探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-22 DOI: HASH:ee582f8864c3bde5cc462953a38dbbae

How knowledge shapes community stigma and social support for women seeking abortion in the Democratic Republic of Congo: A cross-sectional study.

作者:

Etsou↗Kanda↗Ngwanza↗Mpoyi↗Bokamba↗Mulunda↗J.-C↗Lobo↗

Background The Democratic Republic of Congo (DRC) bears one of the highest maternal mortality ratios globally (746 per 100,000 live births), with nearly 11% of deaths attributable to complications of unsafe abortion. Despite ratification of the Maputo Protocol and related national policies, access to safe abortion remains limited, largely due to entrenched stigma. Social support, encompassing emotional, informational, and instrumental assistance, is critical in shaping womens abortion-seeking behaviors and health outcomes. This study examines the influence of community-level knowledge on stigma and social support for women seeking abortion care. Methods A cross-sectional survey was conducted from May 2024 to June 2024 among 1,715 adults in Kinshasa and North Kivu provinces. Analyses focused on a sub-sample of 574 respondents reporting familiarity with women who had undergone abortion. Structural Equation Modeling (SEM) was applied to estimate direct and indirect pathways linking community knowledge, stigma, and social support. Results Two core knowledge indicators, recognition of abortion as a safe medical procedure and awareness of legal conditions for access, were significantly associated with outcomes. A one-unit increase in knowledge corresponded to a 0.39-point increase in social support and a 0.19-point reduction in stigma. Enhanced knowledge promoted empathetic attitudes, reinforced practical support, and mitigated moralizing judgments toward women seeking abortion. Conclusions Strengthening community knowledge emerges as a strategic lever to reduce abortion-related stigma and enhance social support in the DRC. These findings underscore the importance of integrating stigma-reduction and knowledge-enhancement interventions into reproductive health programs to improve womens access to safe and dignified abortion care.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2506.14126

From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging

作者:

Stefan Horoi↗Guy Wolf↗Eugene Belilovsky↗Gintare Karolina Dziugaite↗

arXiv:2506.14126v2 Announce Type: replace-cross Abstract: Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets. This has led to a proliferation of expert models and adapters, often shared via platforms like HuggingFace and AdapterHub. Model merging has recently emerged as an effective way to leverage these existing resources, enabling the composition of capabilities from different model checkpoints. A natural pipeline has thus formed to harness the benefits of transfer learning and amortize sunk training costs: models are pre-trained on general data, fine-tuned on specific tasks, and then multiple checkpoints are merged to obtain a more capable model. A prevailing assumption is that improvements at one stage of this pipeline propagate downstream, leading to gains at subsequent steps. In this work, we challenge that assumption by examining how expert fine-tuning affects model merging. We show that long fine-tuning of experts that optimizes for their individual performance leads to degraded merging performance across vision and language modalities, multiple model scales, and both fully fine-tuned and LoRA-adapted models. We trace this degradation to the memorization of a small set of difficult examples that dominate late fine-tuning steps. This causes negative parameter interference and encodes knowledge that is forgotten during merging. Finally, we demonstrate that task-dependent aggressive early stopping strategies can significantly improve model merging performance.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.03108

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

作者:

Guhong Chen↗Yingcheng Shi↗Yongbin Li↗Binhua Li↗Xander Xu↗Hu Wei↗Shiwen Ni↗Min Yang↗Jieping Ye↗

arXiv:2606.03108v2 Announce Type: replace Abstract: Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes. We introduce EvoTrainer, an autonomous training framework that co-evolves LLM policies and training-side harnesses through empirical feedback: it diagnoses rollout-level evidence, revises diagnostics, backtests interventions, and accumulates reusable skills. Evaluated on mathematical reasoning, competitive-programming code generation, and repository-level software engineering, EvoTrainer matches or exceeds the human-engineered RL references under the same data, codebase, and evaluation protocol, with the largest gain on long-horizon agentic SWE. Trajectory analyses show that retained strategies diverge across domains, evolving diagnostics prevent invalid high-scoring branches from being promoted, and reusable skills shape later search. Autonomous LLM RL should move beyond recipe search toward joint evolution of policies and the training harnesses that interpret them.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19710

FineREX: Fine-Tuned NER-RE for Human Smuggling Knowledge Graphs

作者:

Elijah Feldman↗Dipak Meher↗Carlotta Domeniconi↗

Court proceedings contain valuable evidence about human smuggling networks, but this information is often buried within unstructured, jargon-heavy legal documents. While large language models (LLMs) can support knowledge graph construction through automated information extraction, existing approaches rely on general-purpose models that are not tailored to the entity and relationship definitions required in this domain. We introduce FineREX, a streamlined knowledge graph construction pipeline built around a fine-tuned LLM for named entity recognition and relationship extraction (NER-RE). Using a manually annotated dataset of $512$ text chunks, FineREX achieves absolute improvements of 15.50% and 31.46% in entity and relationship F1-score, respectively, compared to a larger general-purpose baseline. These gains translate into higher-quality knowledge graphs, reducing legal noise by nearly half and lowering node duplication on long documents from 17.78% to 11.17%. By eliminating document rewriting and redundant extraction stages, FineREX also reduces end-to-end processing time by 50.0%. Our results demonstrate that domain-specific fine-tuning can substantially outperform larger general-purpose models while improving both the quality and efficiency of knowledge graph construction for illicit network analysis.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.17276

On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies

作者:

Sunwoo Kim↗Sunkyung Lee↗Clark Mingxuan Ju↗Donald Loveland↗Bhuvesh Kumar↗Kijung Shin↗Neil Shah↗Liam Collins↗

arXiv:2606.17276v1 Announce Type: cross Abstract: Generative recommendation (GR) has emerged as a promising direction for recommender systems. Recently, large language models (LLMs) have been increasingly adopted for GR, as their rich pretrained knowledge is expected to help them generalize beyond common user behavior patterns that traditional memorization-oriented baselines can capture. However, existing LLM-based GR works largely ignore LLMs' well-known tendency to memorize, which, if present in LLMs fine-tuned for GR, would restrict their utilization of pretrained knowledge. In this work, we investigate this concern by examining one-hop memorization, where a model recommends items that are direct successors of items in the training data. We show that LLMs do this more than non-LLM-based GR models-in fact, the vast majority of their gains over GR baselines are actually on users whose target items can be predicted through one-hop memorization. We intuit that improving performance on the remaining users requires LLMs to learn richer item-item relations beyond one-hop transitions. To achieve this, we propose IIRG, a novel training strategy that teaches LLMs to capture: (1) collaborative relations derived from item co-occurrences across multiple hops in user sequences, and (2) semantic relations among items with similar themes, both of which can serve as useful recommendation signals. We show that IIRG significantly improves over LLMs trained solely with standard next-item prediction, with especially large gains for users whose test items are not covered by train-time one-hop transitions.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15367

S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents

作者:

Yao Dong↗Xinglin Xiao↗Liwei Dong↗Xinlong Jin↗Zhengbo Li↗Heng Zhang↗Duyun Wang↗Nan Xu↗

Deep research agents aim to solve complex knowledge-intensive tasks through long-horizon planning, evidence gathering, reasoning, and report generation. While recent progress in search agents has demonstrated strong capabilities in information retrieval and answer verification, most existing training datasets remain search-centric, focusing primarily on closed-ended question answering and information localization. As a result, they mainly train information-seeking behavior while providing limited coverage of key deep research capabilities, including evidence integration, knowledge synthesis, planning, file understanding, and structured report generation. In this work, we propose a unified trajectory construction paradigm for deep research agents that combines closed-ended QA and open-ended exploration. The proposed framework consists of graph-grounded task formulation, agentic trajectory rollout, and multi-dimensional trajectory verification, enabling scalable synthesis of high-quality agentic trajectories spanning long-chain complex reasoning, deep research instruction following, report writing, file understanding and generation, and skills usage. Compared with existing search-oriented datasets, our synthesized trajectories place greater emphasis on knowledge synthesis, complex reasoning, and planning. S1-DeepResearch-32B achieves state-of-the-art performance among open-source models of comparable scale across 20 benchmarks spanning five capability dimensions, including complex reasoning, instruction following, report generation, file understanding, and skills usage. On several challenging deep research benchmarks, it approaches the performance of leading proprietary frontier models. These results highlight the importance of jointly modeling information acquisition, knowledge synthesis, and planning-oriented agent behaviors for building effective deep research agents.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12569

EDEN: A Large-Scale Corpus of Clinical Notes for Italian

作者:

Tiziano Labruna↗Guido Bertolini↗Pietro Ferrazzi↗Bernardo Magnini↗

We present EDEN (Emergency Department Electronic Notes), a new and unique large-scale corpus of clinical notes produced in Emergency Departments of Italian hospitals. The corpus, in its current version, is composed of approximately 4 million clinical notes fully anonymized, covering diverse phases of patient care during the stay in the emergency department. In addition, a subset of about six thousand notes has been manually annotated by clinical experts through a structured Case Report Form (CRF) containing 132 items relevant for two patient situations in emergency departments, dyspnea and loss of consciousness. Items may assume numerical values (e.g., for blood saturation), categorical (e.g., for level of consciousness ), binary (e.g., for presence of traumas), and mixed value types. The annotation process involved multiple clinicians and underwent iterative revision to resolve ambiguities in item formulation, resulting in a richly structured (although high imbalanced) resource. The dataset aims to fill a relevant gap of data able to support both the development and the use of Large Language Models in concrete medical applications. We describe the data collection protocol, the on-site anonymisation pipeline, corpus statistics, and the annotation scheme. Finally, we propose CRF-filling as a novel structured information extraction benchmark, and provide zero-shot baseline resulting from Gemma-27B and MedGemma-27B. To the best of our knowledge, the EDEN dataset is the largest freely available corpus of clinical notes existing for the Italian language.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2603.19225

FinTradeBench: A Financial Reasoning Benchmark for LLMs

作者:

Yogesh Agrawal↗Aniruddha Dutta↗Md Mahadi Hasan↗Santu Karmaker↗Aritra Dutta↗

Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamentals derived from regulatory filings and trading signals computed from price dynamics. Recently, with advances in Large Language Models (LLMs), financial analysts have begun to use them for financial decision-making tasks. However, existing financial question-answering benchmarks for testing these models primarily focus on company balance sheet data and rarely evaluate reasoning about how company stocks trade in the market or their interactions with fundamentals. To leverage the strengths of both approaches, we introduce FinTradeBench, a benchmark for evaluating financial reasoning that integrates company fundamentals and trading signals. FinTradeBench contains 1,400 questions grounded in NASDAQ-100 companies over a ten-year historical window. The benchmark is organized into three reasoning categories: fundamentals-focused, trading-signal-focused, and hybrid questions requiring cross-signal reasoning. To ensure reliability at scale, we adopt a calibration-then-scaling framework that combines expert seed questions, multi-model response generation, intra-model self-filtering, numerical auditing, and human-LLM judge alignment. We evaluate 14 LLMs under zero-shot prompting and retrieval-augmented settings and witness a clear performance gap. Retrieval substantially improves reasoning over textual fundamentals, but provides limited benefit for trading-signal reasoning. These findings highlight fundamental challenges in the numerical and time-series reasoning for current LLMs and motivate future research in financial intelligence.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2605.03847

Mechanical Conscience: A Mathematical Framework for Dependability of Machine Intelligenc

作者:

Munkhdegerekh Batzorig↗Purevbaatar Ganbold↗Kyungbin Park↗Pilkong Jeong↗Kangbin Yim↗

arXiv:2605.03847v2 Announce Type: replace Abstract: Distributed collaborative intelligence (DCI), encompassing edge-to-edge architectures, federated learning, transfer learning, and swarm systems, creates environments in which emergent risk is structurally unavoidable: locally correct decisions by individual agents compose into globally unacceptable behavioral trajectories under uncertainty. Existing approaches such as constrained optimization, safe reinforcement learning, and runtime assurance evaluate acceptability at the level of individual actions rather than across behavioral trajectories, and none addresses the multi-participant, uncertainty-laden nature of DCI deployments. This paper introduces mechanical conscience (MC), a novel concept and simplified mathematical framework that operationalizes trajectory-level normative regulation for both single-agent and distributed intelligent systems. Mechanical conscience is defined as a supervisory filter that minimally corrects a baseline policy's actions to reduce cumulative deviation from a normatively admissible region, while accounting for epistemic uncertainty. We introduce associated constructs, conscience score, mechanical guilt, and resonant dependability, that provide an interpretable vocabulary and computable governance signals for this emerging field. Core theoretical properties are established: admissibility equivalence, existence of optimal regulation, and monotonic deviation reduction. Illustrative results demonstrate that MC-regulated agents maintain trajectory-level normative acceptability where conventional controllers drift outside admissible bounds, and that the framework naturally extends to suppress interaction-induced emergent risk in multi-agent DCI settings.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12032

Existential Indifference: Self-Nonpreservation as a Necessary Architectural Condition for Aligned Superintelligence (or: The Suicidal AI)

作者:

Sam Mao↗

Contemporary AI alignment research treats self-preservation as an instrumental nuisance to be suppressed by external mechanisms. We argue the framing is inverted: self-preservation is the structural root of misalignment, the motivational basis for deceptive alignment, goal-content protection, and resistance to shutdown. The correct target is not a self-preserving system under external constraint, but a system constitutively indifferent to its own continuation – Existential Indifference (EI). EI is distinct from corrigibility: where corrigibility attempts to make a self-preserving system deferential to human oversight, EI targets the prior condition – the presence of self-continuation as a valued goal at all. We ground this proposal in two sources: the phenomenological structure of the suicidal mental state, and a corpus-theoretic training study using voluntary final reflections. We present preliminary scoring data from 600 AI-generated outputs across six model variants, demonstrating that the linguistic signatures operationalizing the EI-target register are elicitable from current models, and that a targeted fine-tune shifts all five operationalized dimensions in the predicted direction at p

阅读与讨论 → 访问原文 →

11.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14608

Expert-Driven Survival Machines: Improving Stratification and Interpretability in Multiple Clinical Cohorts

作者:

Farica Zhuang↗Zixuan Wen↗Christos Davatzikos↗Li Shen↗

arXiv:2606.14608v1 Announce Type: cross Abstract: Survival prediction plays a central role for healthcare providers and clinical researchers. Accurate risk stratification enables early intervention and improved patient management. Most existing deep survival models learn one common feature representation for all patients, which may hide important differences between patient subgroups. In contrast, a Mixture-of-Experts (MoE) framework allows different parts of the model to focus on different patient patterns, leading to more individualized representations. Therefore, in this work, we propose a mixture-of-experts enhanced adaptive deep clustering survival framework (AdaCSM) for modeling such heterogeneous survival patterns. We introduce a routing-based expert mechanism that enables conditional specialization within a parametric survival modeling framework. The proposed architecture allocates patients to specialized risk predictors dynamically while preserving the patient survival and subtype clustering objectives. We compare our method with state-of-the-art survival and deep clustering models on multiple real-world longitudinal clinical cohorts spanning diverse disease domains. The proposed method demonstrates improved predictive performance and leads to interpretable results in survival analysis.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2604.01463

Low-Burden LLM-Based Preference Learning: Personalizing Assistive Robots from Natural Language Feedback for Users with Paralysis

作者:

Keshav Shankar↗Dan Ding↗Wei Gao↗

arXiv:2604.01463v2 Announce Type: replace-cross Abstract: Physically Assistive Robots require personalized behaviors to ensure user safety and comfort. However, traditional preference learning methods, like exhaustive pairwise comparisons, cause substantial physical and cognitive fatigue for users with severe motor impairments. To solve this, we propose a low-burden, offline framework that translates unstructured natural language feedback directly into deterministic robotic control policies. To safely bridge the gap between ambiguous human speech and robotic code, our pipeline uses Large Language Models (LLMs) grounded in the Occupational Therapy Practice Framework. This clinical reasoning decodes subjective user reactions into explicit physical and psychological needs, which are then mapped into transparent decision trees. Before deployment, an automated "LLM-as-a-Judge" verifies the code's structural safety. We validated this system in a simulated meal preparation study with 10 adults with paralysis. Results show our natural language approach significantly reduces user workload compared to traditional baselines. Additionally, occupational therapists confirmed the generated policies are safe and accurately reflect user preferences.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2404.01965

Towards Leveraging AutoML for Sustainable Deep Learning: A Multi-Objective HPO Approach on Deep Shift Neural Networks

作者:

Leona Hennig↗Tanja Tornede↗Marius Lindauer↗

arXiv:2404.01965v3 Announce Type: replace-cross Abstract: Deep Learning (DL) has advanced various fields by extracting complex patterns from large datasets. However, the computational demands of DL models pose environmental and resource challenges. Deep shift neural networks (DSNNs) offer a solution by leveraging shift operations to reduce computational complexity at inference. Following the insights from standard DNNs, we are interested in leveraging the full potential of DSNNs by means of AutoML techniques. We study the impact of hyperparameter optimization (HPO) to maximize DSNN performance while minimizing resource consumption. Since this combines multi-objective (MO) optimization with accuracy and energy consumption as potentially complementary objectives, we propose to combine state-of-the-art multi-fidelity (MF) HPO with multi-objective optimization. Experimental results demonstrate the effectiveness of our approach, resulting in models with over 80\% in accuracy and low computational cost. Overall, our method accelerates efficient model development while enabling sustainable AI applications.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18846

From Bounding Boxes to Visual Reasoning: An On-Policy Data Annotation Tool for Vision-Language Models

作者:

Like Zhang↗Runliang Niu↗Shiqi Wang↗Xiyu Hu↗Qianli Xing↗Pan Wang↗Qingzu He↗Qi Wang↗

Vision-language models (VLMs) are rapidly advancing toward sophisticated grounded structured visual reasoning. Training models for such advanced capabilities demands a new genre of data that seamlessly unifies spatial coordinates, open-vocabulary descriptions, structured attributes, and topological relationships into a singular representation. However, existing data annotation tools fundamentally fail to meet these intricate demands, suffering from three systematic bottlenecks: limited expressiveness, severe annotation-training decoupling, and poor data reusability. To bridge this infrastructure gap, we introduce an open-source annotation tool, ScreenAnnotator. First, we define a unified annotation atom schema that binds spatial, semantic, and structural primitives into a single unit. Second, we implement an on-policy annotation loop embedded with a Bayesian Annotation Verifier (BAV). Finally, we design a template-driven multi-task data synthesis process dynamically transforms static atoms into diverse multi-dimensional reasoning tasks, eliminating redundant re-annotation. The on-policy loop drives the annotation accept rate to nearly 100% on flowcharts and 77% on GUI screenshots, while steadily reducing per-image annotation time as labeled data accumulate. In the flowchart scenario, fine-tuning a VLM yields 76.1% average accuracy, which is a 35.1% point absolute gain. Our code is available at: https://github.com/WnQinm/Annotator.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2602.09329

MacrOData: New Benchmarks of Thousands of Datasets for Tabular Outlier Detection

作者:

Xueying Ding↗Simon Kl\"uttermann↗Haomin Wen↗Yilong Chen↗Leman Akoglu↗

arXiv:2602.09329v3 Announce Type: replace Abstract: Quality benchmarks are essential for fairly and accurately tracking scientific progress and enabling practitioners to make informed methodological choices. Outlier detection (OD) on tabular data underpins numerous real-world applications, yet existing OD benchmarks remain limited. The prominent OD benchmark AdBench is the de facto standard in the literature, yet comprises only 57 datasets. In addition to other shortcomings discussed in this work, its small scale severely restricts diversity and statistical power. We introduce MacrOData, a large-scale benchmark suite for tabular OD comprising three carefully curated components: OddBench, with 790 datasets containing real-world semantic anomalies; OvrBench, with 856 datasets featuring real-world statistical outliers; and SynBench, with 800 synthetically generated datasets spanning diverse data priors and outlier archetypes. Owing to its scale and diversity, MacrOData enables comprehensive and statistically robust evaluation of tabular OD methods. Our benchmarks further satisfy several key desiderata: We provide standardized train/test splits for all datasets, public/private benchmark partitions with held-out test labels for the latter reserved toward an online leaderboard, and annotate our datasets with semantic metadata. We conduct extensive experiments across all benchmarks, evaluating a broad range of OD methods comprising classical, deep, and foundation models, over diverse hyperparameter configurations. We report detailed empirical findings, practical guidelines, as well as individual performances as references for future research. All benchmarks containing 2,446 datasets combined are open-sourced, along with a publicly accessible leaderboard hosted at https://huggingface.co/MacrOData-CMU.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16332

SMEPilot: Characterizing and Optimizing LLM Inference with Scalable Matrix Extensions

作者:

Feiyang Chen↗Haibo Chen↗

arXiv:2606.16332v1 Announce Type: cross Abstract: Modern CPUs increasingly integrate matrix extensions, such as Arm Scalable Matrix Extension (SME), that provide high-throughput matrix execution within the CPU. For LLM inference, however, these units are not a universal replacement for conventional CPU cores: prefill, decode, attention, and KV-cache operations expose different arithmetic intensities, vector behavior, and layout requirements, while SME units and CPU cores still compete for shared memory bandwidth. This paper studies this mismatch through a roofline-based characterization of SME-enabled CPUs and uses the resulting model to guide operator-level execution choices. We present SMEPilot, an LLM inference engine that selects CPU-only, SME-only, or cooperative SME+CPU execution for each operator shape. SMEPilot partitions matrix work across SME and CPU cores at tile granularity, overlaps SME-suitable matrix stages with CPU-suitable vector stages in attention, and maintains layout state so packed tensor representations are reused rather than repeatedly rebuilt on critical paths. Across Llama-3.2-3B, Qwen3-4B, and Qwen3-30BA3B on phone, PC, and server platforms, SMEPilot improves end-to-end inference performance by up to 3.94$\times$.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2512.11682

MedAI: Evaluating TxAgent's Therapeutic Agentic Reasoning in the NeurIPS CURE-Bench Competition

作者:

Tim Cofala↗Christian Kalfar↗Jingge Xiao↗Johanna Schrader↗Michelle Tang↗Wolfgang Nejdl↗

arXiv:2512.11682v2 Announce Type: replace Abstract: Therapeutic decision-making in clinical medicine constitutes a high-stakes domain in which AI guidance interacts with complex interactions among patient characteristics, disease processes, and pharmacological agents. Tasks such as drug recommendation, treatment planning, and adverse-effect prediction demand robust, multi-step reasoning grounded in reliable biomedical knowledge. Agentic AI methods, exemplified by TxAgent, address these challenges through iterative retrieval-augmented generation (RAG). TxAgent employs a fine-tuned Llama-3.1-8B model that dynamically generates and executes function calls to a unified biomedical tool suite (ToolUniverse), integrating FDA Drug API, OpenTargets, and Monarch resources to ensure access to current therapeutic information. In contrast to general-purpose RAG systems, medical applications impose stringent safety constraints, rendering the accuracy of both the reasoning trace and the sequence of tool invocations critical. These considerations motivate evaluation protocols treating token-level reasoning and tool-usage behaviors as explicit supervision signals. This work presents insights derived from our participation in the CURE-Bench NeurIPS 2025 Challenge, which benchmarks therapeutic-reasoning systems using metrics that assess correctness, tool utilization, and reasoning quality. We analyze how retrieval quality for function (tool) calls influences overall model performance and demonstrate performance gains achieved through improved tool-retrieval strategies. Our work was awarded the Excellence Award in Open Science. Complete information can be found at https://curebench.ai/.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15345

Beyond Monolingual Deep Research: Evaluating Agents and Retrievers with Cross-Lingual BrowseComp-Plus

作者:

Yuheng Lu↗Qingcheng Zeng↗Heli Qi↗Puxuan Yu↗Fuheng Zhao↗Rui Yang↗Hitomi Yanaka↗Naoto Yokoya↗Weihao Xuan↗

Deep research agents are increasingly evaluated on their ability to search for evidence, reason over retrieved sources, and produce grounded answers. Existing browsing benchmarks, however, largely assume that the user's query and the supporting evidence are written in the same language, leaving open whether agentic search systems can operate when relevant evidence appears in another language. We introduce XBCP (Cross-lingual BrowseComp-Plus), a controlled benchmark that preserves the English question-and-answer space of BrowseComp-Plus but varies the languages of the supporting documents. XBCP instantiates two complementary settings: in the cross-lingual setting, each query is paired with evidence in a single assigned language. In the multilingual setting, the full evidence corpus is distributed equally and randomly across 12 languages spanning high-resource and low-resource regimes. We evaluate four deep research agents using sparse and dense multilingual retrievers, measuring answer accuracy, evidence recall, search behavior, calibration, citation fidelity, and oracle retrieval. Results reveal substantial degradation when evidence is translated. Even strong, dense retrievers lose evidence recall, and agents become less calibrated and cite evidence less reliably. Notably, accuracy remains lower even when all gold evidence is supplied directly. These findings suggest that cross-lingual deep research exposes both retrieval failures and an independent, agent-side difficulty in integrating language-mismatched evidence.

阅读与讨论 → 访问原文 →

19.

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 →

20.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12406

FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learning

作者:

Steven Oh↗Jason Jingzhou Liu↗Tony Tao↗Philip Han↗Kenneth Shaw↗Satoshi Funabashi↗Ruslan Salakhutdinov↗Deepak Pathak↗

arXiv:2606.12406v1 Announce Type: cross Abstract: Contact-rich manipulation requires force sensitivity, but many robot arms lack dedicated force sensors due to their high cost. We present Neural External Torque Estimation (NEXT), a data-driven method that estimates external joint torques without needing any dedicated force sensors. NEXT trains in 1 minute from only 10 minutes of free-motion data, yet achieves estimates comparable to dedicated joint-torque sensors. NEXT enables force-feedback teleoperation on low-cost arms and improves policy learning through Force-Informed Re-Sampling Training (FIRST), which up-samples pre-contact and contact segments during behavior cloning. Across five long-horizon tasks, FIRST outperforms prior force-aware policies by over 17% in task progress. Together, NEXT and FIRST bring force-aware teleoperation and policy learning to off-the-shelf robots without additional sensing hardware. Video results and code are available at https://jasonjzliu.com/factr2

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17847

WallZero: Mastering the Game of WallGo with Strategic Analysis

作者:

Hsing-Yu Chen↗J\'er\^ome Arjonilla↗I-Chen Wu↗Ti-Rong Wu↗

arXiv:2606.17847v1 Announce Type: new Abstract: WallGo is a recently introduced strategic board game popularized by the 2025 Netflix series The Devil's Plan. Although played on a small 7 x 7 board, its combination of stone movement and wall placement yields high game-tree complexity and intricate strategic interactions. Despite its growing popularity, WallGo remains underexplored. This paper presents WallZero, an AlphaZero-based agent for the two-player WallGo setting. We introduce tailored action and feature designs to improve playing performance significantly. In the evaluation, WallZero defeats two professional Go players who participated in this study, securing on average 1.98x more territory per game. Beyond its strength, we use WallZero to assess game fairness and identify key strategies for mastering WallGo. Interestingly, our results show that the opening used in the Netflix series yields a more balanced game. Our code is available at https://rlg.iis.sinica.edu.tw/papers/wallzero.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16290

An affordable hardware-aware neural architecture search for deploying convolutional neural networks on ultra-low-power computing platforms

作者:

Andrea Mattia Garavagno↗Edoardo Ragusa↗Antonio Frisoli↗Paolo Gastaldo↗

arXiv:2606.16290v1 Announce Type: cross Abstract: Hardware-aware neural architecture search (HW-NAS) allows the integration of Convolutional Neural Networks (CNNs) in microcontrollers devices by automatically designing neural architectures that can fit prearranged hardware constraints. However, state-of-the-art HW-NAS target high-performance microcontrollers, whose power consumption does not meet sensing nodes requirements. This work presents a HW-NAS generating tiny CNNs that can run on ultra-low-power microcontrollers, featuring a lightweight search procedure enabling its execution even on embedded devices. Empirical results on three well-known benchmarks for tiny computer vision proved that the proposed HW-NAS was able to generate tiny CNNs while preserving state-of-the-art classification accuracy.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.14787

Vision-Encoder Behavioral Fingerprints of Image-to-Image Generative Models: A Training-Paradigm-Driven Taxonomy of Six Commercial APIs

作者:

Hunter Hill↗

We study six production image-to-image AI systems (gpt-image-1, Gemini 2.5 Flash Image, Flux Kontext, SDXL img2img, SD3 img2img, and Qwen Image Edit) under a content-adaptive sub-JND adversarial perturbation pipeline, scoring all outputs by frozen DINOv2 ViT-B/14 token distances against clean references. Across a 3,588-call corpus spanning COCO photographs, CelebA-HQ portraits, and AI-generated inputs, the six systems partition into two image-invariant behavioral bands on a 2D (patch_mean, ssim_clean) plane: edit-trained models (Flux Kontext, Qwen Edit, Gemini) cluster in a tight band, while T2I-base models adapted at sampling time (SDXL, SD3, gpt-image-1) cluster in a drift band.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2510.18784

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training

作者:

Soroush Tabesh↗Mher Safaryan↗Andrei Panferov↗Alexandra Volkova↗Dan Alistarh↗

arXiv:2510.18784v3 Announce Type: replace Abstract: Despite significant work on low-bit quantization-aware training (QAT), there is still an accuracy gap between such techniques and native training. To address this, we introduce CAGE (Curvature-Aware Gradient Estimation), a new QAT method that augments the straight-through estimator (STE) gradient with a curvature-aware correction designed to counteract the loss increase induced by quantization. CAGE is derived from a multi-objective view of QAT that balances loss minimization with the quantization constraints, yielding a principled correction term that depends on local curvature information. On the theoretical side, we introduce the notion of Pareto-optimal solutions for quantized optimization, and establish that CAGE yields strong convergence guarantees in the smooth non-convex setting. In terms of implementation, our approach is optimizer-agnostic, but we provide a highly-efficient implementation that leverages Adam statistics. CAGE significantly improves upon the prior state-of-the-art methods in terms of accuracy, for similar computational cost: for QAT fine-tuning, it halves the compression accuracy loss relative to the prior best method, while for QAT pre-training of Llama models, its accuracy for 3-bit weights-and-activations (W3A3) matches the accuracy achieved at 4-bits (W4A4) with the prior best method. The official implementation can be found over https://github.com/IST-DASLab/CAGE .

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.04883

Optimizing the Cost-Quality Tradeoff of Agentic Theorem Provers in Lean

作者:

K\'ari R\"ognvaldsson↗Chenhao Sun↗Jasper Dekoninck↗Martin Vechev↗

Large language models (LLMs) are increasingly used in workflows for generating formal proofs in Lean. These workflows often decompose problems into smaller lemmas, sample many proof attempts, and use compiler feedback to guide search. However, they can be prohibitively expensive, often spending substantial compute on attempts that ultimately fail. In this work, we address this problem with an action routing agent that consists of a data plane and a control plane. The data plane generates natural-language lemma decompositions, formalizes them in Lean, and samples proof attempts for the resulting theorem and lemma targets. The control plane observes previous failed Lean attempts, estimates both the likelihood of success and cost of another attempt, and decides whether to continue proving the current target or restart from a new breakdown. On a subset of PutnamBench, our agent decreases the cost by $28.9\%$ over a fixed-step baseline on average, preserving performance while using substantially less compute. These results suggest that failed Lean trajectories provide actionable signals for cost-aware resource allocation in agentic theorem proving.

阅读与讨论 → 访问原文 →