探索全球前沿学术脉络

01.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16322

PaperJury: Due-Process Review for Bounded LaTeX Revision

作者:

Yiran Wang↗Ruixuan An↗Biao Wu↗Wenhao Wang↗

Pre-submission hardening of human-authored LaTeX computer science papers differs from drafting assistance because it requires adversarial whole-paper review, explicit no-fix outcomes, and bounded artifact-safe revision. Existing writing assistants, critique generators, and judge-centered loops lack durable issue identity across rounds, deterministic routing from critique to adjudication, and manuscript control that can reject invalid concerns or defer author-dependent ones. We present PaperJury, a closed-loop review-verdict-revise-verify system built on a deterministic-versus-semantic split: deterministic orchestration manages decomposition, a frozen claim spine, a durable ledger, routing, stopping, and exact-once patch application, while semantic agents are limited to bounded review, judgment, and repair. PaperJury combines bounded holistic review, contestability-based routing, a due-process trial, and risk-proportional guard chains for anchor-bounded edits, yielding terminal outcomes of invalid-drop, valid-fixable, and author-required. In a two-arm expert-review evaluation on held-out Vision, natural language processing, and machine learning papers against four baselines, we assess issue quality, verdict and routing quality, edit safety, convergence behavior, and cost, supporting the thesis that load-bearing safety and completion logic should reside in deterministic orchestration rather than model discretion. PaperJury is available at https://github.com/u7079256/paperjury.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.14199

OdysSim: Building Foundation Models for Human Behavior Simulation

作者:

Xuhui Zhou↗Weiwei Sun↗Weihua Du↗Jiarui Liu↗Haojia Sun↗Qianou Ma↗Tongshuang Wu↗Yiming Yang↗Maarten Sap↗

Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation. Yet helpfulness-driven post-training pulls them toward a homogeneous, overly agreeable assistant register, creating a behavioral Sim2Real gap. We present OdysSim, the largest open systematic investigation of behavioral foundation models, i.e., models trained to simulate human behavior at scale. We propose SOUL, a taxonomy of five capability axes (CONV, SS, COG, ROLE, EVAL) that unifies 62 datasets and 23 benchmark tasks under one framework. Specifically, we curate the OdysSim corpus (21.4M interactions, 10B tokens, retrofitted with back-generated social contexts), construct the SOUL-Index benchmark, and develop an end-to-end training recipe combining midtraining, task-specific RL, and expert distillation. The resulting open 8B OSim model ranks first or tied-first on 8 of 23 tasks, outperforming any individual frontier model by this count, with the strongest gains on conversational and social tasks. Its outputs are also more human-like in length, formatting, and word choice, and it transfers zero-shot to out-of-distribution user simulation on $\tau$-bench, nearly matching real users on reaction alignment (93.2 vs. 93.5). We further show that LLM-as-judge RL induces reward-hacking patterns, and that our detectors can mitigate them during post-training. Together, our findings suggest that behavioral foundation models require rethinking the LLM training paradigm. We release all artifacts to support future research.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15497

Towards End-to-End Automation of AI Research

作者:

Yutaro Yamada↗Robert Tjarko Lange↗Cong Lu↗Chris Lu↗Shengran Hu↗Jakob Foerster↗David Ha↗Jeff Clune↗

arXiv:2606.15497v1 Announce Type: new Abstract: The automation of science is a long-standing ambition in the field of AI. While the community has made significant progress in automating individual components of the scientific process, a system that autonomously navigates the entire research lifecycle – from conception to publication – has remained out of reach. Here, we present the strongest demonstration to date toward automating the entire process end-to-end. We present The AI Scientist, which creates research ideas, writes code, runs experiments, plots and analyzes data, writes the entire scientific manuscript and performs its own peer review. Its ideas, execution, and presentation are of sufficient quality to produce a manuscript generated by an AI system that passes the first round of peer review at a major machine learning conference workshop. The workshop has an acceptance rate of 70 percent. Our system leverages modern foundation models within a complex agentic system. We evaluate The AI Scientist in two settings: a focused mode using human-provided code templates as an initial scaffold to conduct research on a specific topic, and a template-free, open-ended mode that leverages agentic search for wider scientific exploration. Both settings produce diverse ideas and automatically test, report on, and evaluate them. This achievement demonstrates AI's growing capacity for scientific contribution and signifies a potential paradigm shift in how research is conducted. As with any impactful new technology, there could be significant risks, including taxing overwhelmed review systems and adding noise to scientific literature. However, if developed responsibly, such autonomous systems could greatly accelerate scientific discovery.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18617

AI-Driven Assessment of Human Tutors: Linking Training Performance to Real-Life Practice

作者:

Danielle R. Thomas↗Marie Cynthia Abijuru Kamikazi↗Clara Brandt↗Conrad Borchers↗Kenneth R. Koedinger↗

arXiv:2606.18617v1 Announce Type: cross Abstract: There exist numerous tutor training platforms. However, few provide AI-driven training and evaluation for human tutors based on real-life performance. We present an AI-driven system that assesses both open responses during training and authentic real-life tutoring. Unlike platforms that only assess learning through online training or simulations, our system utilizes Generative AI (Gemini-2.5-pro) to analyze transcriptions of authentic tutoring, measuring the transfer of tutor skills to real-life application. Human tutors instructing students remotely in math (N=86) completed six scenario-based lessons, averaging a significant 7.4% learning gain. Using mixed-effects models across 405 session-to-lesson pairs, we found that training performance significantly predicted real-life transcript scores with an effect size of 0.25 SD. Model comparison (AIC/BIC) indicated averaging open response and multiple choice performance during training predicted real-life tutor performance best, although open responses were comparatively more predictive. Exploratory analysis showed that after training, tutors were significantly more likely to encounter pedagogical opportunities to apply their skills (61.1% to 68.9%) and demonstrated higher execution quality within those opportunities (65.5% to 68.1%). Interrupted time series analysis suggested that these tutor improvements were part of a gradual trend over time rather than an immediate intervention effect of training. We illustrate an AI-driven method to link tutor training with real-life assessment. In doing so, we contribute open datasets, AI prompts, and scoring rubrics to support transparency and reproducibility.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20400

The Significance of Style Diversity in Annotation-Free Synthetic Data Generation

作者:

Zahra Abbasiantaeb↗Zeno Belligoli↗Omar Essam↗Mohammad Aliannejadi↗

arXiv:2606.20400v1 Announce Type: new Abstract: Generating high-utility synthetic data for intent classification typically requires human-annotated seed data, which is often unavailable in fast-paced industrial settings. In this paper, we propose a framework for synthetic dialogue generation that works entirely without human-annotated data, relying solely on intent definitions. Our proposed dialogue generation framework utilizes two different types of topic and style attributes to improve data diversity. Also, we propose two novel post-hoc stylization models called Univ and Exam to transform synthetic LLM-generated utterances into more varied, human-like linguistic styles. To enhance data quality, we utilize an LLM-as-a-judge filtering process. Experimental results on both industrial and public datasets demonstrate that the proposed approach achieves up to 93.3% of the performance obtained using human-annotated training data. Crucially, the findings reveal that style diversity is more critical than topic diversity for synthetic data utility, as it prevents models from learning spurious stylistic correlations. Furthermore, the study shows that incorporating style attributes during the generation process is more effective than post-hoc style adaptation.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19509

LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data

作者:

Akshat Dasula↗Prasanna Desikan↗Jaideep Srivastava↗

arXiv:2606.19509v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied to structured clinical data, yet whether they can recognize the limits of their own knowledge on such tasks remains unexplored. We study this question through the lens of cross-model attribution divergence with the goal of reducing epistemic uncertainty for structured tasks, comparing Qwen 2.5 7B and XGBoost on a prediction task via attribution divergence analysis. We report four findings. First, LLM verbalized confidence is epistemically vacuous, it outputs a near-constant (0.856-0.937) regardless of whether accuracy is 49% or 75.3%, tracking prompt format rather than prediction quality. Second, the LLM exhibits an inverse difficulty effect: accuracy drops to 64.8% when XGBoost is 99% correct, but matches XGBoost (73.8% vs. 73.1%) when it is moderately uncertain. Third, few-shot examples and SHAP-derived feature evidence are orthogonal, super-additive interventions: they reduce the Attribution Disagreement Score (ADS) from 1.54 to 0.38 and improve accuracy from 49% to 75.3% without training. Fourth, a cross-model calibrator that determined LLM reliability using attribution divergence signals reduces expected calibration error from 0.254 to 0.080, replacing uninformative verbalized confidence with patient-specific reliability estimates, without accessing model internals or requiring repeated inference. We frame these findings as a cold start problem for LLMs on structured data and outline a path toward genuine epistemic self-awareness.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2510.01663

Shift-Invariant Attribute Scoring for Kolmogorov-Arnold Networks via Shapley Value

作者:

Wangxuan Fan↗Ching Wang↗Siqi Li↗Nan Liu↗

arXiv:2510.01663v2 Announce Type: replace-cross Abstract: For many real-world applications, understanding feature-outcome relationships is as crucial as achieving high predictive accuracy. While traditional neural networks excel at prediction, their black-box nature obscures underlying functional relationships. Kolmogorov–Arnold Networks (KANs) address this by employing learnable spline-based activation functions on edges, enabling recovery of symbolic representations while maintaining competitive performance. However, KAN's architecture presents unique challenges for network pruning. Conventional magnitude-based methods become unreliable due to sensitivity to input coordinate shifts. We propose ShapKAN, a pruning framework using Shapley value attribution to assess node importance in a shift-invariant manner. Unlike magnitude-based approaches, ShapKAN quantifies each node's actual contribution, ensuring consistent importance rankings regardless of input parameterization. Extensive experiments on synthetic and real-world datasets demonstrate that ShapKAN preserves true node importance while enabling effective network compression. Our approach improves KAN's interpretability advantages, facilitating deployment in resource-constrained environments.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15216

Spokes: Optimizing for Diverse Pretraining Data Selection

作者:

Clarence Lee↗Yejin Choi↗Luke Zettlemoyer↗Pang Wei Koh↗Hai Leong Chieu↗

Diversity plays a critical role in data selection, improving performance under fixed data budgets by reducing redundancy and repetition. However, optimizing for diversity is inherently challenging, as it is a set-level property that depends on interactions between data points rather than individual examples. As a result, existing approaches typically rely on proxies or approximations, which often fail to ensure sufficiently diverse subsets. In this work, we directly optimize diversity by introducing a probabilistic diversification framework based on the G-Vendi score, optimized via exponentiated gradient descent. Our method produces subsets that are substantially more diverse than those obtained via random sampling, achieving a +489 increase in G-Vendi score on a 500k-sample subset. We evaluate our approach on FineWeb and DCLM, where it consistently outperforms existing methods. Notably, SPOKES (diversity-only) improves average downstream performance by +0.4 and +0.5 points over random sampling on DCLM and FineWeb, respectively. More importantly, jointly optimizing for both quality and diversity yields the strongest results: SPOKES achieves gains of +1.5 and +1.4 points on DCLM and FineWeb, outperforming all baselines, including semantic deduplication and quality filtering.

阅读与讨论 → 访问原文 →

09.

arXiv (math.PR) 2026-06-15 DOI: arXiv:2503.18045

Ergodicity for stochastic 2D Boussinesq equations with a highly degenerate pure jump Levy noise

作者:

Jianhua Huang↗Xuhui Peng↗Xue Wang↗Jiangwei Zhang↗

arXiv:2503.18045v2 Announce Type: replace Abstract: This study aims to analyze the ergodicity for stochastic 2D Boussinesq equations and explore the impact of a highly degenerate pure jump L\'{e}vy noise acting only in the temperature equation, where this noise could appear on only a few Fourier modes. By leveraging the equi-continuity of the semigroup established through Malliavin calculus and an analysis of stochastic calculus, together with the weak irreducibility of the solution process, we prove the existence and uniqueness of the invariant measure. Moreover, we overcome the main challenge of establishing time asymptotic smoothing properties of the Markovian dynamics corresponding to this system by conducting spectral analysis of the Malliavin covariance matrix.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13658

Before You Think: System 0, AI-Mediated Cognition and Cognitive Colonization

作者:

Marianna Bergamaschi Ganapini↗Massimo Chiriatti↗Enrico Panai↗Giuseppe Riva↗

arXiv:2606.13658v1 Announce Type: new Abstract: This paper examines three recent frameworks for understanding the cognitive and epistemic consequences of artificial intelligence: Tri-System Theory, Thinkframes, and System 0. It argues that while the first two capture important dimensions of AI's influence on individual reasoning and collective epistemic practices, System 0 occupies a theoretically distinctive position that neither can fully replicate. The paper introduces the concept of cognitive colonization, according to which AI systems can embed external interests within the architecture of the self in ways that are difficult for users to perceive. Because such systems are already widely deployed, understanding these invisible forms of influence is an urgent philosophical and practical task.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2605.21027

Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIs

作者:

Gundeep Singh↗Parsa Kavehzadeh↗Jing Xia↗Xue-Yong Fu↗Julien Bouvier Tremblay↗Md Tahmid Rahman Laskar↗Vincent Lum↗Shashi Bhushan TN↗

Enterprise analytics aims to make organizational data accessible for decision-making, yet non-technical users still face barriers when using traditional business intelligence tools or Text-to-SQL systems. While recent Text-to-SQL approaches based on Large Language Models (LLMs) promise natural language access to structured data, they fall short in enterprise settings where analytics pipelines rely on governed APIs rather than raw databases. In practice, these APIs encapsulate complex business logic to ensure consistency, auditability, and security. However, delegating mathematical or aggregation logic to an LLM introduces reliability and compliance risks. To this end, we present Analytic Agent, an LLM-based agentic system that translates natural language intents into secure interactions with enterprise analytics APIs. Evaluated on 90 real enterprise use cases constructed by domain experts, it reliably interprets user goals, validates permissions, executes governed queries, and generates compliant visualizations through multi-step reasoning and policy-aware orchestration.

阅读与讨论 → 访问原文 →

12.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2602.14736

Coupled integrated photonic quantum memristors using a single photon source made of a colour center

作者:

Alessio Baldazzi↗Roy Philip George Konnoth Ancel↗Sebastiano Guaraldo↗Ivan Fattori↗Xuan Chen↗Ziad Abi Akar↗Regis Deturche↗Stefano Azzini↗Christophe Couteau↗Lorenzo Pavesi↗

arXiv:2602.14736v2 Announce Type: replace Abstract: Photonic quantum memristors provide a measurement-induced route to nonlinear and history-dependent quantum dynamics. Experimental demonstrations have so far focused on isolated devices or simple cascaded devices configurations. Here, we experimentally realize and characterize a network of two coupled photonic quantum memristors with crossed feedback, implemented on a silicon nitride photonic integrated circuit and fed by a room-temperature single-photon source based on a silicon-vacancy color center SiV$^-$ in a nanodiamond. Each memristor consists of an integrated Mach-Zehnder interferometer whose transfer function is adaptively updated by photon detection events on another memristor, thus generating novel non-Markovian input-output dynamics with an enhanced memristive behaviour compared to single devices. In particular, we report inter-memristor input-output hysteresis curves exhibiting larger form factors and displaying self-intersecting loops, respectively revealing marked bistability and self-intersecting hysteresis geometry. Furthermore, numerical simulations show how these features emerge from the interplay between memory depth and relative input phase, for both intra- and inter-memristor input-output relations. We experimentally test the performance of our system in the NARMA task. Our results establish coupled integrated photonic quantum memristors as scalable nonlinear building blocks and highlight their potential for implementing compact quantum neuromorphic and reservoir computing architectures.

阅读与讨论 → 访问原文 →

13.

bioRxiv (Bioinfo) 2026-06-18 DOI: HASH:b09d8b1d795c4c84d6f6cc882a392862

Bayesian modeling of longitudinal metatranscriptomes of broiler meat spoilage microbiomes shows shared predictive signature associated with spoilage at refrigerated temperatures

作者:

Nushi↗Manninen↗Johansson↗Honkela↗Björkroth↗

Microbial spoilage of packaged meat is driven by complex microbial succession and related metabolic activity, yet conventional shelf-life assessment is mainly based on shelf-life studies relying on culturing and sensory analysis. In routine quality assurance, results are obtained retrospectively, and they are only indirectly linked to the metabolic activity related to sensory deterioration. Functional, time informative approaches that capture the active metabolic state of the spoilage microbiome and predict the rate of spoilage are lacking. We developed a censoring-aware Gaussian process (CAGP) framework to model longitudinal pathway expression profiles from broiler meat metatranscriptomes collected over consecutive storage days at 4 or 6{degrees}C. Samples were annotated using odor-based sensory scores defining fresh, early-spoilage, and late-spoilage phases. Because observed zeros in pathway-level data may reflect non-detection rather than true absence, the model treats low values as left-censored observations below a detection threshold while estimating smooth temporal trajectories with uncertainty. In leave-one-out prediction within the 4{degrees}C time series, predicted sampling days differed from the true days by an average of 0.43 days, and predicted spoilage phases agreed with the sensory classification. Trajectories learned at 4{degrees}C also transferred to an independent 6{degrees}C time series at the spoilage-phase level, suggesting that shared functional spoilage programs are preserved despite temperature-dependent changes in spoilage rate. Cross-entropy ranking further identified pathway modules carrying time- and phase-informative signals across temperatures. Overall, this framework provides a probabilistic approach for linking metatranscriptomic functional dynamics to sensory spoilage progression, supporting shelf-life assessment beyond retrospective microbial enumeration.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14699

Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control

作者:

Ruining Li↗Yuxin Yao↗Matt Zhou↗Chuanxia Zheng↗Christian Rupprecht↗Joan Lasenby↗Shangzhe Wu↗Andrea Vedaldi↗

Reconstructing articulated 3D objects is important for animation, gaming, and robotic simulations. Recent neural networks can estimate the articulated structure of 3D objects, but their generalization remains limited by the scarcity of annotated data for this task. To address this gap, we introduce Instruct-Particulate, a model that takes a 3D mesh together with a target kinematic specification, including part descriptions, connectivity, joint types, and optional point prompts, and predicts the corresponding kinematic part segmentation and joint motion parameters. The kinematic specification disambiguates the task and allows the model to target annotations of different granularity, thereby making it possible to use more abundant heterogeneous training data. At test time, the kinematic specification can be obtained automatically from large-scale vision-language models, so the model can be applied to any input mesh. To train our model at scale, we construct a heterogeneous dataset of more than 150,000 articulated 3D objects, extending existing publicly available collections with data obtained by partially labelling other 3D models (monolithic or already decomposed into parts) with kinematic labels by means of vision-language models. Experiments show that our model generalizes better across categories and to AI-generated meshes, enabling articulated asset reconstruction from real-world images via image-to-3D models.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18586

APT: Atomic Physical Transitions for Causal Video-Language Understanding

作者:

Shang Wu↗Haoran Lu↗Songling Liu↗Chenwei Xu↗Lie Lu↗Pranav Maneriker↗Fan Du↗Manling Li↗Zhaoran Wang↗Han Liu↗

Physical events are not understood by their names alone, but by the causal state changes that compose them. A clip-level label such as "bounce" can be correct while hiding the process that makes the event physically valid, from support loss and contact onset to rebound and settling. To make this hidden process explicit, we introduce Atomic Physical Transitions (APTs): minimal, temporally localized state changes that bind a visible cue to an active physical mechanism and before/after dynamical regimes. An APT chain represents a video as an ordered causal transition sequence rather than a single aggregate event label: event labels tell what happened; APT chains explain why it happened. To make APTs learnable by VLMs, we construct mixed-source APT data from human annotations and simulator ground truth, covering 14 transition types across contact, gravity, friction, and rotation/stability, with 27,303 timed instances over 1,246 trials. Using this data, we find that current VLMs miss transition-level physics, with zero-shot recall at most 14% and errors dominated by missed transitions. Direct fine-tuning on APT chains improves transition detection but causes event-level forgetting, indicating that the model learns a specialized answer format rather than a reusable physical representation. We therefore propose APT-Tune, a parameter-efficient recipe that teaches VLMs to use causal transitions without forgetting how to answer video questions. It combines image-pad-aware supervision, format-conditional co-training, and mechanism-conditioned domain-to-type decoding to make APT learning format-robust and physically grounded. With only 11 M LoRA parameters on Qwen3-VL-2B, APT-Tune substantially improves APT recall while also improving event-level video transfer. These results show that APTs are not a new answer format, but a human-aligned causal supervision signal for physical video understanding.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11195

From Consumption to Reflection: Designing Human-AI Relations for Stable Reasoning

作者:

Rikard Rosenbacke↗Carl Rosenbacke↗Victor Rosenbacke↗Martin McKee↗

arXiv:2606.11195v1 Announce Type: cross Abstract: Large language models (LLMs) have transformed how humans access information, but not how we reason with it. Their fluency accelerates consumption while bypassing the slow, reflective processes that underpin sound judgment. This paper introduces Relational Reflective Intelligence (RRI), an inference-time governance layer that operationalizes reflection through auditable reasoning loops. RRI operates not inside the model but around it, providing a practical structure for stable, auditable reasoning between humans and LLMs. The core premise is that LLMs inherit cognitive vulnerabilities similar to those that shape human thought: reliance on intuitive shortcuts, confusion between representation and reality, and a preference for coherence over falsification. When humans and models share these tendencies, their errors compound. We refer to this as relational drift, a failure that arises from interaction rather than from the model alone. Addressing this requires a shift from modeling relations between words to structuring relations between model outputs and human reasoning. RRI provides this missing layer through three components: the Rose-Frame, which identifies likely breakdowns in reasoning; the Architect's Pen, which introduces targeted reflection steps at critical moments; and an inference-time workflow that embeds these steps without retraining the model. Together, these elements transform human-AI interaction into a joint reasoning system with explicit checkpoints, conflict surfacing, and an auditable trail of assumptions. Rather than making machines think like humans or forcing humans to reason like machines, RRI creates a structured interaction in which both compensate for each other's limitations. It reframes AI safety as a cognitive architecture problem, where reliable decisions depend on embedding reflection directly into the interaction process.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2605.06177

BioMedArena: An Open-source Toolkit for Building and Evaluating Biomedical Deep Research Agents

作者:

Jinge Wu↗Hongjian Zhou↗Mingde Zeng↗Jiayuan Zhu↗Junde Wu↗Jiazhen Pan↗Ayush Noori↗Sean Wu↗Honghan Wu↗Fenglin Liu↗David A. Clifton↗

arXiv:2605.06177v2 Announce Type: replace Abstract: Reproducing and comparing deep research agents today is hard: the same backbone evaluated on the same benchmark can report different accuracies across papers because the harness and tool registry differ, and integrating a new model into a comparable evaluation surface costs weeks of model-specific engineering. These are symptoms of a broader reproducibility problem in deep research agent research. Here, we introduce BioMedArena, an open-source toolkit that addresses this reproducibility gap and provides an arena for comparing deep research agents under a shared evaluation environment. BioMedArena decouples six layers of biomedical agent evaluation – benchmark loading, tool exposure, tool selection, harness mode, context management, and scoring – and exposes 166 biomedical benchmarks and 75 biomedical tools across 9 functional families. Adding a new model, benchmark, or tool can be accomplished with a few-line provider adapter. Beyond evaluation infrastructure, BioMedArena ships a library of high-quality reference components: 6 agent harnesses (including our proposed Mutual-Evolve) and 6 context-management strategies, any of which can be equipped on any backbone. Equipping these components substantially improves all 12 backbones; on each of 8 representative biomedical benchmarks, the best equipped backbone surpasses prior state-of-the-art (SOTA), by 15.01 percentage points on average. The toolkit, configurations, and per-task traces are available at https://github.com/AI-in-Health/BioMedArena.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13188

Transformer-Guided Graph Attention for Direct Cardiac Mesh Reconstruction: A Structural Digital Twin Framework

作者:

Abhishek H S↗Akash Ganamukhi↗Abhimanyu Suresh↗Aditya G Hiremath↗Prasad B Honnavalli↗Adithya Balasubramanyam↗

Building patient-specific cardiac models sits at the heart of precision cardiology, yet getting those models into clinical use keeps running into the same wall: mesh generation is slow, messy, and frustrating. The standard workflow – segmenting the image, running Marching Cubes, and then manually cleaning up the result – is time-consuming, inconsistent across operators, and demands specialist knowledge most clinical teams do not have. We take a fundamentally different approach. Instead of treating segmentation and mesh generation as two separate problems, we train a single end-to-end network that goes directly from a raw 3D medical image to a smooth, simulation-ready cardiac surface mesh. The core is a 3D Swin Transformer encoder-decoder that extracts volumetric features from CT or MRI volumes, paired with a Graph Attention Network (GAT) head that iteratively deforms a template mesh to fit the patient's cardiac boundary. We tested on the MM-WHS 2017 benchmark using both CT and MRI. Segmentation scores were competitive (Dice of 0.84 on CT, 0.83 on MRI), but the primary focus is mesh quality: mean Chamfer distance of 1.8 mm, with 95th-percentile surface distance below 5 mm. Every mesh is produced in a single forward pass – no Marching Cubes, no smoothing filters, no manual cleanup. We argue that for cardiac digital twin pipelines, geometric fidelity and topological correctness matter more than pixel-level Dice scores. By removing the post-processing bottleneck, this approach makes patient-specific cardiac simulation substantially more accessible for clinical use.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19613

StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns

作者:

Vlad Sobal↗Shuo Yang↗Yuting Zhang↗Wei Xia↗Stefano Soatto↗

arXiv:2606.19613v1 Announce Type: cross Abstract: We introduce StaminaBench, a benchmark that measures the stamina of coding agents: how many consecutive interaction turns (change requests) they can handle before failing. Unlike the prevailing fraction-of-tasks-solved metric, this matches real vibe-coding where sessions run dozens or hundreds of turns. In StaminaBench, agents implement a REST API server and modify it across a tunable number of procedurally generated follow-up change requests - 100 in our experiments, resulting in codebases of up to 6,000 lines. Tests are generated fully programmatically without LLM involvement, ensuring reproducibility and reliability; change sequences are drawn from either a hardcoded or LLM-driven sampler, both constrained to a structured action space to ensure changes are valid. The agent and the server run in an isolated environment and communicate with the benchmark through HTTP, making testing fully black-box and language-agnostic. We evaluate six agent harnesses paired with seven open-source LLMs across 20 scenarios of 100 turns each and find that: (1) all the tested models fail within 5-6 turns, confirming that vibe-coding-style programming without thorough testing produces bugs; (2) passing test feedback back to the agent and allowing it to retry improves passed turn count by up to 12x; and (3) a good harness is required for strong performance: stronger models exhibit up to a 6x gap between their best and worst harness, while weaker models fail with any harness. We release the benchmark and the generated tasks to enable further research into multi-turn coding agent behavior. Benchmark code and data: github.com/amazon-science/StaminaBench.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19706

NEST: Narrative Event Structures in Time for Long Video Understanding

作者:

Ali Asgarov↗Kaushik Narasimhan↗Najibul Haque Sarker↗Hani Alomari↗Chia-Wei Tang↗Anushka Sivakumar↗Zaber Ibn Abdul Hakim↗Shaurya Mallampati↗Chris Thomas↗

Recent progress in vision-language models has enabled the processing of increasingly long video sequences, but the ability to handle extended token streams does not translate to understanding of narrative structure in long videos. Existing long video benchmarks focus on needle-in-a-haystack retrieval rather than evaluating how low-level actions form events, how events interact across time, and how narratives progress, for example, whether a model can connect an early setback, such as a job loss to a later relationship breakup, despite long gaps, intervening scenes, or flashbacks that reframe what occurred. We introduce NEST (Narrative Event Structures in Time for Long Video Understanding), a dataset of 1005 full-length movies (avg. 98 minutes), each annotated with 102 multimodal narrative events grounded in visual content, dialogue, and audio. NEST captures multimodal narrative events with structured annotations grounded in visual content, dialogue, and audio, and links them through relations that reflect narrative structure, including temporal ordering, hierarchical composition, and long-range dependencies. We introduce baselines for event trigger detection (ETD), event localization (EL), event argument extraction (EAE), and event relation extraction (ERE). The benchmark is highly challenging for grounded event discovery, with ETD below 8%, EL under 6%, and EAE below 11%. In contrast, ERE is more tractable once events are given, reaching 35.45% F1 zero-shot and 44.42% F1 after fine-tuning.

阅读与讨论 → 访问原文 →

21.

medRxiv (Medicine) 2026-06-15 DOI: HASH:112b02b467c7f2745a8fb2b77e3d2725

Shortened blastocyst vitrification achieves live birth rates comparable to standard protocols: an analysis of 3168 cryotransfers

作者:

Ebinger↗Misurac↗Lynch↗Desai↗De Rosa↗Vassena↗Atkinson↗

Study question Do shortened blastocyst vitrification and warming protocols provide comparable live birth rates (LBR) and obstetrical and perinatal outcomes to traditional vitrification and warming protocols? Summary answer Shortened vitrification and warming protocols provide comparable LBR, obstetric and perinatal outcomes to traditional protocols. Shortened vitrification coupled with traditional multi step warming benefitted women >35yrs. What is known already Embryo viability following cryopreservation is dependent on blastomere survival and functional integrity, both impacted by ice crystal formation and osmotic gradients. Recent innovations in cryopreservation challenge the need for stepwise dehydration and rehydration protocols. While one step ''fast'' blastocyst warming protocols seem to provide equivalent clinical outcomes to traditional ''slow'' protocols, fewer studies investigate whether blastocyst dehydration rates can be similarly increased. A thorough safety and effectiveness evaluation remains necessary for both treatment success and offspring health. Study design, size, duration Three clinics within a network participated in this retrospective consecutive cohort study, with cycle data collected for 3603 warmed blastocysts resulting in 3168 frozen blastocyst transfers in 2170 patients between 2023 and 2025. We modelled the relationship between ''fast'' versus ''slow'' protocols and outcomes with Generalized Additive Models, and linear and logistic regressions where appropriate. Two tailed chi square with Yates correction was used to examine pregnancy loss and obstetrical and perinatal outcomes; p0.05). Importantly, women 35yrs or older at vitrification (n=1715 transfers) profited from a F/S strategy, which provided a significant increase in live birth rates (OR:1.42 [1.02-1.98] p=0.038) compared to S/S. The same improved live birth following a F/S strategy were also seen in embryos of lower quality (OR:1.78 [1.12-2.83] p=0.015), suggesting of a protective effect of this cryopreservation strategy on the developmental competence of impaired germplasm. Limitations, reasons for caution Factors affecting the results may be unaccounted for by the study retrospective nature. Wider implication of the findings Overall, shortened, ''faster'' vitrification and warming protocols provide comparable reproductive outcomes to traditional ones. The combination of shorter exposure to cryoprotectant (CPA) during vitrification and stepwise osmotic gradient during warming provided significant clinical benefits specifically to patients >35 and lower quality embryos, pointing to the possibility of adapting vitrification protocols to specific patients populations and optimizing their clinical outcomes.

阅读与讨论 → 访问原文 →

22.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2605.26783

Inhomogeneous Light-Matter Coupling as a Resource for Noiseless Quantum Memories

作者:

Fumiya Hanamura↗Sicheng Bao↗Jie Lerk Yoo↗Alexia Auff\`eves↗Steven Touzard↗

arXiv:2605.26783v3 Announce Type: replace Abstract: Inhomogeneous ensembles of two-level systems are central to both fundamental light-matter physics and quantum-network applications. Understanding and optimizing ensemble-based quantum memories and entanglement protocols requires a unified framework that describes how to store quantum states of light as collective matter excitations and retrieve them on demand. Here we develop such a framework, the waveguide model, by mapping the dark collective modes of the ensemble onto an effective waveguide with well-defined input-output relations, valid in both the weak-excitation regime and near population inversion. This model reveals that inhomogeneous coupling – often regarded as a limitation – is instead the physical origin of noisy-echo suppression by adiabatic pulses, a key ingredient for realizing noiseless quantum memories. For entanglement generation, the same mechanism exposes a previously unexplored shortcoming of robust control pulses and leads to a new composite-pulse protocol that overcomes it. These results establish the waveguide model as a practical bridge between fundamental collective physics and quantum-network protocol design, recasting inhomogeneous coupling from an obstacle into a control knob for collective emission.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.18051

Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose

作者:

Xueping Gao↗

LLM agents increasingly rely on external skills – reusable tool specifications – but real-world tasks often require composing multiple skills, not just selecting one. We formalize this as the Compositional Skill Routing problem: given a complex user query and a large skill library, decompose the query into atomic sub-tasks, retrieve the appropriate skill for each sub-task, and compose an executable plan. We present SkillWeaver, a decompose-retrieve-compose framework combining an LLM task decomposer, a bi-encoder skill retriever with FAISS indexing, and a dependency-aware DAG planner. To support evaluation, we introduce CompSkillBench, a benchmark of 300 compositional queries over 2,209 real MCP server skills spanning 24 functional categories, sourced from the public MCP ecosystem. Our experiments reveal that task decomposition quality is the primary bottleneck: standard LLM decomposition reaches only 34.2% category recall at the step level. To address this, we propose Iterative Skill-Aware Decomposition (SAD), a retrieval-augmented feedback loop that iteratively aligns decomposition with available skills. SAD improves decomposition accuracy from 51.0% to 67.7% (+32.7%, Wilcoxon p < 10^-6) in a single iteration; DA-conditioned analysis confirms that correct granularity is the prerequisite for effective retrieval (CatR@1 rises from 34% to 41% when DA=1). SkillWeaver reduces context window consumption by over 99%, and transfer experiments confirm generalization (+35.6% relative DA gain even when target categories are absent from the retrieval pool).

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2407.07357

A polarity-aware multi-relational model for the signed interaction prediction in biological networks

作者:

Ziye Zhou↗Meijie Wang↗Lun Yu↗

arXiv:2407.07357v3 Announce Type: replace Abstract: Predicting signed interactions in biological networks is crucial for understanding drug mechanisms and facilitating drug repurposing. While deep graph models have demonstrated success in modeling complex biological systems, existing approaches often fail to distinguish between positive and negative interactions, limiting their utility for precise pharmacological predictions. In this study, we propose a novel deep graph model, PAMR (polarity-aware multi-relational model), designed to predict both polar (e.g., activation, inhibition) and non-polar (e.g., binding, affect) chemical-gene interactions. Our model integrates graph convolutional networks with tensor decomposition to enhance feature representation and incorporates a conflict-aware sampling strategy to resolve polarity ambiguities. We introduce new evaluation metrics, polarity discrimination score (PDS) and CP@100, to assess the model's ability to differentiate interaction types. Experimental results demonstrate that PAMR outperforms baseline models, achieving superior classification accuracy and improved discrimination of polar edges. Specifically, PAMR-CL attains a Macro AUROC of 0.9072 and CP@100 of 0.974, surpassing RGCN, GraphSAGE, TransE, and BioNet baselines. A case study on nicotine further identifies two novel chemical-gene suppression links, S100A6 and SPP1, that are corroborated by independent experimental literature. Furthermore, we analyze the impact of subgraph components on predictive performance, revealing that additional network structures do not always enhance accuracy. These findings highlight the importance of polarity-aware modeling in drug discovery and network pharmacology, providing a scalable computational framework for polarity-aware chemical-gene interaction prediction and network pharmacology analysis.

阅读与讨论 → 访问原文 →

25.

medRxiv (Medicine) 2026-06-17 DOI: HASH:afb8cb4e6f4266ec7e57f073f22d73fc

Targeted Proteomic Profiling of Nasal Fluid from the Brain-Nose Interface

作者:

Bashiri↗Babu↗Weiss↗Kotschote↗Metzler↗Wunderlich↗Petrera↗De Domenico↗Theis↗Lehmann↗Heinrich↗Mashreghi↗…

The brain-nose interface is an anatomical junction where olfactory neurons from the olfactory bulb traverse the cribriform plate into the nasal mucosa, providing minimally invasive access to the central nervous system (CNS). We hypothesized that nasal fluid from this region could enable detection of neurology-relevant proteins using targeted multiplex assays. Using nosecollect, a targeted nasal sampling device, nasal fluid proximal to brain-nose interface was collected from cognitively impaired patients, alongside matched cerebrospinal fluid (CSF) and plasma. After nasal sample-specific dilution optimization and intra-assay precision evaluation, all matrices were profiled with the Olink Target 96 Neurology and NUcleic acid Linked Immuno-Sandwich Assay CNS disease 120 (NULISAseq CNS Disease 120) panels. Nasal fluid showed technically repeatable detection (intra-assay coefficient of variation

阅读与讨论 → 访问原文 →