:

Lijuan Wang↗

by Lijuan Wang, Yuze Wang, Chen Qiu, Liwei Xiao, Xianliang Liu, Junjie Chen Protein sequence design for tailored functional properties is a fundamental task in protein engineering, with critical applications in drug discovery and therapeutic development. Efficient navigation of the combinatorial vastness of protein sequence space to identify functional variants remains a formidable challenge. Conventional approaches, which predominantly rely on template-based local search or single-residue mutagenesis, are constrained by their susceptibility to local optima and their potential risk of destabilizing native structural stability. In this study, we introduce ProtHMSO, a heuristic multi-site optimization framework leveraging masked protein language models (ProtLMs) for context-aware sequence exploration. ProtHMSO mimics natural evolutionary mechanisms by employing ProtLM-derived substitution probabilities to guide heuristic searches for synergistic mutations, thereby constraining combinatorial search spaces through evolutionary and biophysical priors. ProtHMSO is further applied to replace the exploration strategies in genetic algorithms (GAs) and Monte Carlo tree search (MCTS) for improving their convergence efficiency. Benchmark experiments demonstrate that protein sequences generated by ProtHMSO exhibit superior functional performance and closer alignment with natural sequence distribution, compared with state-of-the-art methods. These advancements highlight that ProtHMSO has strong potential and compatibility to accelerate functional protein discovery, offering a robust framework for efficient and context-aware exploration of protein sequence space.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2604.19196

Benchmarking Vision Foundation Models for Domain-Generalizable Face Anti-Spoofing

作者:

Mika Feng↗Pierre Gallin-Martel↗Koichi Ito↗Takafumi Aoki↗

Face Anti-Spoofing (FAS) remains challenging due to the requirement for robust domain generalization across unseen environments. While recent trends leverage Vision-Language Models (VLMs) for semantic supervision, these multimodal approaches often demand prohibitive computational resources and exhibit high inference latency. Furthermore, their efficacy is inherently limited by the quality of the underlying visual features. This paper revisits the potential of vision-only foundation models to establish a highly efficient and robust baseline for FAS. We conduct a systematic benchmarking of 15 pre-trained models, such as supervised CNNs, supervised ViTs, and self-supervised ViTs, under severe cross-domain scenarios including the MICO and Limited Source Domains (LSD) protocols. Our comprehensive analysis reveals that self-supervised vision models, particularly DINOv2 with Registers, significantly suppress attention artifacts and capture critical, fine-grained spoofing cues. Combined with Face Anti-Spoofing Data Augmentation (FAS-Aug), Patch-wise Data Augmentation (PDA) and Attention-weighted Patch Loss (APL), our proposed vision-only baseline achieves state-of-the-art performance in the MICO protocol. This baseline outperforms existing methods under the data-constrained LSD protocol while maintaining superior computational efficiency. This work provides a definitive vision-only baseline for FAS, demonstrating that optimized self-supervised vision transformers can serve as a backbone for both vision-only and future multimodal FAS systems. The project page is available at: https://gsisaoki.github.io/FAS-VFMbenchmark-CVPRW2026/ .

阅读与讨论 → 访问原文 →

12.

medRxiv (Medicine) 2026-06-22 DOI: HASH:8b8339f860769b62c6aa477f7ae6ef91

Effectiveness of Stress Management to Reduce Stress Eating for Women: A Systematic Review and Meta-analysis of Intervention Studies

作者:

Volpe↗V. V↗Collins↗A. N↗Davis↗E. M↗Badejoh↗O. O↗Allen↗Holland↗M. C↗Ross↗…

Objective: This systematic review and meta-analysis examined 1) the effects of stress management interventions on changes in stress eating for women, and 2) the longevity of these effects, by summarizing and assessing evidence from controlled and non-equivalent pretest-posttest intervention studies. Method: Five databases (PsycINFO, PubMed, Medline, Web of Science, CINAHL), existing sources, and grey literature were searched (February - June 2025). Studies that assessed stress eating or emotional eating, included a stress management intervention, and comprised at least 70% women were included. The primary outcome was reduction in stress eating. Data were pooled in meta-analyses using multi-level random-effects models and subset by follow-up period. Risk of bias was assessed via funnel plots and sensitivity analyses. Results: Sixty studies with 119 effect size estimates were included in the primary analysis. Pooled estimates indicated that stress management interventions significantly reduced stress eating (Hedges g = -0.4174, p < 0.001), with pre-post designs having larger effects than controlled trials. Subgroup analyses of follow-up periods found small effects in the short-term (before 3 months; Hedges g = -0.4202, p < 0.0001) and moderate effects for mid-term (3-6 months; Hedges g = -0.5886, p < 0.0001). Effects beyond 6 months were small and nonsignificant (Hedges g = -0.4370, p = 0.0660). Conclusion and Relevance: Stress management interventions appear to be effective for reducing stress eating for women, suggesting the potential to incorporate stress management in interventions targeting obesity. Effects may be only sustained 6 months post-intervention, suggesting the need for strategies to bolster long-term effectiveness.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15735

EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries

作者:

Jiyoun Kim↗Muhan Yeo↗Eunhye Jang↗Jeewon Yang↗Hangyul Yoon↗Su Ji Lee↗Hee Jo Han↗Hee-Jae Jung↗Doyun Kwon↗Jun young Lee↗Jaehun Lee↗Jung-Oh Lee↗…

Discharge summaries are crucial clinical documents containing the context of a patient's overall hospital stay, and are routinely reviewed by medical experts for patient readmission, ongoing care, and diagnostic decision-making. When reviewing them, medical experts often must iteratively synthesize information across multiple summaries while verifying the evidence supporting each answer. Although large language models (LLMs) are increasingly explored for clinical question answering, existing benchmarks do not sufficiently reflect this setting: they often evaluate exam-style medical knowledge or focus on single-turn question answering with limited evidence-grounding evaluation. We introduce EHRNote-ChatQA, the first benchmark for evidence-grounded multi-turn clinical question answering over patients' multiple discharge summaries. Built from de-identified MIMIC-IV discharge summaries, EHRNote-ChatQA contains 967 patient-level multi-turn samples spanning one to five notes and 16,072 medical-expert-verified QA pairs (8,036 content questions, each paired with an evidence-grounding question) across eight clinical categories. The benchmark is constructed through an expert-informed pipeline combining discharge-summary structuring schema, expert-curated multi-turn QA templates, and LLM-based generation, followed by review and revision of every single QA sample by 11 medical experts. Benchmarking 22 open- and closed-source LLMs reveals several challenges, including that LLMs struggle more with evidence grounding than content answering, multi-turn errors compound across turns, and single-turn clinical QA performance does not reliably transfer to this setting. These findings establish EHRNote-ChatQA as a rigorous and practical benchmark for evaluating clinical QA systems. The dataset will be made publicly available through PhysioNet credentialed access.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13737

FreoStream:Enhancing Stream Guardrails via Future-Aware Reasoning and Safety-Aligned Optimization

作者:

Jianwei Wang↗Guoyang Shen↗Yanhong Wu↗Haoran Li↗Hao Peng↗Huiping Zhuang↗Cen Chen↗Ziqian Zeng↗

arXiv:2606.13737v1 Announce Type: cross Abstract: Stream guardrails enable token-level safety detection before full responses are generated. However, they often make overly conservative judgements and block those sensitive but safe tokens, which is known as over-refusal. Due to lack of full context, they also fail to detect implicitly harmful content from jailbreaking. To address these challenges, we propose FreoStream, a novel streaming guardrail framework. Specifically, FreoStream fine-tunes a LoRA module to perform Future-Aware Reasoning when the base guardrail detects unsafe tokens. The reasoning process follows a Future-Reason-Judge paradigm: predict the future, reason about the full context and give the final judgement. This design can effectively reduce over-refusal by incorporating the future information. Moreover, we introduce the Safety-Aligned Optimization module that extracts the safety-aligned component from the reasoning gradients to update the base guardrail model, thereby enhancing streaming safety detection. Extensive experiments on various safety benchmarks demonstrate that FreoStream achieves lower over-refusal rates and better jailbreak defense compared to existing streaming guardrails.

阅读与讨论 → 访问原文 →

15.

medRxiv (Medicine) 2026-06-12 DOI: HASH:cf5322742d9f273dc6f02fff13eb3177

Genetic basis of dynamic brain states reveals cellular and disease associations

作者:

Ebneabbasi↗Whiteside↗D. J↗Gu↗Bethlehem↗R. A. I↗Warrier↗Rittman↗

Dynamic resting-state fMRI captures the time-varying patterns of brain activity that are obscured by static approaches. Hidden Markov Models (HMMs) characterise these dynamics as recurring whole-brain states and quantify their fractional occupancy (FO), the proportion of time spent in each state, yet the biological basis of inter-individual variation in FO remains unclear. Using data from 52,335 White UK Biobank participants, with replication in East and South Asian subsamples, this study examined the heritability, cellular and neurotransmitter basis of brain states, and their links with complex phenotypes. FO was significantly heritable and enriched for neuronal populations, particularly glutamatergic and GABAergic signalling. Analyses identified shared and state-specific loci and revealed genetic correlations, colocalisation, and potential causal relationships between FO and several phenotypes, including educational attainment, sleep duration, and disease risk. These findings establish dynamic brain states as biologically grounded intermediate phenotypes, linking genetic variation to neural dynamics, diseases and traits.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2602.00945

Neural FOXP2 – Language Specific Neuron Steering for Targeted Language Improvement in LLMs

作者:

Anusa Saha↗Tanmay Joshi↗Vinija Jain↗Aman Chadha↗Amitava Das↗

LLMs are multilingual by training, yet their lingua franca is often English, reflecting English language dominance in pretraining. Other languages remain in parametric memory but are systematically suppressed. We argue that language defaultness is governed by a sparse, low-rank control circuit, language neurons, that can be mechanistically isolated and safely steered. We introduce Neural FOXP2, that makes a chosen language (Hindi or Spanish) primary in a model by steering language-specific neurons. Neural FOXP2 proceeds in three stages: (i) Localize: We train per-layer SAEs so each activation decomposes into a small set of active feature components. For every feature, we quantify English vs. Hindi/Spanish selectivity overall logit-mass lift toward the target-language token set. Tracing the top-ranked features back to their strongest contributing units yields a compact language-neuron set. (ii) Steering directions: We localize controllable language-shift geometry via a spectral low-rank analysis. For each layer, we build English to target activation-difference matrices and perform layerwise SVD to extract the dominant singular directions governing language change. The eigengap and effective-rank spectra identify a compact steering subspace and an empirically chosen intervention window (where these directions are strongest and most stable). (iii) Steer: We apply a signed, sparse activation shift targeted to the language neurons. Concretely, within low to mid layers we add a positive steering along the target-language dominant directions and a compensating negative shift toward the null space for the English neurons, yielding controllable target-language defaultness.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11543

SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior

作者:

Zhiyu Chen↗Zihan Guo↗Bo Huang↗Bingwei Lu↗Jianghao Lin↗Yuanjian Zhou↗Weinan Zhang↗

arXiv:2606.11543v1 Announce Type: new Abstract: Agent Skills augment large language model (LLM) agents with procedural knowledge at inference time, but current benchmarks rarely distinguish what a Skill says from how it is organized. We study this distinction through Progressive Disclosure, where a concise root file points agents to supporting resources on demand, and compare it with a normalized flat baseline. We present SkillJuror, a framework for evaluating Skill writing paradigms through semantically controlled variants, matched multi-trial evaluations, and trajectory evidence while holding task knowledge fixed. In an 82-task SkillsBench study, Progressive Disclosure changes runtime behavior before aggregate outcomes: distinct Skill resources touched per trajectory rise from 1.18 to 3.85, and effective uptake events rise from 1.33 to 3.92. It also yields 17 additional verifier-passing trials out of 410 matched trials (+4.1%) over the normalized flat baseline. The benefit is task-dependent. Progressive Disclosure helps when supporting resources guide implementation, checking, or repair, but is weaker when success hinges on exact output conventions, numerical thresholds, or long artifact-generation pipelines. These results show that Skill organization is not mere presentation: it can change how agents search and apply procedural knowledge, while outcome gains depend on whether the exposed resources are actionable for the task. Code is available at https://github.com/zhiyuchen-ai/skill-juror.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19899

Measuring Biological Capabilities and Risks of AI Agents

作者:

Patricia Paskov↗Jeffrey Lee↗Kyle Brady↗Alyssa Worland↗

arXiv:2606.19899v1 Announce Type: cross Abstract: This paper addresses a rapidly emerging policy challenge: how to generate and interpret credible evidence about the biological capabilities and risks of AI scientists, or agentic AI systems capable of autonomously or collaboratively performing multi-step scientific tasks. As these systems enter real research workflows, decision-makers increasingly face evaluation results whose meaning depends on underlying design choices that are often implicit or under-documented. We synthesize current evidence on AI-enabled biological risks and introduce biological agentic evaluations as a promising, but interpretation-sensitive, tool for assessing these systems. Our central contribution is a set of practical, experience-grounded considerations – drawing from our own evaluations – that show how choices around defining, designing, running, scoring, and documenting evaluations materially shape what results do and do not imply about risk. The analysis is intended to help policymakers interpret biological evaluation outputs with appropriate caution; guide public and private funders toward high-leverage investments in AI-biology evaluation research; and support biosecurity practitioners assessing emerging AI systems. A secondary audience includes researchers designing or conducting agentic evaluations within frontier AI labs, AI providers, scientific institutions, and third-party evaluation organizations.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11724

Mind the Perspective: Let's Reason Recursively for Theory of Mind

作者:

Chao Lei↗Guang Hu↗Meng Yang↗Yanbei Jiang↗Nir Lipovetzky↗

arXiv:2606.11724v1 Announce Type: new Abstract: Theory of Mind (ToM) reasoning requires inferring agents' beliefs from partial and asymmetric observations, which remains an open challenge for LLMs. Existing prompting-based approaches improve ToM reasoning through observable-event filtering or temporal belief chains, without explicitly modeling nested beliefs. We introduce RecToM, an inference-time framework for ToM reasoning that models nested beliefs via recursive perspective construction. RecToM constructs each character perspective from the preceding character perspective along the character chain specified by the question, reducing higher-order belief questions to actual-world questions within the final constructed perspective. We further provide a KD45 analysis showing that RecToM's perspective construction induces a well-formed belief modality beyond simple event filtering. Experiments on ToM benchmarks, including Hi-ToM, Big-ToM, and FanToM, across multiple LLM backbones show that RecToM consistently outperforms recent advanced approaches, achieving state-of-the-art performance. Notably, RecToM reaches 100\% accuracy on Hi-ToM with GPT-5.4 and Qwen3.5, a benchmark requiring higher-order ToM reasoning.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14438

CADET: Physics-Grounded Causal Auditing and Training-Free Deconfounding of End-to-End Driving Planners

作者:

Zikun Guo↗

arXiv:2606.14438v1 Announce Type: cross Abstract: End-to-end (E2E) autonomous-driving planners trained by imitation are prone to statistical shortcuts: they associate scene elements that merely co-occur with expert actions (a roadside object, a building facade) with driving decisions, rather than the variables that causally determine them. Such causal confusion silently compromises reliability in long-tail scenarios, and it is difficult to detect, because prevailing open-loop metrics (L2 displacement and collision rate) are dominated by ego status and do not indicate whether a planner depends on spurious cues. Existing remedies based on causal-intervention training require retraining large models and cannot audit a planner that is already deployed. We present CADET, a training-free framework that audits, benchmarks, and repairs spurious reliance in pretrained E2E planners without any parameter update.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2602.02355

Mitigating Heterogeneity-Induced Drift in Hierarchical Sign-Based Federated Learning

作者:

Amirreza Kazemi↗Seyed Mohammad Azimi-Abarghouyi↗Gabor Fodor↗Carlo Fischione↗

arXiv:2602.02355v2 Announce Type: replace-cross Abstract: Hierarchical federated learning (HFL) is well suited for large-scale wireless and Internet of Things systems, where devices communicate with nearby edge servers before reaching the cloud. In these environments, uplink bandwidth and latency impose strict communication constraints, making aggressive gradient compression essential. One-bit sign-based stochastic gradient descent methods provide an attractive solution in flat federated settings, but their behavior in hierarchical edge–cloud architectures remains insufficiently understood, especially under inter-cluster data heterogeneity. To address this gap, we develop a sign-based HFL framework in which devices transmit binary stochastic-gradient signs to edge servers, edge servers apply majority voting, and the cloud periodically aggregates edge models. Our analysis reveals that inter-cluster heterogeneity induces a persistent bias term in the convergence bound, reflecting the drift of edge models toward local objectives. This term cannot be removed by increasing the number of training rounds or by tuning standard hyperparameters alone. We therefore propose \(\mathtt{DC-HierSignSGD}\), a drift-corrected sign-based HFL algorithm in which devices apply a cloud-assisted gradient correction before taking the sign. We show that this pre-sign correction mitigates the non-vanishing heterogeneity-induced bias while preserving binary device–edge communication during the repeated local sign-update steps. Experiments under severe inter-cluster heterogeneity demonstrate that \(\mathtt{DC-HierSignSGD}\) improves the stability and accuracy of sign-based HFL and achieves performance comparable to full-precision hierarchical SGD with substantially lower device–edge communication.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12106

MSUE: Multi-Modal Soccer Understanding Expert

作者:

Litao Li↗Yibo Yu↗Yufeng Hu↗Zhuo Yang↗Jiali Wen↗Yixin Chen↗Yixi Zhou↗

This paper presents our solution to the 2026 SoccerNet VQA Challenge. We first develop a cost-effective data synthesis pipeline driven by a Vision-Language Model (VLM), which systematically restructures raw domain data into diverse VQA samples, including concise answers and long-form responses. Second, we propose MSUE, a multi-expert question answering architecture that employs a Large Language Model (LLM) to dynamically dispatch questions to text, image, and video experts. These experts are instantiated as a strong text baseline Gemini3-Flash, a fine-tuned Qwen3-VL, and an external knowledge base, respectively, working collaboratively to enhance VQA performance. MSUE achieves an accuracy of 0.95 on the challenge benchmark, securing third place in the leaderboard.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20014

Hierarchical Control in Multi-Agent Games: LLM-based Planning and RL Execution

作者:

Jannik H\"osch↗Alessandro Sestini↗Florian Fuchs↗Amir Baghi↗Joakim Bergdahl↗Konrad Tollmar↗Jean-Philippe Barrette-LaPierre↗Linus Gissl\'en↗

arXiv:2606.20014v1 Announce Type: cross Abstract: Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments remains challenging due to sparse rewards, large state-action spaces, and the difficulty of learning coordinated strategies. We propose a hierarchical architecture where a pretrained large language model (LLM) acts as a centralized strategic controller that selects among specialized RL skill policies for a team of agents, while RL policies handle reactive low-level execution. We evaluate this hybrid system in a competitive 2v2 King of the Hill environment against behavior tree (BT) and ``Flat'' RL (end-to-end training without skill decomposition) baselines. The LLM+RL system achieves task performance statistically equivalent to hand-crafted BT (46.4\% vs 51.5\% win rate, $p=0.103$) while both significantly outperform Flat RL trained without skill decomposition. A user study ($n=15$) reveals that 60\% of participants perceive LLM+RL agents as the most human-like ($p=0.027$), citing behavioral adaptability and tactical variability. These results demonstrate that pretrained LLM reasoning can effectively orchestrate pretrained RL skills, achieving competitive multi-agent coordination and superior perceived believability without manual rule engineering.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.14788

Unifying Acoustic Features and Text with Multimodal LLMs for Neurodegenerative Screening

作者:

Qingfeng Zhang↗Yuanxiong Guo↗Yanmin Gong↗

arXiv:2606.14788v1 Announce Type: cross Abstract: Voice-based screening offers a scalable and non-invasive way to assess neurodegenerative diseases such as Alzheimer's disease (AD) and Parkinson's disease (PD), but their staging remains challenging due to the difficulty of integrating heterogeneous data. This paper presents NeurMLLM, an efficient multimodal generative framework for neurodegenerative disease staging. NeurMLLM first encodes the spectrograms and Mel-frequency cepstral coefficients of audio data with vision transformers and projects their representations into the embedding space of a large language model (LLM), where they are concatenated with transcript and demographic instruction tokens as a single unified sequence. The LLM is then instruction-tuned via Low-Rank Adaptation using task prompts to autoregressively predict a constrained label token, enabling a generative classification. By evaluating on the Bridge2AI-Voice dataset for fine-grained staging of AD and PD, we observe that NeurMLLM achieves strong performance, consistently outperforming classical machine learning methods and existing LLM-based approaches. The results show the high potential of multimodal LLMs in neurodegenerative disease staging, improving staging accuracy and supporting accessible deployment.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12186

A Resource for Enthymeme Detection in Controversial Political Discourse

作者:

Martial Pastor↗Nelleke Oostdijk↗

Enthymemes, arguments with unstated premises or conclusions, are pervasive in persuasive discourse, yet their annotation remains notoriously subjective. We present a resource of 1,482 tweets from politically controversial discourse, annotated by five annotators for the presence of enthymemes and their argument structure, designed to study label variation. We first revisit the definition of enthymemes and propose annotation guidelines anchored in Walton's argumentation schemes, offering a structured and constrained approach that nonetheless preserves room for the interpretive nature of the task. This contrasts with past resources, which tend to eliminate disagreement, obscuring its sources and preventing investigation of its potential benefits for model performance. We further propose a complexity analysis of the task, identifying where annotation imposes high cognitive load and may give rise to inconsistent annotation. Our preliminary experiments show that models trained on annotator disagreement outperform models trained on hard majority-vote labels. We close by reflecting on how structural openness in enthymeme definitions and guidelines enables the study of variation in subjective inferential processes for future resources and downstream NLP applications concerned with human inference.

阅读与讨论 → 访问原文 →