cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5441, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

29
Compositional Exploits in Autonomous Coding Agents: Attack Mechanics and Ephemeral Defense
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.19764v1 Announce Type: new Abstract: Autonomous coding agents (such as Antigravity, Claude Code, Cursor, and OpenHands) rely on third-party tools to inspect files, run commands, and call external APIs. Today's security auditors evaluate these tools almost entirely in …

🅲 hạng C
28
LuthorSQL: A One-Pass Text-to-SQL Model as System 1 for a Slower LLM Agent
📄 Paper HF Daily Papers 6 ngày trước

Frontier LLM agents that query databases with tools are among the most accurate text-to-SQL systems, but per-query calls to a hosted model are slow, costly, and expose sensitive organizational queries to external APIs. For example, a Claude Opus 5.5 agent serving 10,000 queries a…

🅲 hạng C
28
EnvOpt: Automated Optimization for Agent Environments
📄 Paper arXiv cs.AI 12 ngày trước

arXiv:2611.07372v1 Announce Type: new Abstract: An LLM agent's cost and success depend on its model, its harness, and its environment. In addition to the widely studied directions of parameter tuning and harness optimization, we propose the third direction: optimization over sta…

🅲 hạng C
28
A Gingerbread House for LLM Agents: Source-Planned Honeypots That Lure Autonomous Attackers into an Isolated Shadow
📄 Paper arXiv cs.CR 12 ngày trước

arXiv:2611.07611v1 Announce Type: new Abstract: LLM agents can exploit web vulnerabilities fast enough that patching may come too late. Deception against such agents has mostly lured them away from a real target that stays reachable. We study a different arrangement: an LLM defe…

🅲 hạng C
28
Aegis OS: A Transactional Multi-Tenant Operating System Runtime for Eliminating Authorization Fatigue in Autonomous Coding Agents
📄 Paper arXiv cs.CR 9 ngày trước

arXiv:2611.08516v1 Announce Type: cross Abstract: Autonomous coding agents such as Google Antigravity (agy), Anthropic Claude Code (claude), and OpenAI Codex CLI (codex) execute multi-step software engineering workflows on workstations and cloud hosts. Existing agent environment…

🅲 hạng C
26
Correlated Failures of AI Approval Monitors
📄 Paper arXiv cs.CR 28 ngày trước

arXiv:2610.29178v1 Announce Type: new Abstract: Before an AI agent takes a consequential action, such as paying, messaging or changing code, several monitors check it. Their verdicts are combined by aggregating scores or by counting approvals, whatever inputs the monitors share.…

🅲 hạng C
26
LEASH: Stay Safe in Agentic Robotics
📄 Paper HF Daily Papers 9 ngày trước

Foundation models such as GPT and Claude have shown strong capabilities in spatial understanding and embodied intelligence. These advances make agentic robotics a promising path toward artificial general intelligence in robotics. However, we find that using foundation models to c…

🅲 hạng C
25
AI Reviews Are Biased Towards the Appendix
📄 Paper HF Daily Papers 6 ngày trước

Large language models (LLMs) are increasingly used by reviewers to highlight weaknesses during the reviewing process, and their outputs often shape the reviews that humans submit. Prior work studies how LLM reviews align with human ones, yet we know little about which parts of a …

🅲 hạng C
23
Simple Features Beat Most AI Control Monitors
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2610.41713v1 Announce Type: new Abstract: AI control relies on monitors to catch a capable model that sabotages its work. These monitors are evaluated on their ability to differentiate honest from backdoored code. We show that on a standard evaluation dataset, simple featu…

🅲 hạng C
23
Beyond Benchmarks: Can Small Open-Weight Models Get Real Coding Work Done?
📄 Paper HF Daily Papers 25 ngày trước

Making an open-weight language model generate text is not the same as making it finish coding work. This retrospective empirical systems experience report follows my engineering work from July to October 2026 across coding clients, model-specific serving recipes, vLLM, SGLang, ll…

🅲 hạng C