cập nhật 42 phút 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.

31
Can You Undo It? Reversibility Classes for AI Agent Actions
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.22075v1 Announce Type: new Abstract: Tool-using AI agents change files, databases, access rights and public information, yet permission to call a tool does not establish whether a mistake can be undone. We present Reversibility Classes, a declared five-level vocabular…

🅲 hạng C
28
ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents
📄 Paper HF Daily Papers 16 ngày trước

Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they first synthesize a database and scenario, then derive tools and tasks from them. As …

🅲 hạng C
28
EGI-BENCH: An Enterprise General Intelligence Benchmark Suite
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.27234v1 Announce Type: new Abstract: Enterprise adoption of LLMs in agentic workflows is gated by evaluations that span a wide arc of abilities: CRM operations, heterogeneous-document retrieval, personal data understanding, multi-turn planning, tool use, function call…

🅲 hạng C
28
Agentic AI Defense: Decode-Time Provenance Binding for MCP
📄 Paper arXiv cs.CR 24 ngày trước

arXiv:2610.31974v1 Announce Type: new Abstract: Agentic AI systems using the Model Context Protocol (MCP) are vulnerable to indirect prompt injection through untrusted tool outputs. We demonstrate cross-modal trust laundering, in which instructions concealed in an email-signatur…

🅲 hạng C
28
Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol
📄 Paper arXiv cs.CR 22 ngày trước

arXiv:2610.36108v1 Announce Type: new Abstract: LLM agents increasingly access external tools through the Model Context Protocol (MCP), but the natural-language metadata used to describe those tools creates a prompt-injection surface. Within this established tool-poisoning surfa…

🅲 hạng C
28
AgentCap: Capability-Based Runtime Authorization for Secure LLM Agent Execution
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.00729v1 Announce Type: new Abstract: Language-model agents commonly collapse two decisions that security systems separate: selecting an action and determining whether that action is authorized. When a model exercises standing authority, indirect prompt injection can c…

🅲 hạng C
28
DelegateEval: Evaluating Platforms for Personal External Service Agents
📄 Paper arXiv cs.AI 13 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
Tracing MCP Security Vulnerabilities: Constructing and Analyzing an MCP Security Vulnerability Dataset
📄 Paper arXiv cs.CR 9 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
Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents
📄 Paper HF Daily Papers 25 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
27
MCP vs CLI for AI Agents: A Comparative Analysis of Tool Integration Strategies for Autonomous Systems
📄 Paper arXiv cs.AI 27 ngày trước

Paper này so sánh chi tiết chiến lược tích hợp công cụ CLI và MCP cho các hệ thống AI tự trị trên 14 tiêu chí, bao gồm đánh giá bảo mật và mô hình kinh tế, cung cấp cái nhìn thiết thực để developer lựa chọn phương án tích hợp tool.

🅲 hạng C
26
The Cost of Saying Hello: An Empirical Study of Handshake Overhead in AI Agent Communication Protocols
📄 Paper arXiv cs.AI 27 ngày trước

Bài paper này thực hiện benchmark thực tế đầu tiên về chi phí handshake (overhead thiết lập kết nối) trong các protocol giao tiếp agent hàng đầu như MCP, A2A và ACP, giúp các nhà phát triển AI agent đánh giá hiệu suất trao đổi dữ liệu ban đầu.

🅲 hạng C