探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-22 DOI: HASH:86a8d7e0a2f7d230348d5e26e9add433

Regional Service-System Conditions Associated with Facility-Linked Home-Based Specialist Care in Japan: A Claims-Based Ecological Study of Home Dialysis

作者:

Suzuki↗K. T↗

Background Complex chronic care is increasingly delivered in patients' homes while remaining linked to specialist facilities for training, monitoring, and backup care. Home dialysis provides a useful case because peritoneal dialysis (PD) and home hemodialysis (HHD) share a home-facility delivery structure but differ in technical and operational requirements. This study examined regional service-system conditions associated with the presence and scale of PD and HHD in Japan. Methods This ecological study used publicly available claims, administrative, census, and geospatial data harmonized to 334 Secondary Medical Areas. Regional indicators were organized into four domains: dialysis service delivery, implementation support for home-based care, hospital backup capacity, and living and sociodemographic context. Diffusion was examined using claims-based indicators of regional presence and post-presence scale, analyzed separately for PD and HHD with Firth penalized logistic regression and zero-truncated negative binomial regression, respectively. Results PD was observed in 271 regions and HHD in 109. Patterns of associated regional conditions differed by modality and stage. PD was associated mainly with existing dialysis-service organization, whereas HHD was associated with broader regional supports, including home-care delivery, living infrastructure, transition support, and hospital-system indicators. Conditions associated with presence differed from those associated with scale. Cross-modality associations suggested that shared regional factors may shape the distribution of both modalities. Conclusions Regional conditions for home dialysis diffusion in Japan differed by modality and stage. PD was linked mainly to existing dialysis-service organization, whereas HHD was linked to multi-domain regional support for technically demanding home treatment. Under standardized reimbursement, local service-system capacity may remain important for modality- and stage-specific diffusion of home dialysis.

阅读与讨论 → 访问原文 →

02.

bioRxiv (Bioinfo) 2026-06-20 DOI: HASH:1d1533d50dadea05b1249ee3a67c7593

SAbDab2: The structural antibody database in the age of machine learning

作者:

Capel↗H. L↗Vavourakis↗Williams↗B. H↗Taylor↗C. R↗Deane↗C. M↗

The Structural Antibody Database (SAbDab) is a publicly available repository of experimentally determined antibody structures, first released in 2013. Explicit support for single-domain antibodies was added in 2021, with SAbDab-nano. Recently, increasing interest in antibodies has led to a proliferation of novel antibody formats, while simultaneous advances in machine learning have increased demand for standardised, high-quality structure data. Here, we present SAbDab2, re-engineered for the machine-learning age. It introduces support for a variety of new formats, and makes it easy to retrieve and compare all known structures of a given antibody. In addition, SAbDab2 provides ready access to ML-grade structures of antibody and antibody–antigen-complexes, with standardised, versioned train/test splits. These will be updated every six months going forward, and are available at https://zenodo.org/records/20083995. SAbDab2 itself is updated weekly and is freely available at https://sabdab2.opig.stats.ox.ac.uk.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.13995

Dialogue SWE-Bench: A Benchmark for Dialogue-Driven Coding Agents

作者:

Brendan King↗Jeffrey Flanigan↗

AI coding agents have rapidly transformed software engineering, powering widely used interactive coding assistants. Despite their interactive real-world use, existing benchmarks evaluate them as fully-autonomous systems. In this work, we introduce Dialogue SWE-Bench, an automatic benchmark dataset for evaluating the ability of coding agents to resolve real-world software engineering problems through dialogue with a user. We design a novel, persona-grounded user simulator to support our task evaluation, and augment our task evaluation with automatic evaluations of dialogue quality. We also propose a new schema-guided agent, aimed at improving the dialogue capabilities of off-the-shelf coding agents, which improves over strong baselines by 3-14%. Our results indicate that better coding models do not always correspond to better dialogue models, suggesting that dialogue capability is a distinct and currently understudied dimension of coding agent performance.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16897

Contrastive-Difference CKA Reveals Concept-Specific Structural Alignment Across Language Model Architectures

作者:

Xueping Gao↗

Do different LLM architectures encode high-level concepts in structurally compatible ways? We systematically characterize a geometric-functional universality dissociation: across multiple concept domains and architectural families, moderate geometric convergence coexists with near-perfect functional transfer. Using contrastive-difference CKA (CKA_Delta), a training-free diagnostic that computes kernel alignment on per-sample contrastive differences, we isolate concept-specific convergence from generic similarity – achieving significant discrimination where standard CKA cannot. The dissociation replicates across all six concept domains we test (five with p =70B models. We position CKA_Delta as a practical regime classifier and architectural outlier detector (Gemma: d = 1.08, AUC = 0.79) rather than an absolute transfer-accuracy predictor, providing a training-free diagnostic for cross-architecture concept monitoring.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2603.15952

Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents

作者:

Jacopo Teneggi↗S. M. Bargeen A. Turzo↗Tanya Marwah↗Alberto Bietti↗P. Douglas Renfrew↗Vikram Khipple Mulligan↗Siavash Golkar↗

arXiv:2603.15952v2 Announce Type: replace Abstract: Large language models (LLMs) are capable of emulating reasoning and using tools, creating opportunities for autonomous agents that execute complex scientific tasks. Protein design provides a natural testbed: although machine learning (ML) methods achieve strong results, these are largely restricted to canonical amino acids and narrow objectives, leaving unfilled need for a generalist tool for broad design pipelines. We introduce Agent Rosetta, an LLM agent paired with a structured environment for operating Rosetta, the leading physics-based heteropolymer design software, capable of modeling non-canonical building blocks and geometries. Agent Rosetta iteratively refines designs to achieve user-defined objectives, combining LLM reasoning with Rosetta's generality. We evaluate Agent Rosetta on design with canonical amino acids, matching specialized models and expert baselines, and with non-canonical residues – where ML approaches fail – achieving comparable performance. Critically, prompt engineering alone often fails to generate Rosetta actions, demonstrating that environment design is essential for integrating LLM agents with specialized software. Our results show that properly designed environments enable LLM agents to make scientific software accessible while matching specialized tools and human experts.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12900

Zero-source LLM Hallucination Detection with Human-like Criteria Probing

作者:

Jiahao Yang↗Shuhai Zhang↗Hailong Kang↗Feng Liu↗Qi Chen↗Mingkui Tan↗

Large language models (LLMs) often hallucinate by generating factually incorrect or unfaithful content, posing significant risks to their safe use. Detecting such hallucinations is particularly challenging under the zero-source constraint, where no model internals or external references are available, and detection must rely solely on the textual query-answer pair. In this paper, we propose Human-like Criteria Probing for Hallucination Detection (HCPD), a paradigm that emulates the multi-faceted reasoning of human evaluators. Its core is a Human-like Criteria Probing (HCP) mechanism, in which a LLM agent adaptively decomposes its judgment into a weighted set of interpretable criteria and aggregates criterion-specific scores into a final truthfulness measure. To achieve this adaptive capability, we introduce a reward-based alignment scheme using only weak supervision from semantic consistency. At inference, we employ a multi-sampling aggregation strategy to ensure robust decisions while preserving full interpretability. We further provide theoretical analysis supporting the reliability of our approach. Extensive experiments show that HCPD consistently outperforms state-of-the-art baselines, offering an effective and explainable solution for zero-source hallucination detection. Code is available at https://github.com/TRISKEL10N/HCPD.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18326

Neural Network Implementation of the Renormalization Group for Fault Diagnosis with Class Imbalance

作者:

Evgeny Nikulchev↗Dmitry Ilin↗

arXiv:2606.18326v1 Announce Type: new Abstract: The application of machine learning models in practical tasks faces challenges such as class imbalance and multidimensional noise. This paper proposes RGNet, a neural network architecture based on the concept of the renormalization group (RG), for hierarchical coarse-graining of the feature space. The model sequentially compresses the input dimensionality and concatenates all scales before classification, allowing it to capture both local details and global patterns. The notion of RG-flows is introduced - interpretable low-dimensional representations whose visualization via t-SNE reveals a discrete curvilinear structure confirming the effectiveness of coarse-graining. Experimental results are presented on the imbalanced AI4I dataset. The obtained results demonstrate that RGNet is a universal, interpretable, and competitive solution for fault prediction in applications with imbalanced classes.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.07015

Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation

作者:

Ziyu Zhang↗Chunyu Qiang↗Xiaopeng Wang↗Yuxin Guo↗Kang Yin↗Wenjie Tian↗Jingbin Hu↗Tianlun Zuo↗Zhao Guo↗Teng Ma↗Yuzhe Liang↗Chen Zhang↗…

arXiv:2606.07015v2 Announce Type: replace-cross Abstract: While song generation and singing voice conversion (SVC) have evolved significantly, they have long been developed isolated: the former lacks zero-shot speaker cloning, while the latter overlooks vocal-accompaniment synergy. To bridge this gap, we propose UniSinger, the first end-to-end framework unifying speaker cloning song generation and accompaniment co-generation SVC. Building on the multimodal diffusion transformer, we construct a unified speaker embedding space transferring speaker representation from SVC to song generation, endowing fine-grained cross-task timbre control. To mitigate multi-task optimization conflicts, we design a curriculum learning strategy using task-specific modality masking to guide the model to gradually master the generative mechanisms among semantic content, vocal timbre, and accompaniment. Experiments show state-of-the-art performance on both tasks and realizes complementary benefits, offering new possibilities for intelligent music production.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2604.06802

Riemann-Bench: A Benchmark for Moonshot Mathematics

作者:

Suhaas Garre↗Erik Knutsen↗Sushant Mehta↗Edwin Chen↗

arXiv:2604.06802v2 Announce Type: replace Abstract: Recent AI systems have achieved gold-medal-level performance on the International Mathematical Olympiad, demonstrating remarkable proficiency at competition-style problem solving. However, competition mathematics represents only a narrow slice of mathematical reasoning: problems are drawn from limited domains, require minimal advanced machinery, and can often reward insightful tricks over deep theoretical knowledge. We introduce Riemann-Bench, a private benchmark of expert-curated problems designed to evaluate AI systems on research-level mathematics that goes far beyond the olympiad frontier. Problems are authored by Ivy League mathematics professors, graduate students, and PhD-holding IMO medalists, and routinely took their authors weeks to solve independently. Each problem undergoes double-blind verification by two independent domain experts who must solve the problem from scratch, and yields a unique, closed-form solution assessed by programmatic verifiers. We evaluate frontier models as unconstrained research agents, with full access to coding tools, search, and open-ended reasoning, using an unbiased statistical estimator computed over 100 independent runs per problem. Our results reveal that all frontier models currently score below 10%, exposing a substantial gap between olympiad-level problem solving and genuine research-level mathematical reasoning. By keeping the benchmark fully private, we ensure that measured performance reflects authentic mathematical capability rather than memorization of training data.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11657

Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics

作者:

Katherine Rosenfeld↗Maike Sonnewald↗

arXiv:2606.11657v1 Announce Type: cross Abstract: Generative AI emulators are increasingly used in scientific domains where we already have strong theory, benchmarks, and physical intuition. This raises a central evaluation and interpretability question: when a foundation-style model can reproduce known continuum dynamics, what internal mechanism supports that behavior, is the internal behaviour consistent with known physics, and how does it relate to where the emulator succeeds or fails? We investigate a cross-domain foundation model for continuum dynamics, Walrus by Polymathic, using mechanistic interpretability guided by physical principles. We apply a sparse autoencoder (SAE) to probe a selected layer, and address the practical challenge of triaging a large feature set (over 20,000) using enstrophy as a physically grounded metric. As a deliberately simple testbed, we focus on shear flow and compare feature recruitment across multiple shear-flow setups, i.e. parameter values in the numerical simulation. Across setups we find evidence of piecewise consistency, with subsets of features recurring in similar roles, but this structure is intermittent and does not map cleanly onto standard physical decompositions. In parallel, direct comparisons between numerical simulation and the emulator reveal systematic output-level discrepancies, including regimes where energy/structures become too diffuse or too localized. We connect parts of these discrepancies to changes in specific SAE feature usage. Our work highlights open questions for scientific foundation models: how to robustly prioritize mechanistically meaningful features, how to separate stable structure from analysis artifacts (including single-layer and SAE limitations), and how to use established benchmarks to decide when "different" internal representations are genuinely informative rather than merely effective.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2603.24350

Evidence of an Emergent "Self" in Continual Robot Learning

作者:

Adidev Jhunjhunwala↗Judah Goldfeder↗Hod Lipson↗

arXiv:2603.24350v3 Announce Type: replace-cross Abstract: A key challenge to understanding self-awareness has been a principled way of quantifying whether an intelligent system has a concept of a "self", and if so how to differentiate the "self" from other cognitive structures. We propose that the "self" can be isolated by seeking the invariant portion of cognitive process that changes relatively little compared to more rapidly acquired cognitive skills - because our self is the most persistent aspect of our experiences. We used this principle to analyze the cognitive structure of robots under two conditions: One robot learns a constant task, while a second undergoes continual learning under variable tasks. We find that robots subjected to continual learning develop an invariant subnetwork that is significantly more stable (p < 0.001) compared to the control, and that this subnetwork is also functionally important: preserving it aids adaptation while damaging it impairs performance. We validate this pattern across three different robots spanning locomotion and manipulation.

阅读与讨论 → 访问原文 →

12.

medRxiv (Medicine) 2026-06-15 DOI: HASH:1c5213bf0cfd87aeba8d994cb60b38aa

Instrumental Activities of Daily Living in Older Adults with Epilepsy: A Cross-Sectional and Longitudinal Multicenter Study

作者:

Zawar↗Reyes↗Arrotta↗Hermann↗B. P↗Busch↗R. M↗Quigg↗Kapur↗Struck↗A. F↗Punia↗…

Objective: Instrumental activities of daily living (IADLs) represent a critical but understudied measure of day-to-day function in persons with epilepsy(PWE). In the multicenter Brain Aging and Cognition in Epilepsy (BrACE) study of PWE aged greater than or equal to 55 years, we examined the proportion, clinical correlates, epilepsy-related predictors, and longitudinal trajectory of IADL impairment. Methods: IADLs were assessed using the Functional Activities Questionnaire (FAQ; range=0 to 30; higher=more impaired); a FAQ greater than or equal to 2 defines MCI-level impairment, and a FAQ greater than or equal to 5 defines dementia-level functional impairment. Multivariable logistic regression identified predictors of baseline function. Global cognition (Montreal Cognitive Assessment [MoCA]), individual cognitive measures, and quality of life (QOL) were compared between the impaired and unimpaired groups. Linear regression evaluated predictors of longitudinal functional decline. Results: Of 57 participants (mean age=66.6 years; female=52.6%), 38.6% (n=22) had MCI-level functional impairment and 17.5% (n=10) had dementia-level functional impairment. In univariate analyses, worse FAQ scores were associated with lower education, higher area deprivation index, early-onset epilepsy (EOE less than 60 years), antiseizure medication polytherapy, and epilepsy localization. In multivariable analysis, temporal lobe epilepsy (OR=4.46, 95% CI=1.09, 21.83,p=0.047), EOE(OR=7.14, 95% CI=1.16, 59.97, p=0.046), and lower education(OR=0.70,95% CI=0.49, 0.93, p=0.025) remained independently associated with baseline MCI-level functional-impairment. Lower education (OR=0.55,95% CI=0.29, 0.84, p=0.021) was the only factor associated with dementia-level IADL-impairment. IADL-impaired participants demonstrated lower verbal memory scores (adjusted p=0.041) and MoCA scores (adjusted p

阅读与讨论 → 访问原文 →

13.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2606.13559

Approximate quantum error correction theory of non-isometric codes

作者:

Yixu Wang↗Yijia Xu↗Zi-Wen Liu↗

arXiv:2606.13559v1 Announce Type: new Abstract: Non-isometric encoding arises in various important contexts in quantum error correction, most notably in the finite-energy, non-ideal codewords inevitable in experimental realizations of continuous-variable codes, and holographic quantum gravity. In this work, we present a general and systematic theory of non-isometric quantum error-correcting codes. In particular, we employ the approximate quantum error correction framework to quantitatively study the fundamental limitations imposed by non-isometric encodings on the accuracy of quantum error correction and implementation of logical operations. We apply our theory to analyze GKP and tiger codes under energy constraints, and discuss the implications to holography.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2605.08827

Mental Health AI Safety Claims Must Preserve Temporal Evidence

作者:

Srimonti Dutta↗Ratna Kandala↗

arXiv:2605.08827v2 Announce Type: replace Abstract: The safety of mental health AI is often judged at the wrong temporal scale. Current evaluations typically score isolated responses, endpoint outcomes, or aggregate dialogue quality, while clinically consequential failures may arise from the order and accumulation of interactions themselves, including delayed escalation, repeated reinforcement, dependency formation, failed repair, and gradual deterioration across turns. This paper argues that this mismatch is not merely a limitation of evaluation coverage but a source of invalid safety conclusions. We introduce Temporal Safety Non-Identifiability, a formal account of why safety properties that depend on sequence, timing, accumulation, or recovery cannot be certified by protocols that discard those features. From this formalization, we develop SCOPE (Safety Claims Over Preserved Evidence) as a general principle for aligning safety claims with the evidence an evaluation actually retains, and instantiate it as SCOPE-MH, a mental-health instantiation of this reporting standard. We operationalize SCOPE-MH through a proof-of-concept on the AnnoMI dataset of expert-annotated motivational interviewing conversations, which reveals mechanisms of failure that per-turn behavior scoring does not represent. We propose SCOPE-MH as a diagnostic complement to existing evaluation infrastructure and argue that evaluation preserving temporal evidence is necessary, not optional, for safety-critical mental health AI deployment.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20438

Interpretable Sperm Morphology Classification via Attention-Guided Deep Learning

作者:

Zahra Asghari Varzaneh↗Reza Khoshkangini↗Thomas Ebner↗Lars Johansson↗

arXiv:2606.20438v1 Announce Type: new Abstract: Male infertility is a major cause of couple infertility, often linked to abnormal sperm morphology. While deep learning models offer automated analysis, most lack interpretability, limiting their clinical adoption. This study proposes an attention-guided deep learning framework for sperm morphology classification. We combine a pretrained EfficientNet-B0 with a Convolutional Block Attention Module (CBAM) to focus on key areas of the sperm head, improving both accuracy and interpretability. Evaluated on the SMIDS and HuSHem public datasets, our model achieves accuracies of 90.2% and 93.9% (macro F1 scores of 0.913 and 0.948), outperforming SimpleCNN and standard EfficientNet-B0. Furthermore, we use Grad-CAM++ visualizations to highlight features influencing the model's decisions. The results demonstrate that this accurate and transparent framework is a practical tool for automated sperm analysis in fertility clinics.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14235

Implicit Variational Rejection Sampling

作者:

Jian Xu↗Shigui Li↗Wei Chen↗Jiacheng Li↗Zhiqi Lin↗Delu Zeng↗Xinghao Ding↗John Paisley↗Qibin Zhao↗

arXiv:2606.14235v1 Announce Type: new Abstract: Variational Inference (VI) is a fundamental inference technique in Bayesian machine learning for approximating complex posterior distributions. Traditional VI often relies on the mean-field factorization, which can inadequately capture true posterior complexity. Recent advancements have leveraged neural networks to model implicit distributions, offering increased flexibility. However, the practical constraints of neural network architectures still produces inaccuracies. In this paper, we propose a method called Implicit Variational Rejection Sampling (IVRS), which integrates implicit distributions with rejection sampling to improve the posterior approximation. Our method uses neural networks to construct implicit proposal distributions, and rejection sampling with a discriminator network that estimates the density ratio between the implicit proposal and the true posterior for refining the approximation. Towards this end, we introduce the Implicit Resampling Evidence Lower Bound (IR-ELBO) as a metric to characterize the resampled distribution's quality and derive a tighter variational lower bound. Experimental results demonstrate that our method outperforms traditional variational inference techniques.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2604.14892

Can LLMs Accurately Score Medical Diagnoses and Clinical Reasoning?

作者:

Amy Rouillard↗Sitwala Mundia↗Linda Camara↗Ziyaad Dangor↗Michael Cameron Gramanie↗Ismail Kalla↗Shabir A. Madhi↗Kajal Morar↗Marlvin T. Ncube↗Haroon Saloojee↗Bruce A. Bassett↗

arXiv:2604.14892v3 Announce Type: replace-cross Abstract: Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large language models (LLMs) as alternative adjudicators. Here, we evaluate an LLM Jury, composed of three frontier AI models, for scoring 3334 diagnoses on 300 real-world low- and middle-income country (LMIC) hospital cases. Both LLM- and clinician-generated diagnoses are scored against expert panel diagnoses across four dimensions: diagnosis, differential diagnosis, clinical reasoning, and negative treatment risk. The LLM Jury scores are compared with expert and independent re-scoring panel scores to assess error metrics, inter-rater agreement, severe-risk errors, and the effect of post hoc calibration using isotonic regression. In our data, we find that: (i) the uncalibrated LLM Jury scores preserve ordinal agreement with the expert clinician panel scores, but are systematically lower; (ii) the probability of severe-risk errors is lower for the LLM Jury than the human expert re-score panels; (iii) the LLM Jury combined with LLM diagnoses can be used to identify diagnoses at high risk of error, enabling targeted expert review and improved panel efficiency; (iv) the calibrated LLM Jury scores and rankings of diagnosing agents show excellent agreement with those of the primary expert panels; (v) LLM Jury models show no self-preference bias, they did not score diagnoses generated by their own underlying model or models from the same vendor more (or less) favourably than those generated by other models. Together, these results provide evidence that a calibrated LLM Jury is a trustworthy and reliable proxy for expert clinician evaluation in medical AI benchmarking. Confirming these findings in other clinical settings is an important direction for future work.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12709

Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows

作者:

Timothy McAllister↗Sina Abdidizaji↗Ivan Garibay↗Ozlem Ozmen Garibay↗

arXiv:2606.12709v1 Announce Type: cross Abstract: As LLM-based multi-agent systems (MAS) are deployed in the wild, the resilience of their collaboration structures against adversarial compromise becomes a critical safety concern. Attackers may leverage prompt-injection or jailbreaking to sabotage individual agents within MAS workflows, but the interaction between model scaling and system-level resilience remains poorly understood. This paper investigates how model scale affects the security of linear multi-agent workflows. Our experiments across scales of two open-weight model families on the HumanEval benchmark reveal a compliance-correction symmetry: larger models are far more likely to faithfully execute malicious instructions, with the control-to-malicious performance drop reaching 53.7pp at 27B in uncorrected pipelines. However, appending a lightweight terminal Fixer stage collapses this to 0.6pp and restores statistical parity with control-level performance, demonstrating that strictly linear collaboration structures can be viable and resilient to adversaries at this scale, and suggesting that the brittleness previously attributed to linear topology may stem from a lack of correction.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2510.03520

Certifiable Safe RLHF: Semantic Grounding and Fixed Penalty Constraint Optimization for Safer LLM Alignment

作者:

Kartik Pandit↗Sourav Ganguly↗Arnesh Banerjee↗Shaahin Angizi↗Arnob Ghosh↗

arXiv:2510.03520v2 Announce Type: replace-cross Abstract: Ensuring safety is a foundational requirement for large language models (LLMs). Achieving an appropriate balance between enhancing the utility of model outputs and mitigating their potential for harm is a complex and persistent challenge. Contemporary approaches frequently formalize this problem within the framework of Constrained Markov Decision Processes (CMDPs) and employ established CMDP optimization techniques. However, these methods exhibit two notable limitations. First, their reliance on reward and cost functions renders performance highly sensitive to the underlying scoring mechanism, which must capture semantic meaning rather than being triggered by superficial keywords. Second, CMDP-based training entails tuning dual-variable, a process that is both computationally expensive and does not provide any provable safety guarantee for a fixed dual variable that can be exploitable through adversarial jailbreaks. To overcome these limitations, we introduce Certifiable Safe-RLHF (CS-RLHF) that introduces a cost model trained on a large-scale corpus to assign semantically grounded safety scores. In contrast to the lagrangian-based approach, CS-RLHF adopts a rectified penalty-based formulation. This design draws on the theory of exact penalty functions in constrained optimization, wherein constraint satisfaction is enforced directly through a suitably chosen penalty term. With an appropriately scaled penalty, feasibility of the safety constraints can be guaranteed at the optimizer, eliminating the need for dual-variable updates. Empirical evaluation demonstrates that CS-RLHF outperforms state-of-the-art LLM model responses rendering at-least 5 times efficient against nominal and jail-breaking prompts

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16111

Towards Pareto-Optimal Tool-Integrated Agents with Pareto Ranking Policy Optimization

作者:

Junyi Li↗Xiaowei Qian↗Yingyi Zhang↗Wenlin Zhang↗Guojing Li↗Sheng Zhang↗Xiao Han↗Yichao Wang↗Xiangyu Zhao↗

Recent advances in tool-integrated language agents have significantly improved their ability to solve complex reasoning tasks. However, existing alignment methods predominantly focus on maximizing task accuracy, while overlooking auxiliary objectives such as tool-use efficiency, which are essential for practical deployment. To address this gap, we introduce ParetoPO, a two-stage multi-objective optimization framework for aligning tool-using large language models (LLMs) under competing objectives. In the first stage, ParetoPO leverages hypervolume-guided dynamic scalarization to adapt reward weights based on global Pareto frontier progress. In the second stage, it replaces scalarized learning signals with Pareto-ranking-based advantage computation, promoting nondominated trajectories through dominance-aware credit assignment. This design enables fine-grained, action-level optimization across multiple conflicting objectives. Experimental results on mathematic reasoning and multi-hop QA tasks show that ParetoPO consistently discovers policies with superior accuracy-efficiency trade-offs compared to static and heuristic baselines.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14200

When Should Agent Trust Be Conditional? Characterizing and Attacking Skill-Conditional Reputation in Agent Swarms

作者:

Yihan Xia↗Taotao Wang↗

arXiv:2606.14200v1 Announce Type: new Abstract: Open platforms increasingly route tasks among heterogeneous LLM agents–differing in base model, scaffold, and tool stack–whose competence varies sharply by skill: an agent excellent at one skill may be useless at another. The standard reputation approach summarizes each agent by a single global trust score, but that scalar is the wrong object here, because routing every task to the globally most-trusted agent leaves the value of specialization unclaimed. We study skill-conditional trust R(i | k)–the trust to place in agent i for a task requiring skill k, rather than one score per agent–and pose three falsifiable questions: when is conditioning worth it, how much cross-skill evidence should be borrowed, and whether that borrowing is safe. A controlled phase-diagram analysis answers the first two: conditional trust wins only in a specific regime–high agent heterogeneity, sparse per-skill evidence, and correlated skills–and the coupling strength beta that buys this data efficiency is dual-use, because the same cross-skill borrowing is also a laundering channel. On a public benchmark of 14 genuinely heterogeneous AppWorld agents, real pools land inside the beneficial regime–a small but genuine gain, with the per-skill best agent genuinely changing across skills. We then show that an attacker with cheap evidence in one skill and none in a target skill hijacks the conditional router, driving routing regret from 0 to 0.94 on a pool our zero-cost Conditional Information Value Test (CIVT) rates GREEN–while the ungated trust verdict it contaminates reads -0.06 instead of the honest +0.19. A zero-evidence gate bounds the attack but does not eliminate it; we characterize the residual cost under an explicit budget. We do not claim Sybil-resistance–we quantify the trade-off.

阅读与讨论 → 访问原文 →

22.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2601.08392

On-chip semi-device-independent quantum random number generator exploiting contextuality

作者:

Maddalena Genzini↗Caterina Vigliar↗Mujtaba Zahidy↗Hamid Tebyanian↗Andrzej Gajda↗Klaus Petermann↗Lars Zimmermann↗Davide Bacco↗Francesco Da Ros↗

arXiv:2601.08392v2 Announce Type: replace Abstract: We present a semi-device-independent quantum random number generator (QRNG) based on the violation of a contextuality inequality, implemented by the integration of two silicon photonic chips. Our system combines a heralded single-photon source with a reconfigurable interferometric mesh to implement qutrit state preparation, transformations, and measurements suitable for testing a KCBS contextuality inequality. This architecture enables the generation of random numbers from the intrinsic randomness of single-photon interference in a complex optical network, while simultaneously allowing a quantitative certification of their security without requiring entanglement. We observe a contextuality violation exceeding the classical bound by more than 10{\sigma}, unambiguously confirming non-classical behavior. From this violation, we certify a conditional min-entropy per experimental round of Hmin = 0.077 +- 0.002, derived via a tailored semidefinite-programming-based security analysis. Each measurement outcome therefore contains at least 0.077 +- 0.002 bits of extractable genuine randomness, corresponding to an asymptotic generation rate of 21.7 +- 0.5 bits/s. These results establish a viable route towards general-purpose, untrusted quantum random number generators compatible with practical integrated photonic quantum networks.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19700

TerraMARS: A Domain-Adapted Small-Language-Model Pipeline for Mars Terraforming Literature

作者:

Jyotsna Singh↗Ash Black↗Jeff Larsen↗Scott R. Saleska↗

Researchers are interested in learning about Mars so that it may eventually become habitable for humans. To achieve this, there is a need for comprehensive knowledge of the planet's atmosphere, hydrology, surface chemistry, radiation environment, and spatial features through the scientific literature. These contain valuable information and meaningful quantitative constraints that can be used in other models and studies, such as habitability assessment and future terraforming studies. We present TerraMARS, an end-to-end information extraction pipeline that combines a domain-adapted Small Language Model to answer Mars terraforming-related questions and convert unstructured Mars science text into machine-readable structured outputs in JavaScript Object Notation (JSON) format. A corpus of open-access papers is collected and processed using a multistage retrieval and chunking framework. Google Gemma 3 1B was adapted to the domain using Quantized Low-Rank Adaptation (QLoRA) fine-tuning on Mars-specific question-answering and information extraction datasets. The resulting pipeline generates both types of output and provides a foundation for integrating knowledge from scientific literature into downstream applications like digital twins and habitability modeling for Mars. The output from this pipeline looks promising, but further improvements are needed to increase extraction accuracy and factual consistency.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.13799

The Program Is Still There: A Conservation Law for Program Discovery

作者:

Jorge Miguel Silva↗

arXiv:2606.13799v1 Announce Type: cross Abstract: Finding the shortest program that generates a sequence is uncomputable, and for six decades that fact has been mistaken for a wall around finding any generating program. It is not a wall but a price, and this paper measures it. For every algorithm that learns about a candidate program only through its score, a class spanning Levin search, evolutionary methods, simulated annealing, and the cross-entropy method, we define the coupling width of a search problem and prove an unconditional worst-case lower bound, exponential in that width with base one less than the domain size. From it follows a conservation law: structural knowledge injected into a search trades one for one against the search it removes, and their sum can never fall below the length of the program sought. Levin's 1973 upper bound and the lower bound proved here are the two ends of one conserved quantity, closing on each other as the instruction set grows. The only escape is to read a candidate's structure rather than its score, and its price, which we prove for generic targets, is incompleteness. A deterministic engine built on this theory recovers a generating program, certified by compressing its data and predicting an unseen continuation, for 2,383 of 3,914 sequences across four independent populations, including 244 of the 256 elementary cellular automata, with measured discovery cost rising along program length more than an order of magnitude inside the score-oracle worst case.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20493

Contagion Networks: Evaluator Bias Propagation in Multi-Agent LLM Systems

作者:

Zewen Liu↗

arXiv:2606.20493v1 Announce Type: cross Abstract: When large language models serve as evaluators in multi-agent systems, their systematic evaluation biases propagate through the agent network. We introduce Contagion Networks, a formal framework for measuring how evaluator biases spread across interacting LLM agents. In a controlled 3-agent experiment using DeepSeek-chat with three distinct evaluator bias profiles (structured, balanced, evidence-based), we measure the Cross-Agent Contagion Matrix Gamma_3 and find that evaluator biases consistently propagate between agents (gamma in [0.157, 0.352]), even within the same underlying model. We identify three propagation regimes governed by the spectral radius rho(Gamma_N), and demonstrate that homogeneous-model agents produce contagion coefficients 3-5x weaker than cross-model coefficients observed in prior work (MM-EPC: gamma approx 0.85-1.3), placing them in the suppression regime. We show that increasing evaluator committee size from k=1 to k=3 reduces effective contagion by 72.4%, providing an actionable mitigation strategy. We release the open-source Contagion Network experimental framework.

阅读与讨论 → 访问原文 →