cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 7.2 giờ sau khi CVE được công bố (n = 5392, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

28
VirtualTrialHarness: Coordinating Agentic Operationalization of Virtual Trial Protocols Across Complex Clinical Schemas
📄 Paper arXiv cs.AI 12 ngày trước

arXiv:2611.05551v1 Announce Type: new Abstract: Virtual trials use routinely collected clinical data to evaluate treatment strategies, but translating a study protocol into an executable analysis requires determining how clinical concepts and study requirements should be represe…

🅲 hạng C
28
ViBench 2.0: A Benchmark for Long-Horizon Software Building
📄 Paper arXiv cs.AI 12 ngày trước

arXiv:2611.05620v1 Announce Type: new Abstract: On Replit, our agentic engineering platform, users now build entire products without writing code, through successive feature requests to an agent. Yet existing coding benchmarks evaluate single, fully specified tasks, and many are…

🅲 hạng C
28
Agents, Think Only When it Helps
📄 Paper arXiv cs.AI 12 ngày trước

arXiv:2611.05709v1 Announce Type: new Abstract: LLM agent distillation transfers agentic capabilities to student models by training on complete teacher trajectories that typically interleave thoughts and actions. We question how critical thought supervision is for agents' ultima…

🅲 hạng C
28
Trust Responsive Runtime Authorization for Agentic AI with Empirical Characterization of Policy Behavior and Parameter Sensitivity
📄 Paper arXiv cs.AI 11 ngày trước

arXiv:2611.06996v1 Announce Type: new Abstract: The policy that converts runtime estimates of an autonomous agent's condition into operational authority is rarely specified or measured. We empirically characterize the Trust Responsive Authorization Policy (TRAP), which maps an A…

🅲 hạng C
28
EnvOpt: Automated Optimization for Agent Environments
📄 Paper arXiv cs.AI 11 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
DelegateEval: Evaluating Platforms for Personal External Service Agents
📄 Paper arXiv cs.AI 11 ngày trước

arXiv:2611.07508v1 Announce Type: new Abstract: AI agents that work for an individual over time may also help that individual serve external clients. We define a personal external service agent as an agent authorized and continuously managed by a specific individual to accept cl…

🅲 hạng C
28
A Gingerbread House for LLM Agents: Source-Planned Honeypots That Lure Autonomous Attackers into an Isolated Shadow
📄 Paper arXiv cs.CR 11 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
GuardrailAgent: An Agentic Framework for Jailbreak Defense
📄 Paper arXiv cs.CR 8 ngày trước

arXiv:2611.09734v1 Announce Type: new Abstract: Despite undergoing safety training to align with human values, large language models (LLMs) remain vulnerable to jailbreak attacks that circumvent built-in safeguards and elicit malicious behaviors given by the adversary. Existing …

🅲 hạng C
28
Aegis OS: A Transactional Multi-Tenant Operating System Runtime for Eliminating Authorization Fatigue in Autonomous Coding Agents
📄 Paper arXiv cs.CR 8 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
28
Tail-risk-aware Agent Safety: Constraining Tail Risks Across Multi-step LLM Agent Workflows
📄 Paper arXiv cs.AI 7 ngày trước

arXiv:2611.10411v1 Announce Type: new Abstract: LLM-based agents extend LLMs with tool calls, memory, planning, and retrieval to act in external environments, but they are vulnerable to attacks at different workflow steps. Existing defenses, including prompt engineering and post…

🅲 hạng C
28
The Devil Wears Markdown: Detecting Malicious Intent Hidden in AI Agent Skill Instructions through Hybrid Static, Dynamic, and Agentic Analysis
📄 Paper arXiv cs.CR 7 ngày trước

arXiv:2611.10830v1 Announce Type: new Abstract: Agentic AI ecosystems increasingly rely on reusable agent skills that combine executable code, natural-language instructions, configuration artifacts, and external tool integrations. These hybrid artifacts create software supply-ch…

🅲 hạng C
28
Tracing MCP Security Vulnerabilities: Constructing and Analyzing an MCP Security Vulnerability Dataset
📄 Paper arXiv cs.CR 7 ngày trước

arXiv:2611.11104v1 Announce Type: new Abstract: As a core protocol for integrating large language models (LLMs) with external data sources and tools, the Model Context Protocol (MCP) has quickly become a key interface in emerging AI agent systems. As the MCP ecosystem expands, r…

🅲 hạng C
28
Agentic Attribution of Cloud Resource Ownership
📄 Paper arXiv cs.CR 7 ngày trước

arXiv:2611.11340v1 Announce Type: new Abstract: Security tools raise findings across cloud environments, and AI agents now investigate and prioritize them. A finding is still resolved by people: it has to reach the people responsible for fixing it and accountable for the resourc…

🅲 hạng C
28
OverSeer: Multi-Agent World Models Beyond What Agents See
📄 Paper HF Daily Papers 28 ngày trước

Despite the success of video world models, extending them to multiple agents is difficult because it requires generating several agent-specific video streams that are consistent in time and between agents. To address this gap, we introduce OverSeer, a multi-agent world model that…

🅲 hạng C
28
Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents
📄 Paper HF Daily Papers 23 ngày trước

Language agents increasingly act through external tools and interactive environments, making the interface between the model and its executable capabilities part of the decision process. Model Context Protocol (MCP) and command-line interfaces (CLI) can expose the same semantic o…

🅲 hạng C
28
Harness Scaling for Generalizable Agentic Reinforcement Learning
📄 Paper HF Daily Papers 27 ngày trước

Agent harnesses have become a central component of modern agentic systems, shaping how models use tools, manage context, and coordinate long-horizon interaction. Realizing the benefits of these harnesses depends on how effectively the underlying model can make use of them, motiva…

🅲 hạng C
28
SketchDirector: Complex Scene Sketching via Agentic Layout Reasoning and Detail Refinement
📄 Paper HF Daily Papers 18 ngày trước

Existing sketch generation methods often rely on image guidance and are largely limited to individual objects or simplified scenes, leaving text-guided complex scene sketching underexplored. We present SketchDirector, an agentic framework that mimics the human sketching workflow …

🅲 hạng C
27
What Moves a LoCoMo Score? Memory Context, Answer Prompts and Judges
📄 Paper arXiv cs.AI 9 giờ trước

arXiv:2611.19199v1 Announce Type: new Abstract: LoCoMo is a widely reported benchmark for long-term conversational memory, but published scores mix memory quality with choices of answer prompt, judge and baseline layout that are rarely reported together. We measure how much thes…

🅲 hạng C
27
Privacy-Preserving Clustering Algorithm and Parameter Selection for Collaborative Population Stratification Using Distributed PCA
📄 Paper arXiv cs.CR 9 giờ trước

arXiv:2611.18925v1 Announce Type: new Abstract: We propose a privacy-preserving selection layer for collaborative population stratification workflows, enabling an honest-but-curious server to recommend a strong clustering algorithm-hyperparameter configuration from privacy prote…

🅲 hạng C
27
Attacker Diversity Reduction in Adaptive LLM Red Teaming
📄 Paper arXiv cs.CR 9 giờ trước

arXiv:2611.19680v1 Announce Type: new Abstract: Reinforcement learning can make automated red-teaming more successful while narrowing the attacks it produces. Co-training an attacker and a defender with group-relative policy optimization (GRPO) has been reported to reduce attack…

🅲 hạng C