探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-11 DOI: HASH:2216df3fdc9843cc928a68ae06d0a664

Hantavirus Disease in Uruguay: Trends and Mortality Before and During the COVID-19 Pandemic.

作者:

criscuolo↗Blanco↗Ferrara↗Ciaccio↗Gomez Carassale↗Gonzalez Reyes↗Machado Rivero↗Sosa Dias↗Facal Castro↗J. A↗

Introduction: Hantavirus disease is an emerging and potentially severe zoonosis of global distribution. In Uruguay, it is transmitted by rodents inhabiting peridomestic, suburban, and rural areas. Global incidence is estimated at 150,000 to 200,000 cases per year, with up to 300 annual cases in the Americas. Since 1997, Uruguay's Ministry of Public Health (MPH) has monitored Hantavirus cardiopulmonary syndrome (HCPS), the most common clinical presentation in the region. By 2019, a total of 271 cases had been identified in the country, with an estimated mortality rate of nearly 50%. Objectives: To describe the clinical, epidemiological, and occupational characteristics of patients with Hantavirus disease in Uruguay during the pre-pandemic (2018-2019) and pandemic (2020-2021) periods. Methods: A descriptive, cross-sectional, observational study was conducted, including all serologically confirmed cases of Hantavirus infection reported to the MPH between 2018 and 2021. Clinical and demographic data were extracted from the mandatory reporting form for zoonotic diseases. Incidence and case fatality rates were calculated, and factors associated with fatal outcomes were analyzed. Results: A total of 58 confirmed cases were identified between 2018 and 2021. Most patients were male (62%), with a mean age of 36.5 years (SD 16). A decline in incidence was observed during 2020-2021, with no significant change in case fatality. Direct rodent exposure was the most frequently associated risk factor. Montevideo and Canelones were the most affected departments. Renal and pulmonary involvement were significantly associated with mortality. Conclusion: Hantavirus remains a relevant public health concern in Uruguay. Although a decrease in incidence was observed during the COVID-19 pandemic years, case fatality rates remained high. The findings underscore the need for sustained surveillance and early recognition, particularly in urbanizing regions.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.14934

Separable Neural Architectures as Physical World Models: from Mathematical Theory to Applications

作者:

Reza T Batley↗Andrew Kichline↗Sourav Saha↗

arXiv:2606.14934v1 Announce Type: cross Abstract: This work introduces the Separable Neural Architecture (SNA), a function representational class combining neural approximation with tensor decomposition. The SNA decouples localized coordinate functions (atoms) from global interactions governed by a sparse, low-rank interaction object. This architecture possesses a compact and smooth inductive bias well-suited for solving partial differential equations (PDEs). When viewed as a Galerkin trial space under the variational SNA (VSNA) framework, the formulation satisfies classical variational guarantees under Lax-Milgram: well-posedness, quasi-optimality, convergence, and stability. In high-dimensional spatiotemporal–parametric PDEs, the VSNA mitigates the curse of dimensionality by scaling algebraically rather than exponentially. Exploiting an entirely factorized, tensor-native alternating least squares (ALS) optimization framework reduces this cost to linear in dimension. The VSNA is validated across elliptic, hyperbolic, and parabolic systems, demonstrating close alignment with predicted algebraic and spectral scaling rates. We showcase the SNA as a "solve once, query anywhere" physical world model via two engineering case studies: a 7D parametric manufacturing simulation and an experimental thermal-to-property inversion pipeline for Inconel 718. The VSNA executes a 1,000,000-query Monte Carlo sweep in 102s on a standard laptop CPU, yielding a 150,000x speedup over a full-grid finite element baseline hosted on an NVIDIA A100 GPU. It further enables real-time generative inverse-mode reconstructions under 100ms. These results demonstrate that the SNA serves as a compact mathematical substrate for continuous parameter manifolds to enable real-time inversion, optimization loops, and rapid uncertainty propagation.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.11977

ParseFixer: An Agentic Framework for Document Parsing via Selective Multimodal Correction

作者:

LeKai Yu↗Hao Liu↗Kun Wang↗Zhiran Li↗Ruping Cao↗Fan Liu↗Yupeng Hu↗

In this report, we present our third-place solution for the DataMFM Challenge Track 1: Document Parsing. This track requires models to recover structured Markdown documents from document page images while preserving textual content and document structure. To address the complementary requirements of accurate content recovery and faithful structure reconstruction, we propose ParseFixer, an agentic framework for backbone parsing and selective correction. ParseFixer consists of two key modules: Full-Page Backbone Parsing (FBP) and Agentic Selective Correction (ASC). FBP produces stable initial Markdown outputs with MinerU2.5 Pro, while ASC detects high-value parsing failures and repairs them through a verify-and-rollback correction process. By placing selective multimodal correction after open-source backbone parsing, ParseFixer improves the recovery of key document elements without rewriting reliable backbone predictions. On the test set, our final system achieves an overall score of 61.78 and ranks third in Track 1, demonstrating its effectiveness for accurate document parsing. Our code will be released at: https://github.com/iLearn-Lab/CVPRW26-ParseFixer.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14176

VeriGeo: Controllable Geometry Question Generation with Numerical and Analytical Verification

作者:

Xiaoxian Duan↗Zequn Liu↗Yingce Xia↗

arXiv:2606.14176v1 Announce Type: new Abstract: Geometry problem generation is useful for AI-assisted education and multimodal mathematical reasoning, but reliable synthesis remains difficult because the problem statement, diagram, constraints, and solution should be mutually consistent. Existing methods often trade off controllability and reliability: seed-based rewriting is flexible but weakly verifiable, whereas diagram-first construction improves validity but is less suited to arbitrary user-specified constraints. We introduce VeriGeo, a controllable geometry generation framework grounded in executable reasoning traces. Given user constraints such as target concepts and difficulty, an Author agent generates a problem and diagram, and a Solver agent produces a proof-aligned solution. Both agents use a shared action sequence that connects natural language, diagrams, geometric constraints, and proof steps into a verifiable representation. A three-stage pipeline checks numerical consistency, analytical realizability, and global consistency, using verification-guided reflection to repair recoverable failures and reject unrecoverable ones. Across five LLM backbones, raw generations frequently fail these checks, while VeriGeo repairs a substantial fraction of the invalid attempts. Supervised fine-tuning on 8.7k examples generated by VeriGeo achieves the best reported GeoQA performance among end-to-end multimodal LLM-based solvers, and obtains strong results on PGPS9K and MathVista-GPS, demonstrating the effectiveness of verified synthetic data for improving multimodal geometry reasoning.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2602.14913

Coverage Guarantees for Pseudo-Calibrated Conformal Prediction under Distribution Shift

作者:

Farbod Siahkali↗Ashwin Verma↗Vijay Gupta↗

arXiv:2602.14913v2 Announce Type: replace Abstract: Conformal prediction (CP) offers distribution-free marginal coverage guarantees under an exchangeability assumption, but these guarantees can fail if the data distribution shifts. We analyze the use of pseudo-calibration as a tool to counter this performance loss under a bounded label-conditional covariate shift model. Using tools from domain adaptation, we derive a lower bound on target coverage in terms of the source-domain loss of the classifier and a Wasserstein measure of the shift. Using this result, we provide a method to design pseudo-calibrated sets that inflate the conformal threshold by a slack parameter to keep target coverage above a prescribed level. Finally, we propose a source-tuned pseudo-calibration algorithm that interpolates between hard pseudo-labels and randomized labels as a function of classifier uncertainty. Numerical experiments show that our bounds qualitatively track pseudo-calibration behavior and that the source-tuned scheme mitigates coverage degradation under distribution shift while maintaining nontrivial prediction set sizes.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20442

Evolutionary Two-Stage Hyperparameter Optimization Strategies for Physics-Informed Neural Networks

作者:

Fedor Buzaev↗Dmitry Efremenko↗Egor Bugaev↗Andrei Ermakov↗Denis Derkach↗Daria Pugacheva↗Fedor Ratnikov↗

arXiv:2606.20442v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) solve Partial Differential Equations (PDEs) by embedding physical laws into neural network training. However, their performance suffers from unstable convergence, training plateaus, and strong sensitivity to architectural and optimization hyperparameters due to the highly non-convex and multi-term structure of the physics-informed loss. In this setting, the outer-loop hyperparameter search is a noisy and black-box optimization problem over heterogeneous parameters, where classical local or gradient-based strategies are easily trapped in suboptimal regions. Evolutionary algorithms, with their population-based exploration and ability to handle mixed, non-differentiable search spaces, provide a more robust mechanism for discovering promising configurations. We propose and investigate a two-stage approach based on evolutionary algorithms that combines exploration and exploitation parts of PINNs training to improve solution accuracy and robustness under fixed computational budgets. In the first stage, we perform low-fidelity training runs with truncated epochs to rapidly screen candidate configurations, treating hyperparameter selection as a black-box outer-loop problem. In the second stage, only the most promising candidates are fully trained with standard gradient-based optimizers to refine the solution. Evaluated on three popular problems, namely Advection, Klein-Gordon and Helmholtz equations, our method consistently outperforms standard training and achieves significantly lower mean error within constrained computational resources.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12003

Agreement in Representation Space for Open-Ended Self-Consistency

作者:

Paula Ontalvilla↗Gorka Azkune↗Aitor Ormazabal↗

Self-consistency improves LLM reasoning by sampling multiple outputs and selecting the most consistent answer, but existing formulations largely rely on exact matching and therefore remain limited to tasks with categorical outputs. In this work, we study self-consistency in open-ended generation tasks such as code synthesis and text summarization. We hypothesize that consistency can be understood as a geometric property of the generation space, where semantically compatible generations concentrate in similar regions of representation space. To study this hypothesis, we introduce Embedding-Based Agreement (EBA), a simple training-free operationalization that estimates agreement by clustering sampled generations in embedding space. Through experiments on mathematical reasoning, code generation, and summarization, we show that agreement in representation space provides a robust and scalable signal of self-consistency for open-ended tasks. In particular, EBA consistently outperforms random selection and exhibits more stable scaling behavior than recent selection approaches based on LLM evaluation or uncertainty estimation. We further show that these agreement signals remain stable across model families and embedding spaces, even with native hidden representations. Finally, our analysis shows that the geometric location occupied by sampled generations is strongly correlated with generation quality: generations concentrated near central regions of representation space tend to correspond to more reliable outputs, whereas peripheral generations are substantially less accurate. Overall, our findings support viewing self-consistency as a property of the geometric organization of sampled generations rather than exact symbolic overlap.

阅读与讨论 → 访问原文 →

08.

medRxiv (Medicine) 2026-06-12 DOI: HASH:7b1938f854eaf3926cf382c8fb1e494a

Effect of tenofovir on the outcomes of COVID-19 in persons with chronic hepatitis B: a nationwide cohort study in Sweden.

作者:

Jakobsson↗F. F↗Eriksson↗Kalucza↗S. F↗Fors Connolly↗A.-M↗

Background: Patients with chronic hepatitis B (CHB) may have an increased risk of severe COVID-19. Tenofovir has been hypothesized to confer protection against severe disease, but evidence is inconclusive. We evaluated the risk of severe COVID-19 among CHB patients treated with tenofovir compared with other nucleos(t)ide analogues (NAs). Methods and findings: In this nationwide, registry-based cohort study, we included all adults with CHB and laboratory-confirmed COVID-19 in Sweden between February 2020 and July 2022. Data from national health and socioeconomic registers were linked using unique personal identification numbers (PINs). Patients with HIV, hepatitis C, or hepatitis D coinfection were excluded. Exposure was defined as tenofovir versus other NA therapy. The primary outcome was severe COVID-19, defined as hospitalization >2 days or death within 30 days of diagnosis. Logistic regression was used to estimate adjusted odds ratios (aOR) with 95% confidence intervals (CI), controlling for age, sex, comorbidities, vaccination, socioeconomic status, and region of birth. Among 5,877 CHB patients with COVID-19, 672 were receiving NA therapy (437 tenofovir, 235 other NAs). Severe COVID-19 occurred in 8.0% of tenofovir-treated patients and 14.5% of those receiving other NAs (unadjusted OR 0.52; 95% CI, 0.31-0.85). After adjustment, the association was attenuated and no longer significant (aOR 0.72; 95% CI, 0.39-1.31). Older age, comorbidities, and unvaccinated status were strongly associated with severe disease. Conclusions: The apparent protective effect of tenofovir against severe COVID-19 in unadjusted analyses was largely explained by confounding factors. The risk of severe disease was primarily driven by age, comorbidities, and vaccination status. Prevention of severe COVID-19 in patients with CHB should instead focus on vaccination and management of comorbidities.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11512

SAGE: Answer-Conditioned Uncertainty Targets for Verbal Uncertainty Alignment

作者:

Kaiwen Shi↗Zheyuan Zhang↗Yanfang Ye↗

Large language models increasingly express uncertainty through natural-language statements, yet these expressions often fail to reflect the model's sampled behavior. We study verbal uncertainty alignment as a distributional calibration problem: the appropriate uncertainty target for a prompt should be estimated from repeated model outputs rather than from an isolated response. However, group rollouts alone are insufficient, since the resulting target must provide a useful training signal. Existing targets only partially satisfy this requirement. We propose SAGE, Semantic-Answer Guided Entropy, a group-level uncertainty target that constructs an answer-conditioned uncertainty geometry over sampled responses. SAGE preserves categorical, numeric, and symbolic answer distinctions while maintaining a smooth and scale-preserving calibration signal. We further apply this target through Group-Uncertainty Preference Optimization, or GUPO, an uncertainty-channel training framework that supervises verbal uncertainty expressions rather than the full response. Experiments across factual, mathematical, and multiple-choice reasoning tasks show improved uncertainty ranking, lower calibration error, and reduced overconfidence.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15301

Discovering Lattice Reduction Strategies via Self-Play

作者:

Mohamed Malhou↗Kristin Lauter↗Ludovic Perret↗

arXiv:2606.15301v1 Announce Type: cross Abstract: The Lenstra-Lenstra-Lovász (LLL) algorithm is a seminal contribution to computer science used for lattice basis reduction, yet its polynomial-time outputs produce bases that are far from optimal as the dimension grows. We show that deep reinforcement learning can discover strictly superior, generalizable reduction strategies by interacting with the primitive action space of LLL. We formulate lattice reduction as a single-player Markov Decision Process (MDP) and train a deep residual network using an AlphaZero-style self-play pipeline augmented with adaptive-horizon MCTS (Monte Carlo Tree Search), which couples multi-step network predictions with an entropy-gated expansion mechanism. The resulting policy, DeltaStar, is trained exclusively on small $8$-dimensional $q$-ary lattices and requires fewer primitive row operations than LLL. Crucially, it generalizes zero-shot to unseen moduli and higher dimensions up to $n=32$ without retraining.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16658

Vision-Language Models as Zero-Annotation Oracles in Histopathology

作者:

Vishal Jain↗Giorgio Buzzanca↗Sarah Cechnicka↗Maarten Naesens↗Priyanka Koshy↗Tri Nguyen↗Jesper Kers↗Candice Roufosse↗Bernhard Kainz↗

Foreground segmentation is the critical first step of every computational pathology pipeline, yet existing methods rely on hand-tuned heuristics or supervised models that overfit to narrow stain and scanner distributions, failing silently on specialised stains such as Jones silver or Elastica van Gieson. We propose a coarse-to-fine approach that recasts foreground segmentation as a visual perception task and leverages general-purpose vision-language models (VLMs) as zero-annotation oracles. Our key insight is that tissue-versus-background discrimination is a natural-image recognition problem, not a histopathological one, so VLMs trained on internet-scale corpora generalise where domain-specific models cannot. We introduce Leica-75, a benchmark of 75 renal transplant whole-slide images spanning three stain families. On Leica-75, our method achieves the highest segmentation quality on out-of-distribution stains (Dice 0.858 +/- 0.027 on Jones, 0.853 +/- 0.041 on EVG) with 7x lower cross-stain variance than the best supervised baseline, while remaining competitive on in-distribution H&E. Few-shot prompting with automatically curated exemplars (Auto-context) rescues hard cases on Stress-32 (n=32), a curated stress-test subset (Dice 0.470 to 0.819 for the 2B model). VLM-based annotation review matches human expert consensus (kappa=0.989 for blur detection; mean precision/recall grading accuracy 0.708 vs. human 0.646 for segmentation mask review). The resulting pseudo-labels are used to distil lightweight student models that are as performant as the teacher model while running for a fraction of the cost. Our framework provides a principled, scalable solution to a persistent infrastructure bottleneck in digital pathology.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11264

OmniBioTwin: A System-of-Twinned-Systems Framework for Health Digital Twins

作者:

Zhaohui Wang↗Yu Huang↗Jiang Bian↗

arXiv:2606.11264v1 Announce Type: cross Abstract: Health digital twins (HDTs) promise patient-specific modeling and decision support but current approaches remain structurally fragmented: monolithic models that address a single organ or task lack cross-scale fidelity, while system-level twins lack generalizable architectural frameworks. We propose OmniBioTwin, a System-of-Twinned-Systems (SoTS) framework that organizes HDTs as modular computational entities coupled through explicit interaction operators within a multi-layer network architecture. The framework comprises seven coordinated layers - spanning data integration, autonomous twin modeling, cross-scale coupling, temporal synchronization, and human-in-the-loop decision support. We demonstrate OmniBioTwin by instantiating a multiscale twin for glucagon-like peptide-1 (GLP-1) signaling pathways in Alzheimer's disease, illustrating how molecular, cellular, and organ-level twins can be composed and coupled within a unified system.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.01338

Benchmarking Local LLMs for Natural-Language-to-SQL Querying in Biopharmaceutical Manufacturing: An Empirical Benchmark on Consumer-Grade Hardware

作者:

Sagar Bhetwal↗Rajan Bastakoti↗Nirajan Acharya↗Gaurav Kumar Gupta↗Ambika Baniya Bhandari↗

Biopharmaceutical manufacturing organizations operate under regulatory frameworks such as FDA guidance, EU Good Manufacturing Practice (GMP), and the EU AI Act, which can restrict the use of cloud-based artificial intelligence systems. Locally deployed large language models (LLMs) offer a privacy-preserving alternative, but their suitability for pharmaceutical manufacturing tasks remains underexplored. This study evaluates four open-source LLMs (Qwen 2.5 Coder 7B, Llama 3.1 8B, Mistral 7B, and Meditron 7B) deployed locally via Ollama for natural-language-to-SQL generation over a pharmaceutical manufacturing database. A FastAPI-based evaluation platform, PharmaBatchDB AI, was developed using a synthetic Microsoft SQL Server database containing approximately 63,000 records across Batch, Manufacturing Execution System (MES), and Clean-In-Place (CIP) modules. Models were benchmarked on 60 domain-specific natural-language questions using metrics including SQL extraction rate, SQL compliance, factual consistency, ROUGE-L, hallucination rate, throughput, and latency. Qwen 2.5 Coder 7B, Llama 3.1 8B, and Mistral 7B generated SQL for all evaluation tasks, while Meditron 7B failed on nearly all tasks due to context-window limitations and poor SQL generation capability. Llama 3.1 8B achieved the highest SQL compliance, whereas Qwen 2.5 Coder 7B achieved the strongest overall text similarity and factual consistency. Performance differences between the two leading models were not statistically significant. The results show that code-tuned general-purpose LLMs outperform a domain-specific biomedical model on structured query generation for pharmaceutical manufacturing data. Although fully local, GxP-aligned NLQ systems are feasible on consumer hardware, current performance levels still require human oversight and downstream validation for regulated use.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15017

Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents

作者:

Sina Hajimiri↗Masih Aminbeidokhti↗Jose Dolz↗Ismail Ben Ayed↗Issam H. Laradji↗Spandana Gella↗Nicolas Gontier↗

Online web agents often augment a base actor with memory, workflow, or skill modules. These modules can improve performance, but they also consume test-time tokens, a cost rarely reported alongside the actor's inference cost. We study online augmentation, where this overhead is paid on every task, and re-evaluate its benefits under a fixed total inference budget. We compare AWM, ASI, and ReasoningBank with a token-matched vanilla baseline that uses the same budget for additional actor steps. Across three WebArena domains and three models, Gemini 3 Flash, GPT-5.4-mini, and Qwen 3.6-27B, the vanilla baseline matches or surpasses all three augmentation methods in aggregate success rate while often using fewer total tokens. We observe a similar trend on WorkArena-L1 with Qwen 3.6-27B, indicating that the effect extends to enterprise knowledge-work tasks. Our results suggest that skills and workflow memory can be useful in specific domains, but their apparent gains often vanish against a budget-matched actor. We further show that run-to-run variance materially affects outcomes and should be reported as a core evaluation criterion for online web agents.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20416

On the Redundancy of Timestep Embeddings in Diffusion Models

作者:

Jos\'e A. Ch\'avez↗

arXiv:2606.20416v1 Announce Type: new Abstract: Diffusion models rely heavily on explicit timestep embeddings to modulate the denoising process across various noise scales. In this work, we challenge the necessity of these temporal signals by analyzing their impact on U-Net and Diffusion Transformer architectures. Beyond empirical evidence, we provide a theoretical framework demonstrating that, under certain conditions, the global minimizer of the diffusion training objective can be achieved without explicit timestep conditioning. Our findings reveal a surprising robustness when timestep embeddings are completely removed. Extensive ablation studies on the CelebA and CIFAR-10 datasets show that these time-agnostic models can maintain high structural fidelity and even surpass their conditioned counterparts in competitive metrics, including FID, precision, and recall. Our analysis suggests these architectures can implicitly infer noise scales from the corrupted input under specific assumptions, rendering explicit temporal conditioning redundant. This study challenges long-standing temporal conditioning paradigms and paves the way for more efficient and structurally focused generative architectures.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.20138

Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring

作者:

Po-Chin Chang↗Nicholas Hogan↗Aske Plaat↗Michiel T. van der Meer↗

LLMs can personalize education, although current static-prompt tutoring systems struggle to adapt to diverse academic disciplines. We develop and test a system with subject-aware prompting, based on 14 pedagogical features (e.g., tutor scaffolding, student understanding) extracted from raw transcripts. We first train a prompt routing model in a simulation environment, and then deploy it for online adaptation with actual high-school students. The simulation benchmark shows the router outperforming two static baselines ($0.694$ vs. $0.647$ and $0.64$, $p

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12291

Measuring Epistemic Resilience of LLMs Under Misleading Medical Context

作者:

Hongjian Zhou↗Xinyu Zou↗Jinge Wu↗Sean Wu↗Junchi Yu↗Bradley Max Segal↗Tobias Erich Niebuhr↗Sara Amro↗Michael Petrus↗Sheikh Momin↗Alexandra M. Cardoso Pinto↗Rachel Niesen↗…

Large language models (LLMs) now reach expert-level scores on medical licensing exams, encouraging the assumption that high scores imply safe medical judgment while patients increasingly use them for health advice. We show this assumption is fragile: when misleading context is injected into questions that LLMs originally answer correctly, they abandon the correct answer. We call the ability to maintain correct judgment under adversarial context epistemic resilience, and introduce MedMisBench to measure it. MedMisBench contains 10,932 medical question items and 48,889 misleading context-option pairs spanning medical reasoning, agentic capability, and patient-journey evaluation. Across 11 model configurations, mean accuracy falls from 71.1% on original questions to 38.0% under focused misleading context, with 51.5% attack success. The most damaging injections are formal, rule-like fabrications: authority-framed falsehoods reach 69.5% attack success and exception-poisoning claims reach 64.1%. A 14-member clinical panel from 7 countries identified serious potential harm in 38.2% of reviewed cases. MedMisBench exposes a structural blind spot in LLM evaluation in medical settings: existing benchmarks measure what models know, but not whether they preserve correct medical judgment under misleading context.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.01621

Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation

作者:

Muyi Bao↗Yuxin Cai↗Hang Xu↗Zongtai Li↗Jinxi He↗Jingfan Tang↗Chen Lv↗Ji Zhang↗Yaqi Xie↗Wenshan Wang↗

Vision-language models (VLMs) have become a common foundation for vision-and-language navigation in continuous environments (VLN-CE). Yet most VLM-based methods cast navigation as low-level action prediction, an interface that is ambiguous, tied to short-horizon motion primitives, and inefficient due to repeated VLM querying. We propose Goal2Pixel, a pure pixel-based paradigm that reformulates VLN-CE as navigable pixel grounding. Rather than predicting actions, Goal2Pixel uses the image plane as a unified spatial interface between VLM reasoning and robot motion: the model predicts a visible navigable pixel to the agent, which is back-projected into a 3D waypoint for forward navigation. For non-forward actions, we append auxiliary directive regions to the image plane, where the left/right/bottom regions are interpreted as turning left, turning right, and stopping, respectively. To enable long-horizon navigation, we propose a visibility-aware keyframe memory for compact and informative history representation. To adapt pretrained VLMs to navigable pixel grounding, we introduce semantic embeddings and coordinate-aware auxiliary losses. Goal2Pixel achieves competitive state-of-the-art performance while requiring fewer VLM inference calls than prior methods. On R2R-CE Val-Unseen it achieves 54.1% SR and 52.5% SPL with just 7.75 VLM calls per episode, 6x fewer than the 46.62 required by direct action prediction at 32.9% SR. The same trend holds on RxR-CE.Project Page: https://baobao0926.github.io/Goal2Pixel/.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12837

LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling

作者:

Jiarui Zhao↗Rongzhi Zhang↗Lingchuan Liu↗Hao Yang↗Xunliang Cai↗Xi Su↗

Search agent benchmarks exemplified by BrowseComp have rapidly saturated over the past year, with the strongest models surpassing 90% accuracy. Since these benchmarks are predominantly human-authored, annotators lack a global perspective on entity statistics and cannot systematically maximize search space size and structural complexity. This creates a difficulty ceiling that is hard to break. To address this, we introduce LoHoSearch (Long-Horizon Search Agents), a challenging benchmark comprising 544 human-verified questions across 11 domains. LoHoSearch is constructed via an automated pipeline built upon a knowledge graph covering over 7 million Wikipedia entities, which selects relations with large search spaces and assembles them into structurally complex questions with KG-verified unique answers. Our evaluation demonstrates that even the strongest model achieves only 34.74% accuracy, and existing context management strategies (best +6.8%) yield far smaller gains than on prior benchmarks. LoHoSearch provides a more demanding standard for evaluating long-horizon reasoning and context management in search agents.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.11868

MemNovo: Look Back at the Spectrum for Balanced De Novo Peptide Sequencing from Mass Spectrometry

作者:

Dongxin Lyu↗Jingbo Zhou↗Hongxin Xiang↗Yuqiang Li↗Jun Xia↗

arXiv:2606.11868v1 Announce Type: new Abstract: De novo peptide sequencing from tandem mass spectrometry is pivotal in proteomics, enabling identification of novel peptides without reference databases. While recent Transformer-based encoder-decoder models have achieved remarkable performance, we uncover a critical pathology in their inference dynamics. Through comprehensive feature scaling experiments, we demonstrate that existing auto-regressive peptide decoders tend to over-rely on generated-sequence priors while progressively under-utilizing fine-grained physical evidence from the input mass spectrum. This phenomenon leads to suboptimal results, where generated peptide sequences are biologically plausible yet not faithful to the input spectrum. To rectify this, we propose MemNovo, a training-free and plug-and-play mechanism that re-balances peptide and spectral contributions at inference time. MemNovo alleviates the information bottleneck by establishing a persistent spectral memory bank and injecting retrieved features directly into the final decoding stage via an ultra-conservative residual connection. Theoretical analysis confirms that this mechanism restores the mutual information between the decoder state and the raw spectrum. Extensive experiments on the Nine Species benchmark with two representative baselines, Casanovo and InstaNovo, demonstrate that MemNovo consistently improves both amino acid precision and peptide precision, achieving up to 39.1% relative improvement in peptide precision for Casanovo and up to 3.9% for InstaNovo, with negligible computational overhead.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2510.14807

Beyond the Sampled Token: Preserving Candidate Support in RLVR

作者:

Ruotian Peng↗Yi Ren↗Zhouliang Yu↗Weiyang Liu↗Yandong Wen↗

arXiv:2510.14807v3 Announce Type: replace Abstract: We revisit exploration collapse in reinforcement learning with verifiable rewards (RLVR), from the perspective of the candidate distribution for next-token prediction. We formally show that as probability concentrates on the top-$1$ candidate, the expected number of distinct responses collapses to one regardless of the sampling budget $K$. This theoretical implication is further verified by our empirical tracking of top-$N$ candidate probabilities during training, where the top-$1$ candidate progressively dominates while plausible alternatives are suppressed. These findings suggest a key desideratum for effective exploration: preserving non-negligible probability mass on the top-$N$ candidates. To this end, we propose Candidate-aware Support Preservation (CaSP), with two complementary designs. Specifically, CaSP redistributes positive gradients among top-$N$ candidates for correct responses, and applies a stronger penalty to the top-$1$ candidate for incorrect responses. Unlike many exploration-oriented methods that improve pass@$K$ at the cost of pass@1, CaSP improves pass@$K$ across the full $K$ spectrum. These gains generalize to 6 math, 2 logical-reasoning, and 2 coding benchmarks, and scales to 32B-parameter models and sampling budgets up to $K=1024$, positioning it as a principled, candidate-level approach for RLVR exploration.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13925

Sorries Are Not the Hard Part: An Expert-Review Case Study of a Semi-Autonomous Formalization

作者:

Vasily Ilin↗Brian Nugent↗

arXiv:2606.13925v1 Announce Type: new Abstract: Large language models can often close proof gaps in interactive theorem provers, but a verified theorem is not the same thing as a reusable library contribution. We study this distinction through a detailed case study: a semi-autonomous formalization of Grothendieck's vanishing theorem. The initial version compiles with no sorries, but an expert review found serious problems in definitions, theorem generality, file organization, and the API. We then ran a review-driven refactor and compression process and obtained a second expert review. The before-and-after comparison shows a sharp split: agents adapted well to local, mechanically checkable feedback, but remained weak at choosing definitions and designing APIs. We argue that autoformalization should be evaluated not only by closed sorries, but by whether the resulting formalization survives expert review.

阅读与讨论 → 访问原文 →

23.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2604.14921

Split-Evolution Quantum Phase Estimation for Particle-Conserving Hamiltonians

作者:

Megan Cerys Rowe↗Carlo A. Gaggioli↗Ludmila Szulakowska↗David Mu\~noz Ramo↗David Zsolt Manrique↗

arXiv:2604.14921v2 Announce Type: replace Abstract: We present a hardware demonstration and resource analysis of split-evolution quantum phase estimation (SE-QPE) on a Quantinuum System Model H2 quantum computer. SE-QPE is a modification to canonical QPE for particle-conserving Hamiltonians in which controlled time evolution is replaced by CSWAP-based interference between a target register and a reference register. For factorizations of time evolution with a shared eigenbasis, SE-QPE preserves the phase-register outcome distribution of canonical QPE and, unlike with compute–uncompute substitutions, it remains compatible with non-exact eigenstates. The substitution removes controlled-simulation overhead and enables parallel evolution on two registers, reducing the depth of each phase-kickback block. Resource analysis for Trotterized double-factorized chemistry Hamiltonians shows that the substitution becomes increasingly favorable at higher phase powers and combining QPE and SE-QPE implementations can be a useful option. Over a range of FeMoco active spaces, SE-QPE reduces time evolution resources, with asymptotic reductions of about 33% in CX count, 25% in $T$ count, and an asymptotic depth ratio of $3/N$ for CX layers. On Quantinuum H2-2, a four-qubit model ethylene demonstration with explicit inverse QFT and repeated phase-kickback steps up to 8 phase bits yields distinct energies and shows the auxiliary registers provide useful error detection filters.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19544

Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias

作者:

Justin D. Norman↗Michael U. Rivera↗D. Alex Hughes↗

LLM-as-a-Judge has become the dominant evaluation paradigm for language models, but judge validation in practice relies on exact-match agreement, a metric that does not correct for chance and systematically overstates discriminative ability. We present the largest systematic evaluation of LLM-as-a-Judge to date: 21 judges from nine providers across MT-Bench, JudgeBench, and RewardBench, evaluated under three protocols (agreement, consistency, bias audit) over 118 runs and approximately 541,000 individual judgments. Four findings emerge, consistent across the full cohort, including the April 2026 frontier: kappa deflation between exact match and Cohen's kappa is universal (33–41 pp on MT-Bench), judge rankings shift by up to 14 positions across benchmarks, high test–retest reliability (>0.95) coexists with severe position bias (>0.10) in two production-deployed judges (instantiating a consistency–bias paradox), and verbosity bias is small (

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2602.06014

Optimism Stabilizes Thompson Sampling for Adaptive Inference

作者:

Shunxing Yan↗Han Zhong↗

arXiv:2602.06014v2 Announce Type: replace-cross Abstract: Thompson sampling (TS) is widely used for stochastic multi-armed bandits, yet its inferential properties under adaptive data collection are subtle. Classical asymptotic theory for sample means can fail because arm-specific sample sizes are random and coupled with the rewards through the action-selection rule. We study adaptive inference for Thompson sampling with Gaussian randomized indices in $K$-armed stochastic bandits with independent sub-Gaussian reward noises, and identify optimism as a key mechanism for restoring stability, meaning that each arm's pull count concentrates around a deterministic scale. This stability yields asymptotically valid Wald inference despite adaptive sampling. First, we prove that variance-inflated TS is stable for any $K \ge 2$, including the challenging regime where multiple arms are optimal, with asymptotically uniform allocation over optimal arms and sharp logarithmic pull-count asymptotics for suboptimal arms. This resolves the $K$-armed extension question raised by \citet{halder2025stable}, using new winner-map and Lyapunov-drift techniques to control allocation among multiple optimal arms. Second, we analyze an alternative optimistic modification that keeps the Gaussian index variance unchanged but adds an explicit mean bonus to the index center, and establish a similar stability conclusion. In summary, suitably implemented optimism stabilizes Thompson sampling and enables asymptotically valid Wald inference in multi-armed bandits, while incurring only a mild additional regret cost.

阅读与讨论 → 访问原文 →