探索全球前沿学术脉络

01.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2506.14990

MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning

作者:

Tristan Tomilin↗Luka van den Boogaard↗Samuel Garcin↗Constantin Ruhdorfer↗Bram Grooten↗Fabrice Kusters↗Yali Du↗Andreas Bulling↗Mykola Pechenizkiy↗Meng Fang↗

arXiv:2506.14990v3 Announce Type: replace Abstract: Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied. Despite the motivation of lifelong learning, most continual RL papers consider only 3-10 sequential tasks, as CPU-bound environments make longer sequences impractical. Meanwhile, continual learning in cooperative multi-agent settings remains largely unexplored. To address these gaps, we introduce MEAL (Multi-agent Environments for Adaptive Learning), the first benchmark for continual multi-agent RL. By leveraging JAX and GPU acceleration, MEAL enables training on sequences of 100 tasks in a few hours on a single GPU. We find that long task sequences reveal failure modes that do not appear at smaller scales.

阅读与讨论 → 访问原文 →

02.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2606.13244

Coupling-Grouped XY-QAOA for Joint Anomaly-Feature Selection

作者:

Pauli Taipale↗

arXiv:2606.13244v1 Announce Type: new Abstract: Selecting anomalous samples and explanatory features under fixed budgets defines a coupled constrained-optimization problem. Sequential feature-first selection ranks features before choosing samples, which can overlook features whose utility depends on which samples are selected, especially when scores are calibrated from reference data that may be limited, noisy, or drifting. We instead formulate the task as joint sample-feature selection under the same fixed counts. In the analyzed formal model, calibration-error sensitivity grows linearly with the number of samples for feature-first ordering but stays constant for joint selection. We introduce Coupling-Grouped XY-QAOA, a constraint-preserving grouped-angle variant for the resulting optimization problem. On matched sparse IBM Heron R3 benchmarks, a hardware-aware implementation reduces circuit depth by 45.9%-61.3% and two-qubit gates by 2.6%-5.2% relative to Qiskit optimization level 3 on the CZ-basis target. It enables, to our knowledge, the largest reported width-depth configurations for constraint-preserving bipartite-selection QAOA hardware executions with feasible-sector retention: 64 qubits at p=2 and 36 qubits at p=3. The 20-qubit p=5 runs retain 63% valid samples. Across 36-64 qubits, fixed-angle runs yield lower-energy feasible samples than matched random-feasible sampling. Warm starts reduce the gap to strict-feasible classical references by 57.5%-80.5%, and near-budget repair matches the sparse classical reference at 36 qubits. Benchmarks show gains in balanced fixed-budget regimes, and noiseless simulations show that problem-structured angle grouping improves over same-depth XY-QAOA and matched-parameter, type-preserving randomization controls. Overall, the results support calibrated joint selection and hardware-realizable constrained-mixer execution in the tested regimes.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.08098

When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference

作者:

Yasushi Sakai↗Allen Song↗Kent Larson↗

arXiv:2606.08098v2 Announce Type: replace Abstract: Majority voting over sampled answers is the dominant unsupervised aggregator for multi-sample LLM inference. In this paper, we show a delegation-based aggregator (Propagational Proxy Voting, PPV; Sakai et al., 2025) yields an unsupervised consensus rule that beats majority on MMLU-Pro by +1.5 pp overall and +2.24 pp on the non-trivial subset (paired McNemar p ~ 1.0e-14, n = 8,099). Majority discards two signals that every sample carries: within-group letter entropy and between-group reasoning geometry. PPV exposes per-voter levers that consume exactly these two signals: When (how much weight a voter keeps on its own pick) and Whom (how it splits the remainder across peers). We drive When with letter entropy and Whom with per-question-centered embedding cosine. Our method needs no gold labels and no auxiliary training: per-question, we partition 128 sampled generations into 16 groups, compute each group's letter-level semantic entropy and reasoning embedding centroid, and feed both into a stochastic delegation matrix whose stationary distribution selects the consensus answer. We walk through an example in which PPV overturns a clear 10-6 majority for the wrong letter: the 10-voter majority cluster is geometrically incoherent (mean within-cluster cosine -0.02) while the 6-voter minority is tight (+0.26), so propagated delegation mass concentrates on the minority's answer even though entropy alone would keep the majority ahead. We further report delegation strategies with negative results that constrain the design space for unsupervised LLM aggregation. No within-question ensemble of confidence modes closes the oracle gap.

阅读与讨论 → 访问原文 →

04.

bioRxiv (Bioinfo) 2026-06-19 DOI: HASH:8d9bcc8969e61939289cca4a14c3af3f

StickForStats: automated statistical assumption validation for reproducible computational biology

作者:

Bharti↗Chakraborty↗

Reproducible computational biology depends on statistical decisions that routine workflows often skip: verifying that a differential-expression test's assumptions hold across all genes, that a strategy-comparison ANOVA is robust to non-normality, or that a meta-analysis is not distorted by publication bias. Surveys consistently find that fewer than 20% of published biomedical studies report checking these assumptions, and existing statistical software leaves validation to the analyst as an optional step. We present StickForStats, an open-source web platform that reframes assumption validation as a default precondition for every analysis. Its Guardian system–a middleware pipeline of eight validators (normality, variance homogeneity, independence, outliers, sample size, modality, linearity, homoscedasticity)–checks assumptions before execution and, on critical violations, reroutes to an appropriate nonparametric alternative with a documented decision trail. At genome scale, applying Guardian to a 91-sample synovial-sarcoma RNA-seq study (GSE271517) cascaded 90.6% of 27,221 genes to a rank-based test and flipped the differential-expression verdict for 553 genes–479 rescued from an under-powered t-test and 74 outlier-driven false positives rejected–materially changing the gene list a biologist would act on. The same automatic validation generalizes across domains: a CRISPR editing-strategy comparison (ANOVA F = 1122, with Guardian recommending Kruskal-Wallis H = 36.6), an ordinal correlation (Pearson r = 0.476 corrected to Spearman {rho} = 0.479), and a sixteen-trial clinical meta-analysis revealing severe publication bias (Egger's t = -5.78, p < 0.001); a complementary module extends the same validators to published manuscripts, checking claims against CONSORT, STROBE, ICH-E9, and JARS-Quant reporting standards. By making assumption validation automatic and transparent, StickForStats targets a tractable, under-served contributor to irreproducibility. The platform is MIT-licensed, validated against SciPy and R, and freely available at https://github.com/visvikbharti/stickforstats_new.

阅读与讨论 → 访问原文 →

05.

arXiv (quant-ph) 2026-06-25 DOI: arXiv:2606.24904

Spectral Leakage and Masking Effects in the Measurement of Hyperuniformity

作者:

Yang Jiao↗

arXiv:2606.24904v1 Announce Type: cross Abstract: The detection of hyperuniformity relies critically on accurate characterization of the small-wavenumber behavior of the static structure factor of the system. In practice, however, measurements are performed on finite subsystems or through incomplete observations that effectively mask portions of the underlying configuration. Inspired by a recent numerical study [Y. Liu, X. Li, J. Tian, X. Yan, G. Zhang, {\it J. Chem. Phys.} {\bf 164}, 094102 (2026)], we develop a unified theoretical framework that quantifies how finite windows and spatially correlated binary masks modify the observed structure factor. We show that the measured structure factor $S_{obs}(k)$ is the convolution of the intrinsic structure factor with the spectral density of the observation function, whether it is a compact window or an extended random mask. For generic hyperuniform systems with small-$k$ scaling $S(k)\sim k^{\alpha}$, finite observation window induces a universal quadratic leakage term at sufficiently small wavenumbers (i.e., $k \lesssim 1/L$), leading to an apparent $k^{2}$ scaling independent of the true exponent. The true hyperuniform exponent $\alpha$ can only be measured in the intermediate regime $1/L \ll k \ll q_c$. In stealthy hyperuniform systems, where the intrinsic structure factor possesses a spectral gap, all observed small-$k$ power arises entirely from this convolution mechanism. For spatially correlated masks, we derive the corresponding convolution relation in terms of the mask spectral density and identify conditions under which hyperuniform signatures are suppressed, preserved, or distorted. Our results establish quantitative criteria for reliably extracting intrinsic scaling exponents and distinguishing genuine hyperuniform order from measurement-induced artifacts.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.13741

High-Frequency Pricing at Scale for E-Commerce

作者:

Stefan Birr↗Tobias Huelden↗Mones Raslan↗Adele Gouttes↗Andreas Schmitt↗Mateusz Koren↗Johannes Stephan↗Robert Streek↗Manuel Kunz↗Tim Januschowski↗

arXiv:2606.13741v1 Announce Type: new Abstract: This paper presents the design, development, and implementation of a specialized forecast-then-optimize algorithmic pricing tool for sales campaigns in fashion e-commerce. Sales events present unique challenges for pricing including volatile demand patterns, rapid pricing decisions, and the need to balance short-term revenue with long-term profitability. We describe our approach combining daily-resolution demand forecasting using gradient-boosted trees with a multi-objective optimization framework that maximizes both long-term profit and net merchandise value for more than 5 million articles. Our solution addresses key limitations of existing weekly-granularity systems by implementing a forecast-then-optimize architecture that reduces pricing decision time from hours to minutes. We validate our approach through 23 A/B tests across 12 markets during 2023-2024 sales campaigns at Zalando, one of Europe's leading online fashion retailers. Experimental results demonstrate that the new pricing system achieves approximately 6% higher profit while maintaining equivalent performance on sales and revenue compared to the previous manual-algorithmic hybrid approach. Based on these results, the algorithm was successfully deployed to production and now handles the majority of algorithmic pricing decisions for sales campaigns at the company.

阅读与讨论 → 访问原文 →

07.

medRxiv (Medicine) 2026-06-22 DOI: HASH:c92e2011dba3f802ecab983d335d6548

Multisite Real-World Validation of an Electronic Health Record-Integrated Generative Artificial Intelligence Tool for Venous Thromboembolism Risk Stratification

作者:

Baughman↗D. J↗Liu↗Jee↗Young↗Knight↗A. M↗Davis↗Yegnasubramanian↗Najjar↗Whitbread↗J. J↗…

Background: Guiding risk-appropriate inpatient thromboprophylaxis requires venous thromboembolism (VTE) risk stratification; however, reliable risk determination remains inconsistent in routine care. Health systems increasingly pilot artificial intelligence (AI) tools, yet few studies demonstrate rigorous evaluation in the context of a learning health system (LHS). We evaluated the performance of a pilot electronic health record (EHR)-integrated generative AI (GenAI) system, inHealth General Reasoner (iHGR), for VTE risk stratification versus clinician order set classifications and physician-adjudicated chart review. Methods: This multisite retrospective validation study included adult inpatient admissions at Johns Hopkins Medicine between June 21, 2025, and Dec 18, 2025 (checklist-based order set from June 21, 2025 - November 19, 2025, and clinician judgement-based order set from November 29 - December 18, 2025). From 758 eligible admissions, we randomly sampled 500 balanced by site and order set periods. iHGR and clinician-selected order set classifications were compared with the reference standard (RS). Primary outcomes were iHGR sensitivity and specificity. Secondary analyses compared the order sets with the same RS to evaluate workflow comparators and error patterns. Results: iHGR achieved 81.8% sensitivity (95% CI 77.3-85.6) and 70.9% specificity (63.6-77.3). The checklist-based order set had 61.3% sensitivity (53.7-68.5) and 86.2% specificity (77.4-91.9). The clinician judgement-based order set had 78.1% sensitivity (71.3-83.7) and 65.4% specificity (54.3-75.0). False-negative iHGR classifications were associated with missed narrative risk factors. Conclusion: iHGR showed higher sensitivity for VTE risk than checklist-based order sets and clinician judgement without introducing systematic bias. In silico evaluation of pilot AI systems within LHSs can identify clinically important performance trade-offs and implementation targets before operational scale-up. Narrative clinical data abstraction remained a key limitation, supporting the use of GenAI to support rather than supplant clinician judgement.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.13443

How Much Memory Do We Need? Adaptive Memory Gate for Neural Operators

作者:

Jihyeon Hur↗Yongseok Kwon↗Min-Gi Jo↗Jeongwhan Choi↗Noseong Park↗

arXiv:2606.13443v1 Announce Type: new Abstract: Neural operators have emerged as a powerful data-driven approach for solving time-dependent PDEs. Among recent advances, memory-augmented neural operators explicitly incorporate past states and have achieved remarkable performance under low-resolution observation settings. However, existing approaches apply a fixed memory weight regardless of observation conditions, such as resolution or physical parameters, limiting their adaptability. Our preliminary experiments reveal that optimal memory weight varies with resolution and viscosity, implying that a fixed memory weight cannot simultaneously optimize performance across diverse settings. We propose AMGFNO, which dynamically modulates memory weight through a learnable gate. On the Kuramoto-Sivashinsky and Burgers' equations, AMGFNO achieves 55-79% nRMSE reduction over at low resolution, with the learned gate value automatically decreasing from $\bar{g} \approx 0.7$ to near-zero as resolution increases.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2606.24884

InSight: Self-Guided Skill Acquisition via Steerable VLAs

作者:

Maggie Wang↗Lars Osterberg↗Stephen Tian↗Ola Shorinwa↗Jiajun Wu↗Mac Schwager↗

arXiv:2606.24884v1 Announce Type: cross Abstract: Vision-language-action (VLA) models can learn manipulation skills from demonstrations, but their capabilities are bounded by the skills in the training data. We present InSight, a framework that unlocks autonomous skill acquisition by rendering VLAs steerable at the primitive-action level (e.g., "move gripper to the bowl", "lift upward", "pour the bottle"). InSight consists of two primary stages: (1) an automated segmentation pipeline that partitions demonstrations into labeled primitives via VLM plan decomposition and end-effector poses to enable VLA primitive steerability, and (2) a VLM-guided data flywheel that identifies missing primitives required to accomplish a novel task, autonomously attempts demonstrations of the missing primitives with VLM-proposed low-level control, and automatically labels, stores, and integrates successful demonstrations into the VLA training set. We evaluate InSight across simulation and real-world manipulation tasks, including block flipping, drawer closing, sweeping, twisting, and pouring, without any human demonstrations of these target skills. Once learned, these primitives can be composed to execute novel, long-horizon tasks without additional human demonstrations. Our findings demonstrate that primitive steerability provides a practical foundation for continual skill acquisition in VLA policies. Project website: https://insight-vla.github.io.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.10683

UniDexTok: A Unified Dexterous Hand Tokenizer from Real Data

作者:

Dong Fang↗Youjun Wu↗Yuanxin Zhong↗Rui Zhang↗Yunlong Wang↗Xiaosong Jia↗Yu-Gang Jiang↗

Dexterous hands are essential for fine-grained manipulation, but their hardware designs vary substantially across embodiments. Differences in kinematics, joint definitions, and degrees of freedom make it difficult to define a shared state representation compared with parallel grippers. As a result, dexterous-hand data remains fragmented and difficult to use for joint training. In this work, we propose the Unified Dexterous Hand Model (UDHM), which maps human and robot hand states into a shared 22-DoF semantic interface. Based on UDHM, we introduce UniDexTok, a retargeting-free state tokenizer that learns embodiment-conditioned discrete tokens from standardized real joint states. UniDexTok provides a unified representation for heterogeneous dexterous hands without relying on retargeting or simulation data. Compared with the recent baseline UniHM, UniDexTok reduces MPJAE from 15.63 degrees to 0.16 degrees and MPJPE from 18.51 mm to 0.18 mm, corresponding to error reductions of 98.98% and 99.03%, respectively. These results improve reconstruction from centimeter-scale to sub-millimeter accuracy. Experiments further show that data from other embodiments improves target-embodiment reconstruction accuracy, demonstrating the benefit of cross-embodiment tokenization. UniDexTok also shows strong zero-shot and few-shot reconstruction ability when new dexterous hands are introduced.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2603.27450

FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies

作者:

Chenxiao Gao↗Edward Chen↗Tianyi Chen↗Bo Dai↗

arXiv:2603.27450v2 Announce Type: replace Abstract: Thanks to their remarkable flexibility, diffusion models and flow models have emerged as promising candidates for policy representation. However, efficient reinforcement learning (RL) upon these policies remains a challenge due to the lack of explicit log-probabilities for vanilla policy gradient estimators. While numerous attempts have been proposed to address this, the field lacks a unified perspective to reconcile these seemingly disparate methods, thus hampering ongoing development. In this paper, we bridge this gap by introducing a comprehensive taxonomy for RL algorithms with diffusion/flow policies. To support reproducibility and agile prototyping, we introduce a modular, JAX-based open-source codebase that leverages JIT-compilation for high-throughput training. Finally, we provide systematic and standardized benchmarks across Gym-Locomotion, DeepMind Control Suite, and IsaacLab, offering a rigorous side-by-side comparison of diffusion-based methods and guidance for practitioners to choose proper algorithms based on the application. Our work establishes a clear foundation for understanding and algorithm design, a high-efficiency toolkit for future research in the field, and an algorithmic guideline for practitioners in generative models and robotics. Our code is available at https://github.com/typoverflow/flow-rl.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17165

Statistical Foundations of LLM-based A/B Testing: A Surrogacy Framework for Human Causal Inference

作者:

Joel Persson↗M{\aa}rten Schultzberg↗Sebastian Ankargren↗

arXiv:2606.17165v1 Announce Type: cross Abstract: Organizations and researchers show increasing interest in using large language models (LLMs) in place of human participants in A/B tests, in the hope of experimenting faster and at lower cost. We study when a treatment effect estimated on LLM outcomes recovers the effect that would have been measured on the human population of interest. Distributional equivalence between LLM and human outcomes would make any standard estimator valid but is unrealistic. We therefore develop a statistical framework that adapts surrogate endpoint theory to LLMs. The framework shows that calibrating LLM outcomes to human outcomes identifies the average treatment effect under surrogacy and comparability conditions that are jointly weaker than distributional equivalence. When these conditions fail, the effect of interest is only partially identified, and we provide diagnostics that can falsify surrogacy on historical experiments together with a bound on the worst-case bias from limited overlap. We further show that the stochasticity inherent to LLMs introduces both bias and variance, but using an average of multiple draws as the surrogate mitigates both. We illustrate the methods and theory in simulations and an application to A/B tests on Upworthy headlines. A central takeaway from our work is that the validity of LLM outcomes as surrogates can only be falsified for past treatments and never verified for new ones, so human experiments remain indispensable for novel interventions. We discuss the role of LLM choice, prompting, and temperature as design variables, and how to size human experiments for validation.

阅读与讨论 → 访问原文 →

13.

medRxiv (Medicine) 2026-06-22 DOI: HASH:763a9e8b1ac419f857e7be3be64047ca

Leishmaniasis on YouTube: a critical appraisal of the quality, reliability, and transparency of educational content

作者:

NANTALAGA↗K. C↗Nantege↗

Background: Leishmaniasis is a neglected tropical disease of significant global public health importance, for which accurate information is essential to support prevention and early care-seeking, particularly in endemic, resource-limited settings. YouTube is a widely used source of health information, but the quality and reliability of leishmaniasis-related content have not been evaluated. We aimed to assess the quality, reliability, and transparency of English-language YouTube videos on leishmaniasis. Methods: We conducted a cross-sectional analysis of YouTube videos retrieved via the YouTube Data API on 15 June 2026 using the terms "leishmaniasis," "cutaneous leishmaniasis," and "visceral leishmaniasis." After applying eligibility criteria and screening the 150 most-viewed eligible videos, 48 videos were included. Two reviewers independently assessed each video using the modified DISCERN (mDISCERN) tool, the Global Quality Score (GQS), and the JAMA benchmark criteria, with disagreements resolved by consensus. Inter-rater agreement was assessed using the intraclass correlation coefficient (ICC), and associations were examined using Spearman's rank correlation. Results: Of 402 videos retrieved, 48 met the inclusion criteria. The median GQS was 3.00 (IQR 2.00-4.00) and median mDISCERN was 3.00 (IQR 2.38-4.50), indicating moderate quality and reliability, while the median JAMA score was 2.00 (IQR 1.00-2.00), reflecting limited transparency; no video met all four JAMA criteria. The overwhelming majority of videos (47/48, 97.9%) were of professional or institutional origin. Inter-rater agreement was good to excellent (ICC 0.883 for GQS, 0.896 for mDISCERN, 1.000 for JAMA). The instruments were strongly inter-correlated (mDISCERN-GQS rho = 0.841, p < 0.001). Quality scores did not correlate positively with views, likes, or video duration; comments correlated weakly and negatively with mDISCERN (rho = -0.337, p = 0.031) and JAMA (rho = -0.381, p = 0.014). Conclusions: YouTube videos on leishmaniasis are of moderate quality and reliability but limited transparency, and are produced almost exclusively by professional sources. Video popularity, length, and age were not indicators of quality. There is a need for experts and institutions to produce clearly authored, well-sourced, and transparent educational content on this neglected tropical disease.

阅读与讨论 → 访问原文 →

14.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2603.04615

Generating function and Bloch representation for quantum Fisher tensor

作者:

Felipe P. Abreu↗Wei Chen↗

arXiv:2603.04615v2 Announce Type: replace Abstract: The Uhlmann relative amplitude between two density matrices is shown to be a generating function, through which the quantum Fisher tensor that contains both the quantum Fisher information matrix and the mean Uhlmann curvature can be obtained via differentiation over system parameters. In the pure state limit, our generating function recovers that of the quantum geometric tensor proposed by Het\'{e}nyi and L\'{e}vay, and also clarifies the fidelity and phase between two quantum states as the generating functions of the quantum metric and Berry curvature, respectively. A generic expression for the quantum Fisher tensor in terms of the Bloch representation of density matrices is derived, which facilitates the calculation of the tensor, mean Uhlmann curvature, and geometric properties derived from the quantum Fisher information matrix. Canonical ensembles of spins are adopted to demonstrate our formalism, which reveals a constant Ricci scalar, a vacuum Einstein equation, and a cosmological constant on the 3D Euclidean manifold of the magnetic field.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19938

Triangular Consistency as a Universal Constraint for Learning Optical Flow

作者:

Yi Xiao↗Carlos Rodriguez Coronel↗Jing Zhan↗Haniyeh Ehsani Oskouie↗Alex Wong↗Dong Lao↗

arXiv:2606.19938v1 Announce Type: cross Abstract: We propose triangular consistency as a first-principled constraint for optical flow, which is agnostic to network architecture, supervision type, and dataset, and applies to both image-pair and multi-frame settings. This simple but powerful constraint is to compose two flows to induce a third flow and enforce consistency among the three. The composed flows may arise from (i) image pairs, yielding cycle consistency; (ii) multiple video frames, producing longer-range motion through temporal chaining; or (iii) image pairs combined with controlled synthetic transformations, which becomes data augmentation. This triangular consistency introduces negligible computational overhead and requires no additional annotations. Since it is derived directly from the geometry of optical flow, it does not rely on model-specific assumptions and serves as a ``universal'' plug-and-play component for optical flow training. Experiments show consistent improvement across supervised, unsupervised, and transfer learning settings.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11447

AI Coding Agents Can Reproduce Social Science Findings

作者:

Meysam Alizadeh↗Mohsen Mosleh↗Fabrizio Gilardi↗Atoosa Kasirzadeh↗Joshua Tucker↗

Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic evaluation across social sciences remains limited. Existing evaluation benchmarks are insufficient, either small or conflate agent performance with problems in the reproduction materials themselves, such as code that fails to execute correctly. Here we introduce SocSci-Repro-Bench, a benchmark of 221 tasks spanning four disciplines and 13 substantive domains, constructed from studies whose results are either fully reproducible with available materials or demonstrably non-reproducible due to missing data, allowing us to isolate agents' reproduction capacity. Evaluating two frontier coding agents, Claude Code and Codex, we find that both can reproduce a large share of social science findings, with Claude Code substantially outperforming Codex. These reproduction rates considerably exceed those previously reported for general-purpose LLM-based agents on comparable reproducibility benchmarks. Both agents also perform strongly on a reasoning task requiring identification of underlying research questions, and additional analyses suggest that results are not primarily driven by memorization. Providing the original paper PDF alongside replication materials modestly improves performance but introduces bias on tasks where reproduction is impossible. We also show that agents can be nudged toward confirmatory specification search through subtle prompt framing. Together, these findings suggest that at least some frontier coding agents can serve as reliable executors of computational workflows while underscoring the need for careful benchmarking and prompt design as AI systems assume larger roles in scientific production.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.18021

LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI

作者:

Lalit Yadav↗Akshaj Gurugubelli↗

AI systems deployed in legal workflows hallucinate at rates that aggregate metrics report at ~52%, but this average conceals where errors concentrate and in which direction they run, leaving compliance officers without an actionable signal for trustworthy deployment. We present LegalHalluLens, an auditing framework with three components: typed hallucination profiles across four legally-motivated claim categories (numeric, temporal, obligation/entitlement, factual) over CUAD (Hendrycks et al., 2021); a Risk Direction Index (RDI) that reduces omission-versus-invention bias to a single deployment-comparable scalar; and a typed debate pipeline calibrated to both magnitudes and directions. Across 510 contracts and 249,252 clause-level instances we measure a within-model gap of approximately 38-40 pp between obligation/numeric and temporal claims that aggregate reporting hides, and show that two systems with matched 52% rates can carry opposite RDIs. The debate pipeline reduces fabricated detections by 45% with per-category gains tracking the diagnosis, matching commercial APIs with a substantially smaller backbone (4B active parameters). Typed profiles and RDI surface failure modes that aggregate metrics hide; we further show these diagnostics serve as calibration inputs for multi-agent debate pipelines, where Skeptic challenges and asymmetric gates targeted at measured failure modes outperform generically-tuned debate. The framework supports direction-aware procurement, accountability, and agent design for legal AI deployed in the wild.

阅读与讨论 → 访问原文 →

18.

medRxiv (Medicine) 2026-06-24 DOI: HASH:02d90d6d97a095f84592bd9424637023

Pembrolizumab, Temozolomide and HSPPC-96 Vaccine in Newly Diagnosed Glioblastoma Post-Chemoradiation: Results from a Multi-institutional, Phase 2, Randomized, Placebo-Controlled Trial

作者:

Ozer↗B. H↗Lindhorst↗S. M↗Merrell↗R. T↗Trevino↗C. R↗Rudnick↗J. D↗Avgeropoulos↗N. G↗…

Background: GBM is one of the most common and most aggressive brain tumors in adults, and upfront standard of care treatment has limited efficacy. Immune checkpoint inhibitor strategies have significantly improved outcomes in various solid tumors but have not proven effective in GBM, suggesting other strategies may be needed to realize their full potential. Methods: GBM patients were treated with upfront standard of care chemoradiation with temozolomide and pembrolizumab, followed by adjuvant temozolomide and pembrolizumab for six nine-week cycles. Depending on production of sufficient vaccine, patients were randomized into HSPPC-96 vaccine or placebo group (q4 weeks) while those with failed vaccine production continued on study unblinded as an ancillary group. The primary objective was overall survival at one year, and secondary endpoints were progression-free survival at six months, overall and progression-free survival, radiographic response, and tolerability by patient-reported outcomes and adverse event documentation. Results: 90 patients were screened, 32 were treated (8 vaccine, 9 placebo, 15 ancillary), and 26 were evaluable for radiographic responses prior to accrual termination. The study did not meet its primary endpoint of overall survival at one year (65.5% in vaccine group, 75% in placebo). Progression-free endpoints were mildly improved in the vaccine group but were not significant, and response rates were not significantly different. The regimen was well-tolerated and safe. Conclusions: Though limited by early discontinuation, these findings do not support the combination of pembrolizumab and HSPPC-96 vaccine with standard of care therapy. Trials Registration: ClinicalTrials.gov identifier: NCT03018288

阅读与讨论 → 访问原文 →

19.

arXiv (quant-ph) 2026-06-25 DOI: arXiv:2606.25471

A phase-space approach for performing continuous-variable quantum teleportation with a non-Gaussian resource

作者:

Ankita↗Arpita Chatterjee↗

arXiv:2606.25471v1 Announce Type: new Abstract: We present a comprehensive phase-space analysis of continuous-variable quantum teleportation employing a photon-subtracted two-mode squeezed Fock state (PS-TMSFS) as an entangled resource. We investigate the usefulness of PS-TMSFS within the Braunstein-Kimble teleportation protocol. We explain the generation scheme for the resource state and derive the analytical expression for the success probability associated with the photon-subtraction process. The Wigner characteristic function of PS-TMSFS is calculated and then employed to determine the fidelity for coherent and squeezed state inputs. The dependence of the success probability and teleportation fidelity on the squeezing parameter and beam-splitter transmissivity is analyzed in detail for both symmetric and asymmetric photon-subtraction scenarios. We find that the teleportation fidelity exhibits a strong dependence on the resource parameters and is highly sensitive to variations in the subtraction process. The photon-subtraction process modifies the non-Gaussianity of the resource state, but no substantial enhancement of the teleportation fidelity is detected. Despite the non-Gaussian character of the resource state, fidelity above the classical coherent-state benchmark is observed only for the symmetric $(1,1) $ photon-subtraction configuration in the low-squeezing regime that decreases with increasing squeezing. The remaining configurations remain below the classical threshold throughout the parameter range considered. These findings indicate that the PS-TMSFS may not be a suitable resource for continuous-variable quantum teleportation and offers insight into the limitations of this class of non-Gaussian states.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-25 DOI: arXiv:2606.08998

The Token Not Taken: Sampling, State, and the Stochasticity of AI Agents

作者:

Muhammad Zia Hydari↗Raja Iqbal↗

arXiv:2606.08998v2 Announce Type: replace Abstract: Agentic AI systems can behave differently across runs: the same request may produce a different plan, a different tool call, a different code edit, or a different final answer. Such variability arises from several layers that are often conflated. At the core of many current agents is a foundation model, a large pretrained model adaptable to many downstream tasks, embedded in an orchestration loop that plans, calls tools, observes results, and updates state. One explicit intrinsic source of variability in such systems is token generation: the model computes scores over possible next tokens, the scores are converted into probabilities, and a decoder may sample tokens using a pseudo-random number generator. A small sampled token difference can then propagate upward into a different tool call, code path, search query, or agent state. Other sources of variability are extrinsic to token sampling, including changing environments, live data, serving infrastructure, batch effects, and numerical details. By separating these layers, this tutorial clarifies what it means to call agentic AI systems stochastic, when such variability can be reproduced under matched conditions, and why deterministic execution need not imply identical behavior in deployed settings.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12191

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application

作者:

Jiachun Li↗Zhuoran Jin↗Tianyi Men↗Yupu Hao↗Kejian Zhu↗Lingshuai Wang↗Dongqi Huang↗Longxiang Wang↗Shengjia Hua↗Lu Wang↗Jinshan Gao↗Hongbang Yuan↗…

Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities. Despite this importance, existing work lacks a systematic categorization and deep analysis. This paper systematically studies current researches on agentic environments from the perspective of the environment engineering lifecycle, covering their modeling, synthesis, evaluation and application. Specifically, the paper first introduces representative environments from the perspectives of eight attributes and eight domains, providing detailed analyses of their development paths and highlighting their core capabilities. Second, for automated environment synthesis, two paradigms are introduced, such as symbolic synthesis and neural synthesis. This paper also shows different environment evaluation methods in each paradigm. Thirdly, the corresponding environment applications from the perspective of agent-environment co-evolution are discussed. In specific, the paper characterizes the primary pathways for agent evolution in dynamic environments from four complementary perspectives: memory-centric experience evolution, orchestration-centric workflow evolution, trajectory-centric offline evolution, and exploration-centric online evolution. And three paradigms of environment evolution are identified, namely neural-driven, difficulty-driven, and scaling-driven approaches. At last, several promising future directions are discussed, including Environment-as-a-Service, Multi-agent Environments, and Neural-Symbolic Environments.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15788

GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreaking

作者:

Aman Anifer↗Vignesh Kumar Kembu↗Vishnu M↗Antonino Nocera↗Vinod P↗Amal Murali PK↗Akshay S Rajan↗

arXiv:2606.15788v1 Announce Type: cross Abstract: Large Language Models (LLMs) constitute pivotal components within the AI-dominated information technology ecosystem. To mitigate risks associated with harmful or policy-violating outputs, commercial systems employ advanced alignment strategies and multi-layered content moderation mechanisms. Despite these safeguards, recent research has demonstrated that LLMs remain vulnerable to adversarial manipulation, particularly through jailbreaking and prompt injection techniques. In this work, we propose GAS-Leak-LLM a novel jailbreaking attack based on a genetic algorithm that systematically evolves adversarial suffix to bypass safety constraints. Operating in a strict black-box setting, our method requires no access to model parameters or internals, thereby reflecting realistic threat scenarios in deployed systems. Through the iterative application of selection, mutation, and crossover heuristics, the framework systematically explores the discrete prompt space to identify high-fitness adversarial suffixes. Empirical findings reveal critical shortcomings in existing safety enforcement mechanisms and confirm the effectiveness and practical viability of the proposed attack.

阅读与讨论 → 访问原文 →

23.

medRxiv (Medicine) 2026-06-10 DOI: HASH:a903a8e94f3f107ef892a0011b0ee22b

Frozen elephant trunk repair in heritable thoracic aortic disease: Impact of genetic aortopathy on long-term outcomes - A multicenter analysis

作者:

Berger↗Peterss↗Pitts↗Kempfert↗Nucera↗Yildiz↗Holubec↗Haas↗Czerny↗Kreibich↗Kletzer↗Discher↗…

Aims This multicenter study aims to compare outcomes of total aortic arch replacement (TAR) using the frozen elephant trunk (FET) technique in patients with and without heritable thoracic aortic disease (HTAD) and to assess whether HTAD influences postprocedural adverse aortic events (AAEs). Methods From 06/2007 to 05/2024, aortic databases from 13 European centers were screened for HTAD patients undergoing TAR with FET. All consecutive dissection and aneurysm non-HTAD patients from the four core centers served as comparator. The primary outcome was AAE, a composite of diameter progression, distal stent graft induced new entry (dSINE), malperfusion, rupture and pseudoaneurysm at 5 years after FET implantation. Results Of 2739 FET patients, 196 (7.2%) were diagnosed with HTAD. The control group consisted of 867 non-HTAD FET patients. Marfan syndrome was the most common condition (72%), followed by Loeys-Dietz syndrome (11%), vascular Ehlers-Danlos syndrome (5.6%) and Turner syndrome (2.0%). Seventeen (8.8%) patients were diagnosed with ns-HTAD. At 5 years 46 (24%) AAEs occurred in the HTAD group, 169 (20%) in the non-HTAD group (p=0.2). Diameter progression was the most common event (10% vs. 12%; p=0.6), followed by dSINE (5.8% vs. 4.5%; p=0.5), malperfusion (4.2% vs. 3.3%; p=0.5), rupture (2.1% vs. 0.7%; p=0.09) and pseudoaneurysm (0.5% vs. 0.2%; p=0.5). Conclusions The FET technique appears safe and effective for acute and chronic aortic disease in HTAD patients, with outcomes comparable to non-HTAD cases and no increase in graft-related complications, challenging traditional concerns about stent graft use in genetically mediated aortic disease.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2605.03289

Imbalanced Classification under Capacity Constraints

作者:

Daniel Fraiman↗Ricardo Fraiman↗

arXiv:2605.03289v2 Announce Type: replace-cross Abstract: Detecting observations from a minority class under severe class imbalance is a central challenge in applications such as fraud detection, medical screening, and industrial quality control. In these settings, each positive prediction triggers a costly follow-up action, an MRI scan, a transaction audit, whose execution is subject to real operational constraints. This paper proposes a formal classification framework under capacity constraints: given a user-defined bound limit $b$ on the proportion of observations that can be labeled as belonging to the minority class, the goal is to find the classifier that maximizes sensitivity on that class. We characterize the optimal classifier under this constraint and establish its equivalence with the classical Bayes classifier under a reweighting of the prior probabilities. We also introduce a capacity-adjusted performance metric $M$ that accounts for the effective detection rate when the capacity constraint is binding. The framework is implemented on top of standard learning methods, k-NN, SVM, random forests, and neural networks, and statistical consistency is established for each. We further show that these methods reduce to post-hoc thresholding when no hyperparameters are oriented toward the capacity-constrained objective, and introduce a capacity-aware support vector machine that exploits the constraint during training and achieves the strongest empirical performance. Experiments on the Taiwanese credit card default dataset confirm that capacity-constrained classifiers substantially outperform both classical approaches and SMOTE under high imbalance regimes. The framework extends naturally to multiclass settings and online environments.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CL) 2026-06-25 DOI: arXiv:2606.25354

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing

作者:

Yutong Yin↗Mingyu Jin↗Jin Pan↗Changyi Yang↗Zijie Xia↗Dhruv Pai↗Shuming Hu↗Zhen Zhang↗Chenyang Zhao↗Jinman Zhao↗Wujiang Xu↗Raymond Li↗…

Test-time scaling improves language-model reasoning, but existing approaches often face a difficult trade-off: long chain-of-thought sampling remains single-threaded, while sentence- or solution-level search can be computationally expensive and hard to train end-to-end. We introduce Local Branch Routing (LBR), a token-level test-time scaling framework that expands a small local lookahead tree, forwards all sampled branches through the language model, and uses a lightweight router to select the depth-1 subtree to commit. By routing over the hidden states of candidate local futures, LBR allows each token decision to use evidence beyond the root next-token distribution while avoiding full solution-level search. The resulting prune-shift-grow decoding process preserves discrete branch identities and defines a tractable tree-trajectory likelihood: newly grown nodes are counted when first sampled, and router decisions are assigned explicit probabilities. This enables end-to-end reinforcement learning with verifiable rewards, jointly optimizing the base model and router under the same likelihood-ratio principle as discrete-token RLVR. On synthetic hierarchical-planning tasks, LBR shows that post-candidate hidden states provide useful routing evidence. On mathematical reasoning benchmarks, LBR improves both Pass@1 and Pass@32 over discrete chain-of-thought, vanilla discrete-token RLVR, and RL-compatible soft-token branching baselines. These results suggest that lightweight local branching offers an efficient, trainable, and discrete form of language-model test-time scaling.

阅读与讨论 → 访问原文 →