cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.3 giờ sau khi CVE được công bố (n = 5297, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

28
Agent-ZTA: A chain-Aware Zero Trust Model for Bidirectional Security-State Propagation and Runtime Containment in Multi-Agent Delegation
📄 Paper arXiv cs.CR 5 ngày trước

arXiv:2611.18999v1 Announce Type: new Abstract: Multi-agent systems increasingly delegate tasks and permissions across chains of autonomous agents that invoke protected tools. Although agent identities and delegated credentials may remain valid throughout a workflow, the securit…

🅲 hạng C
27
The Resolution Hypothesis: Agent Evolution's Key Is Identifying Improvements
📄 Paper HF Daily Papers 5 ngày trước

Agent evolution follows a simple loop: a proposer writes candidate artifacts (prompts, skills, memories) and selection accepts those that score higher. This loop has shown promise, yet practitioners face a puzzle: methods trade wins across papers, and evolution often fails to boo…

🅲 hạng C
27
Staged Semantic Distillation: Preserving Free-Form Semantics in a Low-Compute Non-LLM Surrogate of a Staged LLM Agent
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.19299v1 Announce Type: new Abstract: Staged LLM agents make market and social simulators realistic, but one 102-day run of a 200-agent, ten-index market simulator issues 203,100 language-model calls and returns one realization. Conventional low-compute distillation dr…

🅲 hạng C
26
A Push Down the Mountain: Framing Effects and Internal State Interventions on Collusive Behavior in a Long-Horizon LLM Agent
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.17515v1 Announce Type: new Abstract: Can sustained gain-loss (valence) framing sway an LLM agent toward market manipulation? We place Gemma 3 12B into the seat of a defendant in the London silver-fixing litigation, in a market simulation built from real case transcrip…

🅲 hạng C
25
Backtracking Agent Applications Security Incidents
📄 Paper arXiv cs.CR 2 ngày trước

arXiv:2611.26525v1 Announce Type: new Abstract: Agent applications are increasingly deployed, yet agent-specific attacks pose real threats to them. Upon a security incident, organizations backtrack to identify the CEP (compromise entry point), remediate the damage, and prevent i…

🅲 hạng C
25
Posterior Matching Distillation
📄 Paper HF Daily Papers 3 ngày trước

Diffusion distillation accelerates image and video generation by compressing a pretrained teacher's iterative sampling process into a few network evaluations. Distribution-based methods achieve this by matching the student's output distribution to the teacher's. This matching is …

🅲 hạng C
25
Auditable Clinical Support with Decision Agents
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.23700v1 Announce Type: new Abstract: Clinicians reviewing a diagnostic work-up will ask what was considered at each step and why the assessment changed. Agents powered by free text can reach physician-level diagnostic accuracy, but their written reasoning does not alw…

🅲 hạng C
24
Heave-Ho: Decentralized Long-Horizon Multi-Humanoid Collaboration
📄 Paper HF Daily Papers 5 ngày trước

Collaboration promises to extend humanoid capabilities beyond what individual robots can achieve. However, realizing this potential requires coordinated whole-body interactions, coherent long-horizon planning, and precise synchronization across robots. We introduce Heave-Ho, a de…

🅲 hạng C
24
In Situ Training of Optical Neural Networks by Coding Agents
📄 Paper HF Daily Papers 4 ngày trước

Optical neural networks promise fast, energy-efficient computing, but every device departs from its design and must be trained with the hardware. In situ training relies on an expert-built calibrated digital model of each device or on gradient-free trial and error. Coding agents,…

🅲 hạng C
24
CADMAGEDDON: High-Fidelity CAD Reconstruction with Local Inference
📄 Paper HF Daily Papers 5 ngày trước

CAD practitioners often work with proprietary parts that they are unwilling to share with external services. For individuals and small companies, bringing this work in-house also requires computational resources they can afford. We introduce CADMAGEDDON, an open-source agent that…

🅲 hạng C
24
PlayCraft: Designing Engaging Games from Agent Play Experience
📄 Paper HF Daily Papers 3 ngày trước

Recent AI agents can generate playable games, but these games are not necessarily engaging. Mastery is a key source of engagement, yet designing for it requires extensive human play and tuning. We propose PlayCraft, an automated framework that uses a vision-based agent to play ga…

🅲 hạng C
24
NexSight: Verifiable Tasks for Fine-Grained Agentic Long-Video Understanding
📄 Paper HF Daily Papers 5 ngày trước

Fine-grained questions about long videos ask how many times an action occurs, in what order events unfold, or exactly when a state changes. Answering them can require finding brief moments scattered across hours of footage. Agentic models that decide when and where to look promis…

🅲 hạng C
24
Causally Constrained and Uncertainty-Aware Cardiopulmonary Risk Prediction
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.17819v1 Announce Type: new Abstract: Routine chest computed tomography (CT) captures pulmonary, cardiac, and vascular phenotypes that jointly stratify lung cancer and cardiovascular disease, the two leading causes of death in lung-screening populations. Yet clinical r…

🅲 hạng C
24
Twice-Told Critiques: Claim-Level Homogenization of Peer Review in the LLM Era
📄 Paper HF Daily Papers 3 ngày trước

Peer review relies on several readers finding different problems. We measure critique overlap in conference and journal reviews. At ICLR, measured overlap rose from 12.0% in 2026 to 21.3% in 2027, in reviews from the same stage of the review process, with year-on-year rises at Ne…

🅲 hạng C
24
GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.23476v1 Announce Type: new Abstract: Autonomous AI agents pair a frozen base model with an editable harness of prompts, skills, tool rules, and memory. Recursive self-improvement (RSI) adapts this harness from experience without weight updates, yet self-editing withou…

🅲 hạng C
23
From Sorry to QED: Refining LLM Math Proofs via Angelic Execution
📄 Paper arXiv cs.AI 4 ngày trước

arXiv:2611.22103v1 Announce Type: new Abstract: Large language models (LLMs) can now generate Lean proof scripts that capture the high-level structure of many mathematical arguments. However, these scripts frequently fail on complex theorems: a single missing side condition or m…

🅲 hạng C
23
LLMs as Validators for Cross-Chain Bridges: Evaluating Source-Level and Transaction-Level Attack Detection on Solana
📄 Paper arXiv cs.CR 4 ngày trước

arXiv:2611.21777v1 Announce Type: new Abstract: Cross-chain bridges have suffered substantial asset losses due to vulnerabilities in their on-chain programs. On Solana, missing validation checks can enable exploits even when the underlying blockchain operates correctly. The abil…

🅲 hạng C