cập nhật 2 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5467, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

24
Rethinking Verification in Agent Harnesses
📄 Paper HF Daily Papers 25 ngày trước

Agent harnesses enable large language models to act through tools, observe the results, and iteratively work toward a task goal. Verification checks and revises agents' work to improve output quality. Yet there is limited guidance on how harnesses should organize this effort. We …

🅲 hạng C
24
MemSteer: Turning User Histories into Supervision for Agent Memory Optimization
📄 Paper HF Daily Papers 21 ngày trước

An effective agent memory system should adapt to a user's history and task requirements. Human-annotated supervision can guide this adaptation by providing feedback for evaluating and improving memory designs. Yet suitable labels are rarely available for new user histories, and m…

🅲 hạng C
24
Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?
📄 Paper HF Daily Papers 18 ngày trước

Software development sessions often involve several unfinished tasks rather than one issue carried through to completion. As coding agents take on repository-level development, they need to recover an earlier task's requirements and partial progress after intervening work. Existi…

🅲 hạng C
24
A general-purpose System One decision model for clinical records
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.27099v1 Announce Type: new Abstract: Clinical care, health-system operations and biomedical discovery depend on extracting reliable answers from patient records, yet applying diverse clinical questions across entire populations remains computationally expensive. Here …

🅲 hạng C
24
How Intervention History Changes AI Agent Sabotage on Subsequent Tasks
📄 Paper arXiv cs.CR 29 ngày trước

arXiv:2610.26935v1 Announce Type: new Abstract: AI control evaluations often reset agents' memory between tasks, although deployed agents may retain records of prior interventions. We ask whether learning that an earlier attack was caught changes an agent's ability to evade defe…

🅲 hạng C
24
AutoRedClaw: Automated Red-Teaming for Claw-Style Agents
📄 Paper arXiv cs.CR 29 ngày trước

arXiv:2610.27244v1 Announce Type: new Abstract: Agent systems are shifting from task-scoped tool-use agents to persistent, personalized assistants such as OpenClaw. These claw-style agents maintain configuration files (e.g., AGENTS.md), long-term memory, and reusable skills. Onc…

🅲 hạng C
24
Fig: Automated Multiagent Behavior Elicitor
📄 Paper arXiv cs.AI 28 ngày trước

arXiv:2610.28891v1 Announce Type: new Abstract: Many social evaluations for multiagent systems study behaviors as they emerge from environments instead of systematically intervening in the environment to elicit such behaviors. We introduce Fig (Finding Interactions in Games), an…

🅲 hạng C
24
D-Skill: Distilling Teacher Knowledge through Agent Skills
📄 Paper arXiv cs.AI 28 ngày trước

arXiv:2610.28914v1 Announce Type: new Abstract: Frontier language-model agents excel at complex tasks, but high inference costs make transferring their capabilities to smaller models essential. Traditional knowledge distillation achieves this through parameter updates, requiring…

🅲 hạng C
24
Diagnosing Personalization Failures in Mobile GUI Agents
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.30573v1 Announce Type: new Abstract: Unlike conventional GUI agents, personalized GUI agents require user preferences to guide sequential execution over changing GUI states. This raises two challenges: determining HOW each preference should alter execution strategy an…

🅲 hạng C
24
ReDence: A Hybrid Agentic and Decision-Model Framework for Rapid, Evidence-Grounded Detection of Modern Social Engineering Scams
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.30963v1 Announce Type: new Abstract: Detecting online social engineering (SE) scams often requires examining website workflows, verifying claims against external sources, and connecting evidence across multiple pages. Existing detectors provide limited support for the…

🅲 hạng C
24
BARC-Bench: Benign Asks, Risky Consequences
📄 Paper arXiv cs.AI 24 ngày trước

arXiv:2610.32024v1 Announce Type: new Abstract: Task instructions from users for agents are inherently underspecified, especially regarding safety boundaries--creating behavioral risks. To study these risks, we introduce BARC-Bench, a collection of 110 tasks across nine simulate…

🅲 hạng C
24
SWE-Shift: Evaluating Coding Agents in Evolving Workspaces
📄 Paper arXiv cs.AI 24 ngày trước

arXiv:2610.32196v1 Announce Type: new Abstract: Repository-level coding benchmarks largely assume that tasks and environments remain unchanged throughout execution. In software development, code, dependencies, runtime state, and requirements can change while an agent is still wo…

🅲 hạng C
24
Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own Discoveries Are Statistical
📄 Paper arXiv cs.AI 24 ngày trước

arXiv:2610.32245v1 Announce Type: new Abstract: AI systems that discover scientific relations now generate candidate "laws" at scale, but the bottleneck has shifted from generation to vetting: which candidates deserve belief? We show that a deployed self-improving science agent …

🅲 hạng C
24
Incomparable Minima in Agent Tool Authorization
📄 Paper arXiv cs.CR 24 ngày trước

arXiv:2610.31914v1 Announce Type: new Abstract: An agent that needs a tool needs authority to call it, and every proposal for governing that authority has to answer one question: of two grants that both let the agent finish a task, which one is smaller? Over-privilege benchmarks…

🅲 hạng C
24
Tracing Money Laundering Across DeFi, Bridges, and Mixers on Ethereum
📄 Paper arXiv cs.CR 24 ngày trước

arXiv:2610.32210v1 Announce Type: new Abstract: Illicit actors exploit Ethereum's deep liquidity and diverse on-chain services to launder criminal proceeds by combining decentralized finance (DeFi) protocols, cross-chain bridges, and mixers in multi-stage processes. Existing ant…

🅲 hạng C
24
Back to Basics: Formal Analysis Hints Improve Weak-to-Strong Monitoring
📄 Paper arXiv cs.CR 23 ngày trước

arXiv:2610.34064v1 Announce Type: new Abstract: Frontier agentic systems are capable of taking misaligned actions that may cause significant harm. Monitoring techniques are developed to oversee these systems in order to detect and prevent dangerous actions. However, current stat…

🅲 hạng C
24
Artificial Intelligence in Mechanical Engineering: Foundations, Opportunities, Challenges, and Responsibilities
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33105v1 Announce Type: new Abstract: Artificial intelligence (AI) is reshaping mechanical engineering (ME), from modeling, simulation, and optimization to diagnostics, design, and technical communication. Drawing on a round-table at the 28th ABCM International Congres…

🅲 hạng C