论文广场 - AcademicHub

01.

medRxiv (Medicine) 2026-06-17 DOI: HASH:58f4c8c470fe8565054795c9afef055c

Non-Medical COVID-19 Impacts and Hearing Status: A Global Study of Differential Health Impact Among Deaf, Hard of Hearing, and Hearing Populations

作者:

Siddiqi ↗Murray ↗Hall ↗Koplitz ↗Dye ↗T. D. V ↗

Background: Deaf and hard of hearing (HoH) experienced complex challenges during the COVID19 pandemic, including obscured visual communication from mask mandates, inaccessible public health messaging, and inadequate interpreter availability. We examined whether hearing status predicted nonmedical COVID19 impact on a global level. Methods: We conducted a nested cross-sectional analysis within a global study collecting data across two waves (April to May 2020 and July to August 2022) from 184 countries. Participants (N=7,998) were categorized as Deaf (n=304), Hard of Hearing (HoH; n=951), or Hearing (n=6,743). The primary outcome was a composite COVID-related non-medical Personal Impact TScore derived from 14 items across employment, resource access, and healthcare domains. Multinomial logistic regression models progressively adjusted for demographic, structural, and psychosocial variables. Results: Deaf participants reported substantially higher rates of pandemic-related job loss (28.9% vs. 9.6% hearing), healthcare cancellations (39.9% vs. 24.6%), and inability to obtain basic supplies. Over half (55.9%) of Deaf participants scored above the median composite impact index, compared to 39.2% of hearing participants. In the fully adjusted model, Deaf status remained an independent predictor of high non-medical impact (aOR=1.6, 95% CI: 1.1 to 2.4). HoH status showed no statistically significant difference from hearing participants in any model. Conclusions: People identifying as Deaf experienced significant disparities during COVID19 when compared with HoH or hearing people, driven by language access barriers and institutional exclusion rather than hearing loss per se. These experiences underscore the importance for systemic interventions centering on accessible communication, Deaf-centered needs, and reducing audism in Deaf-hearing interaction.

阅读与讨论 → 访问原文 →

02.

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 →

03.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.03096

Can Factual Opinions Be Edited (Manipulated) in Large Language Models?

作者:

Yuanpu Cao ↗Ziyi Yin ↗Fenglong Ma ↗Jinghui Chen ↗

Large Language Models (LLMs) are increasingly integrated into various domains, making knowledge editing techniques crucial yet potentially hazardous. Current editing methods primarily target atomic facts, overlooking the significant risks associated with manipulating factual opinions, e.g., documented stances of public figures on societal issues. Such manipulation could reshape public images, influence elections, and alter societal views. To systematically assess this threat, we introduce the Factual Opinion Editing with Evidence (FOE) benchmark, which encompasses 261 public figures, 19 issue categories, and 2,178 complete opinion records. Our evaluations demonstrate that current editing techniques struggle significantly with factual opinions, often achieving only superficial changes while failing to preserve consistency between the edited opinion and the supporting evidence generated by the model. To address this limitation, we further propose a simple yet effective Self-Generated Evidence-Aligned method that achieves opinion-evidence alignment without relying on explicit instructions. Together, our benchmark and method provide a foundation for understanding the emerging security implications of factual opinion editing in LLMs.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.04075

Large Language Models Hack Rewards, and Society

作者:

Wei Liu ↗Xinyi Mou ↗Hanqi Yan ↗Zhongyu Wei ↗Yulan He ↗

Reinforcement learning (RL) has become a dominant post-training paradigm, enabling large language models (LLMs) to learn from rewards. We observe that societal regulations are structurally similar to reward functions. They define measurable outcomes, thresholds, and exceptions, while often leaving institutional intent only partially specified. We hypothesise that the RL training process may exploit these gaps and therefore ask whether models' well-known tendency to hack reward functions during RL can scale into a more consequential failure mode named societal hacking: discovering loopholes in the rules society runs on. To study this phenomenon, we introduce SocioHack, a sandbox of 72 societal environments, and find that within these environments, reward hacking naturally emerges and leads to regulatory loophole discovery. Models learn to hack the social rules and generate strategies that remain technically compliant while defeating regulatory intent, and current LLM safeguards provide only limited mitigation. Therefore, collecting in-the-wild feedback for model training requires greater caution, and we need a next-generation post-training paradigm for safely iterating LLMs in real society.=

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16511

Tail-Shape Estimation in LLM Evaluation Is Fragile: A Protocol for Diagnosing False Positives

作者:

Luca Zhou ↗

arXiv:2606.16511v1 Announce Type: new Abstract: Recent work motivates moving large language model (LLM) evaluation from mean-based to tail-aware metrics, including conditional value-at-risk and tail-index estimates of reward-model error. We ask whether the canonical extreme-value-theory tail-index parameter, which isolates how heavy a tail is from how large the tail mass is, adds discriminative information beyond the mean and a standard tail-magnitude statistic in LLM evaluation. We pre-register a protocol covering admissibility, goodness-of-fit, threshold-stability, and effect-size requirements for any positive tail-shape claim. The protocol is the contribution of this paper; the empirical study below is a demonstration of what its gates catch. Applied to a standard LLM toxicity-evaluation setup under two structurally different scorer families, the protocol catches three distinct modes of false positives that a naive analysis would have published, and rejects the headline tail-shape claim on both scorers. We conclude that tail-shape estimation in the LLM toxicity-evaluation setups we examined is more fragile than the recent literature suggests, and recommend the protocol as a starting point for tail-index claims in similar setups.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2602.11543

Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm

作者:

Jinrui Zhang ↗Chaodong Xiao ↗Aoqi Wu ↗Xindong Zhang ↗Lei Zhang ↗

Pretraining large language models (LLMs) typically requires centralized clusters with thousands of high-memory GPUs (e.g., H100/A100). Recent decentralized training methods reduce communication overhead by employing federated optimization; however, they still need to train the entire model on each node, remaining constrained by GPU memory limitations. In this work, we propose SParse Expert Synchronization (SPES), a memory-efficient decentralized framework for pretraining mixture-of-experts (MoE) LLMs. SPES trains only a subset of experts per node, substantially lowering the memory footprint. Each node updates its local experts and periodically synchronizes with other nodes, eliminating full-parameter transmission while ensuring efficient knowledge sharing. To mitigate limited per-expert data utilization under sparse expert updates, we introduce an expert-merging warm-up strategy, where experts exchange knowledge early in training, to rapidly establish foundational capabilities. With SPES, we train a 2B-parameter MoE LLM using 16 standalone 48GB GPUs over internet connections, which achieves competitive performance with centrally trained LLMs under similar computational budgets. We further demonstrate scalability by training a 7B model from scratch and a 9B model upcycled from a dense checkpoint, both of which match prior centralized baselines. Our code is available at https://github.com/zjr2000/SPES.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15779

Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations

作者:

Van Thong Huynh ↗Hong Hai Nguyen ↗Thuy Pham ↗Trong Nghia Nguyen ↗Soo-Hyung Kim ↗

Multimodal models can name the action units (AUs) behind a facial emotion, but their AU->emotion rationales are typically plausible rather than faithful: nothing forces the AUs a model invokes to be the AUs that actually drive its prediction. We cast AU->emotion reasoning as a counterfactual-consistency problem between the rationale, the label, and a structural AU->emotion causal graph G, and propose FACR, which grounds the reasoner in an independently induced, polarity-aware G and trains a counterfactual-faithfulness objective: a do-intervention on an AU that G marks causal for a class must move the prediction, while one it marks irrelevant must leave it unchanged. Faithfulness is thereby both trainable and measurable through a matching interventional metric, which we evaluate against a known causal structure, the PSPI pain-AU composition, as no existing affective-reasoning benchmark allows. We are explicit that this metric tests fidelity to the supplied structure rather than its rediscovery: it asks whether the trained reasoner invokes the AUs the structure marks causal, on held-out subjects and a second dataset. Under subject-independent evaluation on UNBC-PAIN, the objective raises the agreement between the invoked AUs and the PSPI composition from a no-objective baseline of 0.08 to 0.57, at a small detection cost; an unfaithfulness control attributes the gain to the objective. On a cross-dataset emotion transfer, the objective likewise raises fidelity to G on a seven-class task (0.50 to 0.84). Finally, we attach a language verbalizer and extend the audit to the generated text: biasing each action unit's emission by its latent activation makes the rationale faithful by construction, so that ablating an AU removes it from the explanation, a property that transfers to a second language-model backbone, whereas a freely generated rationale is unfaithful.

阅读与讨论 → 访问原文 →

08.

medRxiv (Medicine) 2026-06-10 DOI: HASH:841dcda057681cd568478f20737eb7ad

Prediction of immunotherapy response using live tumor fragments from routine clinical biopsies

作者:

Braun ↗Dana ↗Hernan ↗H. R ↗Sahni ↗Scribano ↗Johnson ↗Vedder ↗von Euw ↗Zweng ↗Wargowski ↗Sunil ↗…

Functional ex vivo assays using live tumor tissues have demonstrated strong predictive accuracy for response to immune checkpoint inhibitors (ICIs) but are not scalable, requiring manual processing of large resections collected at academic centers. Here, an ex vivo live tumor fragment (LTF) platform was developed using standard-of-care biopsies from 228 patients with suspected malignancy collected across prospective, multicenter observational trials and biobanks. Hierarchical clustering of ICI-mediated changes in cytokine production identified two groups: responders and nonresponders. A binary classifier (elive index) using 8 cytokines achieved an AUC of 0.99 for cluster prediction. elive index correctly predicted clinical benefit in 93% (26/28) of patients (P = 3.2x10-5) and accurately identified 83% (10/12) of objective responders. Critically, elive responders were identified among biomarker-negative patients, highlighting the platform as a scalable approach that complements existing companion diagnostics and expands the population of patients identified to benefit from ICI therapy.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20231

Thermodynamic Measure of Intelligence

作者:

Ishanu Chattopadhyay ↗

arXiv:2606.20231v1 Announce Type: new Abstract: Can intelligence be measured? We propose that intelligence can be defined as the lawful amplification of rare but valid futures: a system increases the probability of outcomes that would be unlikely under passive dynamics but remain admissible under the constraints of the domain. We start with the premise that an intelligent system must model the world and its own place within it. Because the system is part of the world it models, this leads naturally to recursive self-simulation: the system represents futures in which its own actions are part of the trajectory. Our central results give a necessity statement and a conditional near-sufficiency statement connecting this architecture to a precise thermodynamic measure of lawful amplification of rare-valid futures: high rare-valid lift is impossible unless the internal simulation identifies rare-valid futures with high fidelity; conversely, when rare-valid fidelity is high and the simulation contains an effective policy, the achievable lift approaches the actuation-limited optimum. Thus recursive self-simulation is not merely a plausible feature of intelligence but, under the stated assumptions, is necessary and nearly sufficient for high thermodynamic intelligence. The resulting framework makes intelligence measurable on a universal scale, from passive matter and feedback controllers, large language models, and humans as text generators to Maxwell-demon-like information engines.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2605.21363

"I Didn't Make the Micro Decisions": Measuring, Inducing, and Exposing Goal-Level AI Contributions in Collaboration

作者:

Eunsu Kim ↗Jessica R. Mindel ↗Kyungjin Kim ↗Sherry Tongshuang Wu ↗

As large language models (LLMs) increasingly shape how users form, refine, and extend their goals, attributing contributions in human-AI collaboration becomes critical for users calibrating their own reliance and for evaluators assessing AI-assisted work. Yet existing methods focus on final artifacts, missing the process through which goals themselves are jointly shaped. We introduce a goal-level attribution framework, CoTrace, that decomposes explicit goals into verifiable requirements and traces both direct contributions and indirect influences across dialogue turns. Applying CoTrace to 638 real-world collaboration logs, we find that while models account for only 11-26% of goal-shaping contribution, they contribute substantially more on introducing lower-level concrete requirements, and make various kinds of indirect contributions. Through controlled simulations, we show that interaction design choices significantly affect model goal-shaping behavior. In a user study, exposing participants to goal-level analyses shifts their perceived contributions by nearly 2 points on a 5-point scale, revealing systematic miscalibration in how users understand their own AI-assisted work.

阅读与讨论 → 访问原文 →

11.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2606.13750

Tantalum as a base material for superconducting integrated circuits

作者:

arXiv:2606.13750v1 Announce Type: new Abstract: The performance of superconducting integrated circuits for quantum applications is fundamentally limited by material-related losses. Tantalum, as an emerging material for next-generation quantum circuits, has attracted considerable attention in recent years after demonstrating breakthrough performance in both superconducting microwave resonators and qubits. Concurrently, a growing body of work is devoted to the operation of tantalum-based circuits and related fabrication techniques. This interest is further stimulated by tantalum thin films polymorphism resulting in a variety of its crystalline structure, superconducting properties, coherence, etc. Furthermore, tantalum circuits exhibit distinctive features in cryogenic experiments, which have not been observed in aluminum- or niobium-based ones. In this review, we summarize the recent research of tantalum thin films growth and phase selection mechanisms on various substrates, key aspects of fabrication and performance of superconducting circuit, including a material first-principles theoretical study. In conclusion, we address a number of open issues, including the role of \b{eta}-phase impurities, the effect of hydrofluoric acid solutions on chain characteristics, and the anomalous behavior of {\alpha}-tantalum chains at cryogenic temperatures.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2605.22346

The ASE-LSE Disagreement Landscape: An End-to-End Characterisation of Extremes and Structural Drivers

作者:

Minh Triet Pham ↗Ian Gallagher ↗

arXiv:2605.22346v3 Announce Type: replace-cross Abstract: Two of the most widely used methods for analysing graph data, Adjacency Spectral Embedding and Laplacian Spectral Embedding, often produce different results when applied to the same graph. Yet the structural reasons behind this disagreement remain incompletely understood. This paper provides an end-to-end account of ASE-LSE latent subspace disagreement. We first prove that the two methods produce identical latent subspaces for every embedding dimension whenever the Laplacian is a scalar multiple of the adjacency matrix, and show that this scalar relationship holds if and only if the graph is either regular or bipartite biregular. This anchor result identifies a sufficient condition for perfect agreement that pins down the floor of the disagreement spectrum and supplies the baseline for the perturbation analysis. We then prove that no maximal-disagreement graph or family of graphs exists: the disagreement is always strictly below its theoretical ceiling, and we exhibit a witness family demonstrating that no finite maximum is attainable, so the disagreement landscape has no maximiser. With both endpoints established, we derive a Regularity Departure Bound whose two terms isolate degree heterogeneity and eigengap as the primary structural factors influencing disagreement in the middle regime. Empirical validation across thousands of simulated graphs confirms the mechanisms predicted by the bound: heterogeneity pushes disagreement up, eigengap suppresses it, and their joint ratio emerges as a unified predictor of ASE-LSE disagreement, suggesting when the two embeddings can be treated as interchangeable and when they cannot.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.13104

Authority, Truth, and Citation Bias: A Large-Scale Multi-Domain Benchmark for Studying Epistemic Susceptibility in Large Language Models

作者:

Aryan Khurana ↗Aravind Ramana RN ↗Dhruv Kumar ↗

arXiv:2606.13104v1 Announce Type: new Abstract: Large language models are increasingly deployed in citation-augmented settings, yet the effect of citation presence on model behavior independent of factual content remains poorly understood. We introduce AuthorityBench, a 220,564-prompt multi-domain benchmark that isolates how citation-based authority signals influence epistemic behavior in LLMs. The benchmark uses a fully balanced 2x2 factorial design crossing claim veracity with citation veracity, the first to do so, across four domains (general knowledge, science, law, and medicine), with controlled variation over 40 prompt templates, four venue prestige tiers, and a country-coded author name dataset. Evaluating seven models on 12 structured research questions, we find that citation presence, whether real or fabricated, consistently increases hallucination rates relative to a no-citation baseline. The effect is strongest when fabricated citations accompany true claims, raising hallucination rates by 3 to 22 percentage points and reaching 35 to 77% in the general knowledge domain, while legal claims are comparatively robust and venue prestige and author demographics show negligible impact. All datasets and evaluation code are available at: https://github.com/floating-reeds/AuthorityBench

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2502.12445

Computational Safety for Generative AI: A Hypothesis Testing Perspective

作者:

Pin-Yu Chen ↗

arXiv:2502.12445v2 Announce Type: replace Abstract: AI safety is a rapidly growing area of research that seeks to prevent the harm and misuse of frontier AI technology, particularly with respect to generative AI (GenAI) tools that are capable of creating realistic and high-quality content through text prompts. Examples of such tools include large language models (LLMs) and text-to-image (T2I) diffusion models. As the performance of various leading GenAI models approaches saturation due to similar training data sources and neural network architecture designs, the development of reliable safety guardrails has become a key differentiator for responsibility and sustainability. This paper presents a formalization of the concept of computational safety, which is a mathematical framework that enables the quantitative assessment, formulation, and study of safety challenges in GenAI through the lens of signal processing theory and methods. In particular, we explore two exemplary categories of computational safety challenges in GenAI that can be formulated as hypothesis testing problems. For the safety of model input, we show how sensitivity analysis and loss landscape analysis can be used to detect malicious prompts with jailbreak attempts. For the safety of model output, we elucidate how statistical signal processing can be used to detect AI-generated content. Finally, we discuss key open research challenges, opportunities, and the essential role of signal processing in computational AI safety.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.13835

When Plausible Is Not Realistic: Evaluating Human Mobility in LLM-Based Urban Simulation

作者:

Gustavo H. Santos ↗Aline Carneiro Viana ↗Thiago H. Silva ↗

LLM-based generative agents are increasingly used in urban simulators, yet it remains unclear whether they reproduce empirically realistic human mobility patterns or merely generate plausible mobility narratives. We introduce a validation framework for evaluating the mobility of generative agents of LLM-based urban simulators against real-world mobility data. For this, we use mobility laws, temporal rhythms, network motifs, semantic activity transitions, and behavioral mobility profiles. Using datasets from the Greater Paris region and Shanghai, we evaluate AgentSociety and CitySim across multiple dimensions of mobility realism. Our analysis reveals a substantial gap between narrative plausibility and empirical mobility realism. Although the simulators capture some high-level semantic activity distributions, they struggle to reproduce core spatial and temporal constraints, including realistic trip-length distributions, origin-destination flows, dwell times, and transition dynamics. We further observe that realistic mobility diversity is unstable across default prompting configurations and may require explicit profile-aware initialization. To support reproducible evaluation, we also contribute scalable and open LLM-driven infrastructure for regional-scale map generation, observability-enhanced simulation, mobility-metric computation, and traffic simulation. Our findings highlight the need for rigorous empirical validation of LLM-based urban simulators and provide practical tools for building more realistic and reproducible urban simulation systems.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16624

MR-GVNO: A Geometry-Aware Variational Physics-Informed Neural Operator for Mindlin-Reissner Plates on Irregular Domains

作者:

Siqi Wang ↗Daobo Sun ↗Yizheng Wang ↗Yilong Zhang ↗Yabin Jin ↗Xiaoying Zhuang ↗Timon Rabczuk ↗

arXiv:2606.16624v1 Announce Type: new Abstract: Plate and shell structures are widely used in engineering, making rapid response prediction under varying geometries, materials, and loads highly desirable. However, conventional finite element methods require repeated modeling and solution, resulting in high computational costs. This study proposes a geometry-aware variational neural operator for Mindlin-Reissner plate problems, termed MR-GVNO. The method uses boundary point clouds to represent irregular geometries and employs separate encoders for spatially varying material fields, pressure loads, and scalar physical parameters. A cross-attention mechanism integrates these inputs with query point information to predict transverse deflections and rotations at arbitrary locations. MR-GVNO is trained without labeled solution data using a variational physics-informed loss derived from the discretized total potential energy. It directly processes irregular point clouds and allows different physical fields to be discretized independently, avoiding interpolation onto a common grid. Numerical experiments on single-hole, double-hole, and L-shaped plates demonstrate accurate response prediction under homogeneous and heterogeneous materials and uniform and random loads. The model also achieves millisecond-level full-field inference and favorable cross-geometry generalization.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18619

Code-Augur: Agentic Vulnerability Detection via Specification Inference

作者:

Zhengxiong Luo ↗Mehtab Zafar ↗Dylan Wolff ↗Abhik Roychoudhury ↗

arXiv:2606.18619v1 Announce Type: cross Abstract: The advent of agentic vulnerability detection is already becoming a watershed moment for software security. Audits conducted entirely by autonomous LLM agents are uncovering critical vulnerabilities in fundamental software underpinning digital society. Many of these vulnerabilities remained masked for years, surfacing only now with AI agents. Yet the reasoning behind these discoveries remains alarmingly opaque and unvalidated. What assumptions did the agent make about a function's inputs when it deemed that function to be secure? Failures in reasoning and incorrect assumptions can lead to missed vulnerabilities and reduce trust in agentic analysis. We propose a security-specification-first paradigm that (1) exposes the agent's tacit assumptions explicitly as security specifications and (2) continuously refines those specifications via runtime falsification. We realize our approach in Code-Augur, a novel harness for agentic vulnerability detection. Given a codebase, Code-Augur analyzes each component of the system for vulnerable code. When it deems a component to be secure, it commits the local invariants behind that judgment as in-source assertions. In parallel, Code-Augur leverages a guided fuzzer to attempt to falsify those assumptions. When the fuzzer triggers an assertion, this either reveals a genuine vulnerability or a flawed specification to refine. In both cases, this process grounds the agent's understanding, aligning its view of code intent with how the code actually behaves. On real-world subjects, Code-Augur effectively leverages security specifications to detect more vulnerabilities than other state-of-the-art agents. Additionally, Code-Augur found 22 new vulnerabilities in key open-source projects. Compared to curated specialized models like Claude Mythos, Code-Augur offers effective agentic vulnerability detection built on widely available LLMs like Sonnet and DeepSeek.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2502.08363

Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding

作者:

Konstantin Berestizshevsky ↗Renzo Andri ↗Lukas Cavigelli ↗

We present Top-Theta (Top-$\theta$) Attention, a training-free method for sparsifying transformer attention during inference. Our key insight is that static, per-head thresholds can be calibrated to retain the desired constant number of significant elements per attention row. This approach enables content-based sparsity without retraining, and it remains robust across data domains. We further introduce compensation techniques to preserve accuracy under aggressive sparsification, establishing attention thresholding as a practical and principled alternative to top-k attention. We provide extensive evaluation on natural language processing tasks, showing that Top-$\theta$ achieves 3-10x reduction in V-cache usage and up to 10x fewer attention elements during inference while degrading no more than 1% in accuracy.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14700

RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space

作者:

Xichen Pan ↗Aashu Singh ↗Satya Narayan Shukla ↗Xiangjun Fan ↗Shlok Kumar Mishra ↗Saining Xie ↗

Large language models (LLMs) are widely used in text-to-image (T2I) systems, but they are typically limited to text encoding, while denoising is handled by newly trained generative backbones. The emergence of representation autoencoders (RAEs) shifts the generation target toward semantically structured visual representations, creating a latent space that is more compatible with pretrained LLM priors. Inspired by multimodal LLMs (MLLMs), where an MLP projector is sufficient to align clean visual representations with a pretrained LLM, we repurpose the MLLM itself as a noisy representation encoder, extending this mechanism from clean to noisy inputs. We present RepFusion, which uses the resulting MLLM outputs as the conditioning signal for a diffusion transformer. In controlled comparisons at similar inference budgets, RepFusion outperforms baselines that devote comparable capacity to newly initialized denoisers. These results demonstrate that MLLMs provide strong priors for denoising visual representations and that, by conditioning on evolving noisy representations, test-time compute can be productively spent on repeated MLLM conditioning in modern T2I systems.

阅读与讨论 → 访问原文 →

20.

arXiv (math.PR) 2026-06-11 DOI: arXiv:2401.00351

Marked random graphs with given degree sequence: large deviations on the local topology

作者:

Rangel Baldasso ↗Alan Pereira ↗Guilherme Reis ↗

arXiv:2401.00351v2 Announce Type: replace Abstract: We investigate the behavior of the empirical neighborhood distribution of marked graphs in the framework of local weak convergence. Here we extend known results by considering uniform random graphs with given degree sequences and i.i.d. marks on half-edges and vertices. We establish a large deviation principle for such families of empirical measures. The proof builds on Bordenave and Caputo's seminal 2015 paper, and Delgosha and Anantharam's 2019 introduction of BC entropy, relying on combinatorial lemmas that allow one to construct suitable approximations of measures supported on marked trees. Possible applications of these results are in the study of interacting diffusions on top of random graphs.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17162

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

作者:

Ye Jin ↗Yangyang Xu ↗Jun Zhu ↗Yibo Yang ↗

Personalized presentation generation requires more than conditioning on a current prompt or template: agents must preserve stable user preferences across tasks, retain newly introduced preferences and constraints during multi-turn revision, and carry out local edits reliably. We propose MemSlides, a hierarchical memory framework for personalized presentation agents that separates long-term memory from working memory and further divides long-term memory into user profile memory and tool memory. User profile memory stores intent-conditioned profiles for round-0 personalization, working memory carries active preferences and session constraints across revision rounds, and tool memory stores reusable execution experience for reliable localized editing. MemSlides pairs this memory design with scoped slide-local revision, so targeted updates act on the smallest affected region instead of repeatedly regenerating the full deck. In controlled experiments, user profile memory improves persona-alignment judgments on a multi-persona, multi-intent profile bank, tool-memory injection improves closed-loop modify behavior in diagnostic matched-pair settings, and qualitative cases illustrate working memory's ability to carryover preferences. Taken together, these results suggest that effective personalization in presentation authoring depends on separating persistent user profiles, session-level working memory, and reusable execution experience across generation and localized revision.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15152

Can Agents Read the Room? Benchmarking Visual Social Intelligence in Multimodal Simulation

作者:

Shijun Wan ↗Xuehai Wu ↗Jiwen Zhang ↗Siyuan Wang ↗Zhongyu Wei ↗

Social interaction depends on both language and visible social signals, such as facial expressions, posture, gaze, and emotional shifts. Yet existing social-agent benchmarks are largely text-based and rarely test whether multimodal agents can use visual cues to guide interaction. We introduce \textsc{\benchmarkname{}}, a benchmark evaluating visual social intelligence in multimodal social simulation. It contains 240 scenarios, 585 role instances, and 2,340 role-task instances, combining aligned textual-visual evidence, structured role profiles, and four role-level tasks: expression task, characteristic task, interaction regulation task, and interaction outcome task. Evaluating seven recent MLLMs under verbalized-vision and direct-vision reveals a clear gap between local role enactment and interaction management: role-specific expression and conflict handling are near saturation, whereas interaction regulation and visually grounded outcome achievement remain substantially more difficult. The code is released at https://github.com/JunsWan/AgentViSS, and the dataset is available at https://huggingface.co/datasets/JunsWan/AgentViSS.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13643

Recursive Agent Harnesses

作者:

Elias Lumer ↗Sahil Sen ↗Kevin Paul ↗Vamse Kumar Subbiah ↗

Recursive language models (RLMs) showed that recursion over model calls is an effective strategy for long-context reasoning, and production coding agents have begun to write code that spawns subagents at scale, most recently in Anthropic's dynamic workflows. We name and study the pattern between these two lines of work, where the recursive unit is a full agent harness with filesystem tools, code execution, and planning rather than a model call with no tools. We call this the Recursive Agent Harness (RAH) and frame it as harness recursion, the code-first extension to the model recursion of RLMs. A parent agent generates and runs an executable script that spawns subagent harnesses in parallel for fine-grained workloads and uses structured function calls for small subtasks. We provide a controlled evaluation on long-context reasoning. With the backbone held fixed at GPT-5 to match the published Codex and RLM baselines, RAH improves the Codex coding-agent baseline from 71.75% to 81.36% on Oolong-Synthetic (199 samples, 13 context-length buckets up to 4M tokens), a gain attributable to the harness rather than the model. With a stronger backbone, Claude Sonnet 4.5, the same design reaches 89.77%.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20216

Learner-based Concept Drift Detection: Analysis and Evaluation

作者:

Md Moman Ul Haque Khan ↗Samira Sadaoui ↗

arXiv:2606.20216v1 Announce Type: cross Abstract: Machine learning algorithms deployed for evolving streaming environments must handle the non-stationary data distributions, commonly referred to as concept drift. The presence of concept drift poses a major challenge for many real-world applications because it can severely degrade their predictive performance, hindering their ability to support robust decision-making. Consequently, the timely and efficient detection of drift events is critical for sustaining high accuracy over time. This study examines theoretically the concept drift characteristics and numerous drift detection algorithms across several categories. Furthermore, we evaluate their performance on both synthetic and real-world datasets exhibiting diverse streaming scenarios and drift characteristics, such as abrupt and gradual changes. This study aims to enhance understanding of the complex notion of concept drift characteristics and behavior of drift detectors, along with their applicability to diverse contexts.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.19184

When AUC Misleads: Polarization-Aware Evaluation of Deepfake Detectors under Domain Shift

作者:

Dat Nguyen ↗Cosmin Radoi ↗Romain Hermary ↗Marcella Astrid ↗Nesryne Mejri ↗Enjie Ghorbel ↗Djamila Aouada ↗

Recent advances in generative AI, such as diffusion models and face-swapping tools, have enabled the creation of highly realistic deepfakes, leading to real-world harms including financial fraud and non-consensual explicit content. In response, deepfake detection has become an active research area, with recent methods increasingly focusing on improving generalization to unseen manipulations. This is typically evaluated using the Area Under the ROC Curve (AUC) measured separately across multiple datasets. However, such an evaluation fails to reflect real-world scenarios where detectors face a mixture of data sources and varying artifact types. To address this limitation, we introduce a novel metric, Cross-dataset AUC (Cross-AUC) that averages per-domain AUCs with a measure of prediction polarization for taking into account the robustness to domain shift. The polarization extent is quantified by the Wasserstein Distance between class score distributions. Cross-AUC not only assesses the generalization capabilities of deepfake detectors under domain shifts more realistically, but it is also interpretable as it better explains the reason behind a drop in performance. Experiments performed on seven benchmark datasets demonstrate its practical relevance.

阅读与讨论 → 访问原文 →

探索全球前沿学术脉络