探索全球前沿学术脉络

01.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2601.19072

HalluJudge: A Reference-Free Hallucination Detection for Context Misalignment in Code Review Automation

作者:

Kla Tantithamthavorn↗Hong Yi Lin↗Patanamon Thongtanunam↗Wachiraphan Charoenwet↗Minwoo Jeong↗Ming Wu↗

arXiv:2601.19072v3 Announce Type: replace-cross Abstract: Large Language models (LLMs) have shown strong capabilities in code review automation, such as review comment generation, yet they suffer from hallucinations – where the generated review comments are ungrounded in the actual code – poses a significant challenge to the adoption of LLMs in code review workflows. To address this, we explore effective and scalable methods for a hallucination detection in LLM-generated code review comments without the reference. In this work, we design HalluJudge that aims to assess the grounding of generated review comments based on the context alignment. HalluJudge includes four key strategies ranging from direct assessment to structured multi-branch reasoning (e.g., Tree-of-Thoughts). We conduct a comprehensive evaluation of these assessment strategies across Atlassian's enterprise-scale software projects to examine the effectiveness and cost-efficiency of HalluJudge. Furthermore, we analyze the alignment between HalluJudge's judgment and developer preference of the actual LLM-generated code review comments in the real-world production. Our results show that the hallucination assessment in HalluJudge is cost-effective with an F1 score of 0.85 and an average cost of $0.009. On average, 67% of the HalluJudge assessments are aligned with the developer preference of the actual LLM-generated review comments in the online production. Our results suggest that HalluJudge can serve as a practical safeguard to reduce developers' exposure to hallucinated comments, fostering trust in AI-assisted code reviews.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.LG) 2026-06-25 DOI: arXiv:2606.24962

Towards Scalable Multi-Task Reinforcement Learning with Large Decision Models

作者:

Thibaut Kulak↗

arXiv:2606.24962v1 Announce Type: new Abstract: Recent progress in large-scale sequence modeling has shown that a single model can learn useful representations across highly diverse data distributions. Inspired by these advances, we investigate whether a unified transformer policy can be trained across large collections of heterogeneous reinforcement learning environments. We introduce LDM-v0, a Large Decision Model trained offline on trajectories collected from thousands of environments spanning multiple domains and modalities. LDM-v0 is a multi-task, multi-modal transformer policy conditioned on histories of observations, actions, rewards, and termination signals, and trained through supervised next-action prediction over offline trajectories. We describe the environment infrastructure, automated data generation pipeline, model architecture, and training methodology used to build LDM-v0, and evaluate its performance across diverse environments. We show that a single pretrained model matches the performance of independently trained task-specific reference policies on approximately 1,000 environments including robotics, autonomous driving, inventory management, cybersecurity, trading, and video games. These results demonstrate the feasibility of large-scale offline pretraining across heterogeneous reinforcement learning environments using a single transformer policy.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18383

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability

作者:

Dibyanayan Bandyopadhyay↗Asif Ekbal↗

Sparse autoencoders (SAEs) are increasingly used to extract interpretable features from language models (LMs), yet a central question remains: when can an SAE-based explanation be treated as a faithful view of an underlying frozen LM We study this through a post-hoc generalization framework that certifies the LM via a sparse proxy, obtained by replacing a native hidden activation with its pretrained SAE reconstruction. Our framework derives an upper bound on the base model's expected risk using four measurable quantities: proxy risk, SAE reconstruction gap, concept-pool mismatch, and sparse complexity. We interpret this certificate as an operational criterion for explanatory faithfulness. In particular, a non-vacuous bound indicates that the extracted sparse features retain meaningful predictive information, while small reconstruction and mismatch errors indicate that the proxy remains behaviorally close to the original model. Empirically, we show that the bound becomes non-vacuous on GPT-2 Small, Gemma-2B, and Llama-3-8B at practical sample sizes. A detailed layerwise analysis of Llama-3-8B reveals a strong depth dependence, with later layers becoming much easier to certify, associated with both stronger local fidelity and weaker downstream error amplification. Finally, through feature-shuffling ablations, we show that the decomposition distinguishes genuine semantic alignment from mere statistical sparsity, providing a useful diagnostic for when SAE-based explanations become less reliable.

阅读与讨论 → 访问原文 →

04.

medRxiv (Medicine) 2026-06-15 DOI: HASH:059b2ac339eaa148442e7ad7eb582385

Filum Terminale Diameter on Routine Pediatric MRI: A Large-Cohort Clinical Reference in 3,406 Children and the Age-Dependent Meaning of the 2-mm Thickened-Filum Threshold

作者:

Tang↗Dong↗Chen↗Yang↗Huang↗Yu↗Zhu↗Shen↗

Background. A filum diameter >2 mm is the conventional MRI threshold for a thickened filum, but it derives from small, mostly adult series showing no age dependence; whether one cutoff suits all of childhood is untested. Objective. To build an age-specific filum-diameter reference on routine pediatric MRI and test, adjusting for image resolution, whether the 2-mm threshold is age-stationary. Materials and methods. In this retrospective study an nnU-Net tracer measured the maximal filum diameter on consecutive lumbosacral MRI; versus manual tracing it showed negligible bias but moderate single-measure agreement. After excluding report-confirmed fatty filum, lipoma, or tethered cord, the proportion >2 mm was analysed within one acquisition protocol and by logistic regression adjusting for voxel size and slice thickness. Results. Of 7,245 examinations, 3,869 (53%) were traceable; untraced ones were younger (median 0.75 vs 2.0 years). The presumed-normal cohort had median diameter 1.48 mm. At matched resolution, 2 mm marked the 94th percentile in infants (5.6% exceeded it) but the 83rd by 3-6 years (17.4%); the age effect persisted after adjusting for voxel size and slice thickness (3-6 years vs infants, adjusted OR 4.7; P < .001). Conclusion. Filum diameter clusters near 1.5 mm, and the fixed 2-mm cutoff flags ~5% of infants but ~17% of preschoolers. Caliber should be judged against an age-specific clinical reference, not one fixed cutoff; a thick filum is not itself a diagnosis of tethered cord.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11522

Search Discipline for Long-Horizon Research Agents

作者:

Adithya Srinivasan↗Devesh Paragiri↗

arXiv:2606.11522v1 Announce Type: new Abstract: Autoresearch agents now propose, evaluate, and select scientific candidates against a metric, and that metric is usually an aggregate reduced over a heterogeneous space of regions, slices, or cohorts. We show that when scientific validity lives in that disaggregated structure, the aggregate can rank the wrong candidate first. The headline number improves while the structure underneath inverts, so a decision made on the number accepts a candidate that quietly breaks the model. The failure is not domain-specific. It appears wherever a candidate's validity is multi-dimensional but its verifier is a single reduction. We demonstrate the inversion on a fire-model task in the Ecosystem Demography model. The highest-scoring candidate and a slightly lower one are within noise of each other on global score, yet the top-scoring one collapses the protected boreal regions while the other preserves them. What separates them is the per-region behavior, not the headline number. This decision should not be left to the agent that produced the candidates. The agent optimizing the score is the last party likely to catch the score being wrong, and a prompt has no remaining turn once the agent has stopped. We move the decision to an external control loop that audits each candidate on its disaggregated behavior and acts after the agent has decided. It can demote a candidate the agent would have accepted, and it can reopen a run the agent had declared finished. Our contribution is the inversion finding itself, and a search-discipline protocol that decides on reviewable candidate-effect evidence instead of the score.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-24 DOI: arXiv:2606.24381

On the Stability of Prompt Ranking in Large Language Model Evaluation

作者:

Shaoshuai Du↗Penghao Liang↗Yixian Shen↗Chuanqi Shi↗Hang Zhang↗Lun Wang↗

Prompt-based interaction has become a dominant paradigm for using large language models (LLMs), where multiple candidate prompts are evaluated and the top-ranked one is selected for downstream use. This workflow implicitly assumes that prompt rankings are stable under minor variations in evaluation conditions. In this paper, we systematically study prompt ranking stability under common sources of variability, including random seeds and limited evaluation subsets. Across three open-weight LLMs and two benchmark tasks, we find that while overall rank correlations are often moderate to high, the identity of the top-performing prompt frequently changes, leading to unreliable selection decisions. To address this issue, we propose a simple stability-aware selection strategy based on a lower confidence bound, which accounts for both performance and variance. Our results show that this approach improves robustness in unstable settings while remaining competitive in more stable regimes. These findings highlight the importance of accounting for evaluation uncertainty in prompt selection and LLM benchmarking.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.15514

Reinforcement Learning-Guided Retrieval with Soft Fusion for Robust Multimodal Imitation Learning under Missing Modalities

作者:

Hassan Ismkhan↗Hamid Bouchahcia↗

arXiv:2606.15514v1 Announce Type: cross Abstract: Robotic systems perceive the world through multiple input modalities – including visual camera streams and natural language instructions – and must select appropriate actions based on these signals. However, assuming the permanent availability of all input devices is unrealistic, as sensors may fail, become occluded, or drop out entirely during deployment. Robust handling of such missing-modality scenarios is therefore essential for real-world robot operation. This paper introduces RL4IL, a reinforcement learning guided method for imitation learning that selects the most suitable action for a given observation by identifying the most relevant expert demonstrations from a training library. A reinforcement learning policy, trained via Proximal Policy Optimisation over Breadth-First Search candidate sets, ranks candidate demonstrations and a soft cross-attention fusion head aggregates their action signals to produce the final prediction. When a modality is missing at inference time, a dedicated per-modality RL retrieval policy identifies donor demonstrations from the training library, and a soft imputation head reconstructs the missing embedding via cross-attention over the top-ranked donors – without requiring any retraining of the system. Experiments on three LIBERO benchmark suites demonstrate that RL4IL substantially outperforms state-of-the-art imitation learning methods under sensor dropout conditions, while requiring no policy network training. The code can be found at https://github.com/h-ismkhan/Reinforcement-Learning-via-kNN-for-Robotic-Learning-with-Missing-Camera

阅读与讨论 → 访问原文 →

08.

bioRxiv (Bioinfo) 2026-06-11 DOI: HASH:7f0767439e6501da86fbc3e792d6f9af

A quantitative coordinate system for developmental dynamics

作者:

Wang↗Ren↗Moore↗Kelsh↗R. N↗McDole↗Dumitrascu↗Marioni↗J. C↗

Quantitative comparison of morphogenesis across individuals remains a fundamental challenge, as developing embryos vary in shape, orientation and developmental tempo. Moreover, real-time three-dimensional imaging generates large, heterogeneous four-dimensional datasets that are difficult to directly align. As a result, developmental variability is typically described qualitatively rather than measured. Here we introduce STERN, a quantitative framework that learns continuous spatiotemporal representations of morphogenesis directly from in vivo 4D imaging data. By embedding embryos into a shared spatiotemporal space, STERN defines a quantitative developmental coordinate system that enables direct comparison of developmental trajectories across individuals without requiring explicit registration or staging. Applied to mouse embryogenesis, STERN reveals that embryos follow conserved developmental trajectories while progressing at distinct temporal rates, providing a quantitative measure of developmental heterochrony. Extending this framework to zebrafish neural crest light-sheet timelapse imaging, we further show that developmental order is preserved across distinct imaging views even with altered anatomical coverage, supporting the generality of the learned representation across vertebrate imaging contexts. Finally, in developing mouse hearts, where morphogenesis proceeds through subtle and continuously evolving structural changes, STERN resolves fine-scale developmental dynamics at minute-scale temporal resolution that are difficult to localize reproducibly using human experts or general-purpose multimodal AI. Together, these results establish a shared quantitative coordinate system for morphogenesis, in which developmental trajectories become directly comparable across individuals and developmental variability becomes a measurable property.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16774

OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models

作者:

Tianyi Lin↗Chuanyu Sun↗Jingyi Zhang↗Changxu Wei↗Huanjin Yao↗Shunyu Liu↗Xikun Zhang↗Liu Liu↗Jiaxing Huang↗

Equipping Large Language Model (LLM) agents with effective skills is crucial for solving complex tasks in real-world systems like OpenClaw. In this work, we aim to develop a framework that automatically constructs such reusable skills to enhance LLMs in tool use, multi-step reasoning, and dynamic environment interaction. To this end, we propose Collective Skill Tree Search (CSTS), a novel tree-search-based skill construction framework that constructs structured, diverse and generalizable tree of skills. The core idea of CSTS is to leverage collective intelligence to jointly search, identify and compose effective skills via two iterative phases: Collective Skill Node Generation (CSN-Gen) and Collective Skill Node Assessment (CSN-Assess). CSN-Gen exploits collective knowledge from multiple models to explore diverse candidate skills for each subtask, enabling comprehensive skill exploration. CSN-Assess employs multiple models as judges to evaluate and select skill nodes with two scoring mechanisms: (1) collective quality scoring that aggregates independent evaluations to produce a robust estimate of skill effectiveness, and (2) collective transferability scoring that explicitly verifies whether a skill generalizes well across different models. With CSTS, we construct a set of comprehensive tree of skills along with skill-augmented training data, enabling models to effectively learn and utilize skills. Besides, we introduce Collective Skill Reinforcement Learning, which actively selects multiple relevant skills from the tree to broaden solution-space exploration, avoid being trapped by a single skill and its resulting homogeneous or suboptimal solutions. As a result, our trained model, OpenClaw-Skill, exhibits outstanding agentic capabilities in long-horizon planning, tool use and generalization over challenging benchmarks.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2505.10496

CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs

作者:

Raman Dutt↗Pedro Sanchez↗Yongchen Yao↗Steven McDonagh↗Sotirios A. Tsaftaris↗Timothy Hospedales↗

Structured benchmarks have advanced text-conditional image generation for real-world imagery, however, no such benchmark exists for synthetic radiograph generation. Despite being a highly active area of research, existing studies continue adopting inconsistent evaluation protocols and lack a unified assessment of the three most critical criteria: generative fidelity, privacy risk, and downstream utility. To address these limitations, we introduce CheXGenBench, the first unified evaluation framework for synthetic chest radiograph generation that simultaneously assesses fidelity, privacy risks, and downstream utility across frontier text-to-image (T2I) generative models. Our evaluation protocol, comprising over 20 quantitative metrics, covers 11 leading T2I architectures with plug-and-play integration for newer models. Through a rigorous and fair evaluation protocol, we establish comprehensive baseline state-of-the-art (SoTA) performances across all dimensions to guide future research. Furthermore, our results uncover several limitations of current generative models, which include first, even SoTA models struggle with long-tailed medical distributions; second, models pose high privacy risks regardless of fidelity quality; and third, while synthetic data already benefits downstream classification, it is of limited utility for downstream multimodal tasks. Drawing from these results, we propose concrete research directions to advance the field. The code is available at https://github.com/Raman1121/CheXGenBench

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2510.16152

Mapping Scientific Literature with Large Language Models and Topic Modeling

作者:

Mason Smetana↗Lev Khazanovich↗

Scientific literature is increasingly fragmented by disciplinary boundaries, specialized terminology, and potentially sparse keyword systems, making it difficult to capture the evolving structure of modern science. This study introduces a large language model (LLM)-driven framework for mapping scientific literature from a topic modeling perspective. The approach is demonstrated on a 20-year corpus of more than 1,500 engineering-related articles published in the Proceedings of the National Academy of Sciences (PNAS). A two-stage classification pipeline first assigns a primary thematic category to each article based on its abstract, followed by full-text analysis to identify secondary classifications that reveal latent cross-topic connections within the corpus. Unlike conventional topic models, the LLM-based framework produces semantically interpretable topics while maintaining strong quantitative performance. Comparative evaluation against established topic modeling methods shows higher topic diversity and lower overlap with competitive coherence metrics. Manual validation on a randomly sampled subset of abstracts yields an accuracy of 75.9%. Additional traditional natural language processing analyses confirm that the generated topics correspond to meaningful linguistic patterns in the corpus. A bipartite network linking primary and secondary classifications further reveals implicit thematic relationships that are not readily observable through abstracts or keyword systems alone. The findings indicate that the framework independently recovers much of the journal's editorial dual-classification structure without prior knowledge of its schema. Overall, the proposed approach offers a powerful tool for mapping science and identifying emerging cross-topic connections in research.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20538

Multi-Task Bayesian In-Context Learning

作者:

Qingyang Zhu↗Eric Karl Oermann↗Kyunghyun Cho↗

arXiv:2606.20538v1 Announce Type: new Abstract: Bayesian predictive inference provides a principled framework for uncertainty quantification, data efficiency, and robust generalization. However, exact inference is often intractable, and scalable approximations may remain computationally expensive or require restrictive modeling assumptions that degrade predictive performance. Prior-Data Fitted and in-context models have recently emerged as an amortized alternative by learning to map datasets directly to predictive distributions, but existing approaches are tightly coupled to the support of the training prior and lack explicit mechanisms for adapting to new priors at test time, resulting in limited robustness under distribution shift. We introduce a multi-task in-context learning framework for amortized hierarchical Bayesian predictive inference that explicitly represents prior information as a prefix of in-context datasets. A transformer trained on sequences of prior and target tasks learns to adapt its predictions across families of priors. On a suite of evaluations with increasing difficulty, including out-of-meta-distribution priors and priors with high-dimensional latent structures, our method matches oracle Bayesian predictors while being orders of magnitude faster. We further demonstrate its practical relevance on a real-world spatiotemporal temperature prediction benchmark. Code is available at https://github.com/martianmartina/multi-task-bayesian-icl/.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13461

Reinforcement Learning for Neural Model Editing

作者:

Shaivi Malik↗

Editing pretrained neural networks requires specialized algorithms tailored to specific objectives. Designing such algorithms is often time-consuming and demands significant effort. We present an exploratory framework that formulates neural model editing as a reinforcement learning problem, where agents modify models using reward feedback. We introduce two environments: MaskWorld, where agents scale weights multiplicatively, and ShiftWorld, where agents apply additive weight updates. The reward function combines a utility-preservation objective with a task-specific editing objective, enabling agents to learn targeted modifications while maintaining overall model performance. We evaluate the framework on bias mitigation in text classification and machine unlearning in image classification, both of which traditionally rely on specialized algorithms. Our results show that the learned policies reduce forget set accuracy to nearly 0% while preserving over 90% retain set accuracy on the unlearning task. In the bias mitigation setting, the learned policies improve bias-related performance by more than 5% while maintaining general classification utility. Our findings show that neural model editing can be cast as a reinforcement learning problem, allowing editing policies to be learned from reward feedback rather than manually engineered for each task.

阅读与讨论 → 访问原文 →

14.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2511.19302

Quantitative and Optimal Device-Independent Lower Bounds on Detection Efficiency

作者:

Arkaprabha Ghosal↗Soumyadip Patra↗Peter Bierhorst↗

arXiv:2511.19302v2 Announce Type: replace Abstract: This paper examines a quantitative and optimal lower bound on the detector efficiency in a (2,2,2) Bell experiment within a fully device-independent framework, whereby the detectors used in the experiment are uncharacterized. We provide a tight lower bound on the minimum efficiency required to observe a desired Bell-CHSH violation using the Navascués-Pironio-Acín (NPA) hierarchy, confirming tightness up to four decimal places with numerical optimization over explicit quantum realizations. We then introduce the effect of dark counts and demonstrate how to quantify the minimum required efficiency to observe a desired CHSH violation with an increasing dark count error. Finally, to obtain an analytical closed-form expression of the minimum efficiency, we consider the set of no-signaling behaviors that satisfy the Tsirelson bound, which are easier to characterize than the quantum set. Using such behaviors, we find a simple closed-form expression for a lower bound on the minimum efficiency which is monotonically increasing with the CHSH violation, though the analytically obtained lower bounds are meaningfully below the numerically tight lower bound.

阅读与讨论 → 访问原文 →

15.

arXiv (math.PR) 2026-06-18 DOI: arXiv:2606.19075

Random Schrödinger operators on manifolds and abstract bounds for multiplier-type operators

作者:

Jean-Claude Cuenin↗Konstantin Merz↗Eduard Stefanescu↗

arXiv:2606.19075v1 Announce Type: cross Abstract: We study random Schrödinger operators on closed Riemannian manifolds with Anderson-type potentials. We prove high-probability spectral inclusion bounds showing that eigenvalues remain close to those of the Laplacian, with deviations controlled by a norm of the potential coefficients. Compared with deterministic bounds, this yields a square-root cancellation gain. The proof is based on a general principle showing that randomisation improves operator norm bounds for multiplier-type operators, which we formulate in both discrete and continuous settings.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2603.11417

Zero-Shot Cross-City Generalization in End-to-End Autonomous Driving: Self-Supervised versus Supervised Representations

作者:

Fatemeh Naeinian↗Ali Hamza↗Haoran Zhu↗Anna Choromanska↗

End-to-end autonomous driving models are typically trained on multi-city datasets using supervised ImageNet-pretrained backbones, yet their ability to generalize to unseen cities remains largely unexamined. When training and evaluation data are geographically mixed, models may implicitly rely on city-specific cues, masking failure modes that would occur under real-world domain shifts when generalizing to new locations. In this work, we formulate zero-shot cross-city transfer as a controlled representation-level stress test for end-to-end autonomous driving and ask how visual pretraining affects transfer behavior under geographic domain shift. We conduct a comprehensive study by integrating self-supervised backbones I-JEPA, DINOv2, and MAE into planning frameworks. We evaluate performance under strict geographic splits on nuScenes in the open-loop setting and on NAVSIM in the closed-loop evaluation protocol. Our experiments reveal a substantial generalization gap when transferring models across cities with different road topologies, traffic conventions, and visual environments. In open-loop evaluation, a supervised backbone exhibits severe degradation when transferring between cities, yet some domain-specific self-supervised methods can substantially reduce both displacement and collision degradation. In closed-loop evaluation, self-supervised pretraining improves average out-of-distribution PDMS in several single-city training settings. Our results provide empirical evidence that representation learning influences the robustness of cross-city planning and motivate zero-shot geographic transfer as an important stress test for evaluating end-to-end autonomous driving systems.

阅读与讨论 → 访问原文 →

17.

arXiv (math.PR) 2026-06-16 DOI: arXiv:2606.15843

Exponential Convengence of DLRA for SDEs

作者:

Jianhai Bao↗Haitao Wang↗Yue Wu↗

arXiv:2606.15843v1 Announce Type: new Abstract: We study dynamical orthogonal (DO) approximations of stochastic differential equations and investigate their long-time behaviour. The DO formulation represents the solution by a low-rank decomposition and leads to a coupled system consisting of an evolution equation on the Stiefel manifold and a reduced stochastic process. We establish the well-posedness of the strong DO system and derive quantitative error estimates between the original stochastic differential equation and its low-rank approximation in the Wasserstein distance. Our main contribution is the analysis of invariant probability measures for the DO dynamics. Under suitable dissipativity, Lipschitz continuity, and non-degeneracy assumptions on the coefficients, we prove the existence of an invariant probability measure for the strong DO system. The proof combines uniform moment estimates, a Krylov–Bogoliubov argument for an associated frozen system, and a Kakutani-Fan-Glicksberg fixed-point theorem to recover the self-consistent dynamics. We further show that the induced low-rank process admits an invariant probability measure and discuss the structure of invariant measures through several illustrative examples. These results provide a rigorous foundation for the use of dynamical low-rank approximations in the approximation of long-time statistical properties of stochastic dynamical systems.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20512

Probe-and-Refine Tuning of Repository Guidance for Coding Agents

作者:

Asa Shepard↗Jeannie Albrecht↗

arXiv:2606.20512v1 Announce Type: cross Abstract: LLM-based coding agents need higher-level operational knowledge about a repository (which files house which subsystems, how to run the test suite, which workflows have historically led to wrong fixes) that does not exist in the code itself. Engineers typically maintain \texttt{AGENTS.md} files to supply this context as instructions for coding agents, but whether they help is contested: recent studies disagree on whether LLM-generated guidance improves or harms agent performance. In this paper we show that how the guidance is produced is the decisive variable, and introduce probe-and-refine tuning: a procedure that uses synthetic bug-fix probes to iteratively diagnose and patch a repository's guidance file through single-shot LLM calls, with no agent loop or tool use during tuning. On SWE-bench Verified across four independent trials with Qwen3.5-35B-A3B at 200 steps, probe-and-refine achieves 33.0\,\% mean resolve rate vs.\ 28.3\,\% for the static knowledge base used to initialize it and 25.5\,\% for an unguided baseline ($p < 0.001$ for both probe-and-refine contrasts). The improvement comes from coverage rather than precision: refined guidance produces evaluable patches for 14.5 percentage points (pp) more instances while per-patch precision remains statistically constant ($\sim$59\,\%, $p = 0.119$), showing that improved guidance helps agents reach the correct file rather than improving the quality of the changes they make. Further, a step-budget experiment shows that guidance is what lets the agent use a larger step budget productively, and a cross-model experiment with NVIDIA-Nemotron-3-Nano-30B-A3B finds that the tuning loop degrades when the model cannot generate sufficiently diagnostic output, though per-patch precision remains constant even then.

阅读与讨论 → 访问原文 →

19.

bioRxiv (Bioinfo) 2026-06-11 DOI: HASH:f34a6c3c9d1b52daa265c99de17cd612

TifBERT: a self-supervised foundation model for normalization-robust bulk RNA-seq representation learning

作者:

Hosseini↗Sharma↗

Bulk RNA sequencing remains central to translational genomics, yet foundation-model development has largely focused on single-cell data. Existing transformer approaches for bulk RNA-seq often rely on expression discretization, numerical reconstruction, external gene embeddings, or restricted gene sets, limiting robustness across normalization schemes and cohorts. Here, we introduce TifBERT, a self-supervised framework for full-transcriptome bulk RNA-seq representation learning. TifBERT converts each unordered expression profile into a sample-specific gene sequence using term frequency-inverse document frequency (TF-IDF) ordering, prioritizing genes that are both highly expressed within a sample and selectively expressed across the cohort. It is then pretrained using masked gene modeling, predicting gene identities from transcriptomic context rather than reconstructing expression values. Pretrained on harmonized TCGA Pan-Cancer data spanning five RNA-seq normalization schemes, TifBERT learns contextual representations across approximately 10,000 genes without expression binning, landmark-gene restriction, or external biological embeddings. Across 33 TCGA cancer types, TifBERT achieved 90.83% accuracy, 0.996 macro AUC-ROC, and 0.903 MCC. It also captured pathway-level biology, achieving mean sample-wise and pathway-wise Pearson correlations of 0.754 and 0.762 across 1,387 PARADIGM pathway activities. Independent evaluation on GTEx healthy tissues showed preservation of tissue-level transcriptomic structure without retraining. In comparison with existing models, TifBERT achieves competitive subtype discrimination with substantially greater stability and produces markedly richer embedding geometry (effective rank 95.6 versus 6.3), without requiring expression discretization or in-distribution pretraining exposure. Together, TifBERT provides a scalable, normalization-independent foundation model for reusable bulk transcriptomic representation learning

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-25 DOI: arXiv:2606.25059

What Does It Mean to Break a Distillation Defense?

作者:

Lena Libon↗Pura Peetathawatchai↗Michael Aerni↗Daniel Paleka↗Florian Tram\`er↗

arXiv:2606.25059v1 Announce Type: cross Abstract: Black-box LLMs (accessible only via API) are vulnerable to distillation attacks, in which an attacker queries the model and trains a student on its outputs. A recent line of work proposes output perturbation defenses that modify the teacher's output to reduce student performance while preserving utility for legitimate users. As a relatively new family of approaches, output perturbation defenses lack a shared threat model, making it difficult to compare them, reason about composing them with other attacks, or evaluate their robustness against realistic adversaries. This underspecification matters beyond technical evaluation: when defenses are deployed to protect intellectual property or justify regulatory compliance, an imprecise threat model can create a false sense of security. We propose a threat model framework that describes attackers along three dimensions: a query budget, a data budget, and an interface profile that captures how attackers interact with the API. Using antidistillation sampling as a case study, we show that whether the defense is considered effective depends on the assumed threat model. We argue that future work on distillation defenses, along with any governance or policy frameworks built around them, should explicitly specify and stress-test attacker capabilities along our three dimensions.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11520

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories

作者:

Siyuan Luo↗Nairong Zheng↗Lin Zhou↗Tiankuo Yao↗Shengyou Yuan↗Haojia Yu↗Cong Pang↗Jiapeng Luo↗Lewei Lu↗

Training capable OS agents requires data that simultaneously captures structured user intents, multi-turn task delegation, and grounded tool execution–properties absent from existing datasets. We propose ISE (Intent -> Simulate -> Execute), a three-stage synthesis paradigm that addresses these gaps jointly. Stage 1 constructs roughly 50000 structured intents via a 4D framework (Persona x Domain x Task x Complexity); after deduplication the pool contains 43956 unique intents and attains a Vendi Score of 61.57 over the entire pool on mpnet-base-v2 embeddings (cosine kernel, q=1). Stage 2 drives multi-turn user-agent interaction through a role-locked user simulator that grounds each user turn in actual execution outcomes, producing 23132 complete trajectories averaging 8.12 user turns and 68.24 total dialogue turns. Stage 3 runs every tool call inside a live, isolated OS workspace, generating authentic failure-recovery dynamics instead of simulated responses. Fine-tuning on ISETrace improves ClawEval pass@1 from 19.3 to 37.7 using Qwen3-8B on agent tool-use tasks with a standard protocol. This result outperforms zero-shot GPT-4o and the larger Qwen3-32B base model which is four times bigger. An ablation on Stage 2 proves multi-turn simulation brings a large portion of the performance gain. We release all source code and dataset at https://github.com/Valiere01/ISE-Trace.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2606.24832

Difference-Making without Making a Difference

作者:

Sander Beckers↗

arXiv:2606.24832v1 Announce Type: new Abstract: Over a series of seven papers, Andreas & Günther have introduced seven definitions of actual causation and have classified them as belonging to three different, competing, types of accounts: factual difference-making, counterfactual difference-making, and regularity-based. I show that their most recent - factual difference-making - definition instantiates all three types, thereby proving that these are distinctions without a difference. I further compare their novel account to the other six accounts on several crucial examples, revealing that this undermines all seven of their accounts.

阅读与讨论 → 访问原文 →

23.

arXiv (math.PR) 2026-06-24 DOI: arXiv:2506.17496

The Zeta Tail Distribution: A Novel Event-Count Model

作者:

Michael R. Powers↗

arXiv:2506.17496v3 Announce Type: replace-cross Abstract: We introduce the Zeta Tail$\left(a\right)$ probability distribution as a new model for random damage-event counts in risk analysis. Although a natural analogue of the Geometric$\left(p\right)$ distribution, Zeta Tail$\left(a\right)$ has received little attention in the scholarly literature. In the present work, we show this distribution to be reasonably tractable by deriving various fundamental properties, including moments, generating functions, and reliability functions. We then assess its usefulness as an alternative to Geometric$\left(p\right)$, both theoretically and through application to a set of meteorological data. Finally, we discuss conceptual differences between employing the Zeta Tail$\left(a\right)$ model conditionally (i.e., given observed data with certain known characteristics) and unconditionally (i.e., for arbitrary, as yet unobserved data).

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19921

eCNNTO: A Highly Generalizable ConvNet for Accelerating Topology Optimization

作者:

Shengbiao Lu↗Xiaodong Wei↗

arXiv:2606.19921v1 Announce Type: new Abstract: This work proposes an element-based Convolutional Neural Network (CNN) to accelerate density-based Topology Optimization (TO), termed eCNNTO. TO generally undergoes a large number of iterations, where finite element analysis is performed in every iteration, leading to the efficiency bottleneck especially when dense meshes are used to achieve high-resolution designs. To address this limitation, eCNNTO is proposed to build upon Kallioras et al. (2020), where a Deep Belief Network (DBN) was trained for every element to predict its near-optimal density from its early history, thereby skipping the great majority of iterations and significantly accelerating the TO procedure. However, the method lacks spatial correlations among neighboring elements and may lead to disconnected features in the final structure. The proposed method employs CNN with residual connections to address this issue. On top of it, a novel training strategy is introduced to further enhance the optimization efficiency, where the training dataset consists of the final stage density histories rather than early ones. This change can also help reduce the required training data size. eCNNTO requires only a small dataset to train and yet it can be generalized to problems with largely different boundary conditions, loading cases, design domain geometries, mesh resolutions, as well as non-design domains. In the end, the generalization capabilities and efficiency of eCNNTO are demonstrated through a variety of examples in two and three dimensions, achieving up to 90% and 97% reduction of iterations, respectively.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.17451

Credibility-Weighted Pricing of Autonomous Vehicle Liability Under Operational Design Domain Shift

作者:

Doyeon Jang↗

arXiv:2606.17451v1 Announce Type: new Abstract: Automated Driving System deployments create a foundational ratemaking challenge: sparse experience, shifting operational design domains, and non-stationary risk across software releases. We propose a hierarchical Bayesian credibility framework pooling across cities, software versions, and territories via a learned ODD-similarity kernel, nesting Buhlmann-Straub as a limiting case. Demonstrated on 648 verified-engaged Waymo crashes across four U.S. metros from the NHTSA Standing General Order database against 116 million matched miles, city-aggregate credibility weights are moderate (0.12-0.46), partial pooling decisively outperforms no pooling, and a power analysis shows the learned kernel's advantage becomes detectable at approximately twelve deployed cities.

阅读与讨论 → 访问原文 →