cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 7.2 giờ sau khi CVE được công bố (n = 53, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

30
Agent-ZTA: A chain-Aware Zero Trust Model for Bidirectional Security-State Propagation and Runtime Containment in Multi-Agent Delegation
📄 Paper arXiv cs.CR 1 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
30
VAST: Compiling Grounded Vulnerability Scenarios into Verifiable, Multi-Step Environments for Evaluating LLM Red-Team Agents
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.19465v1 Announce Type: new Abstract: Evaluating Large Language Model (LLM) security agents requires reproducible environments whose workflow difficulty can be varied and whose failures can be diagnosed. We present VAST (Verifiable Adversarial Scenario Training & Evalu…

🅲 hạng C
28
Tail-risk-aware Agent Safety: Constraining Tail Risks Across Multi-step LLM Agent Workflows
📄 Paper arXiv cs.AI 8 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
VirtualTrialHarness: Coordinating Agentic Operationalization of Virtual Trial Protocols Across Complex Clinical Schemas
📄 Paper arXiv cs.AI 13 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
RuntimeTickets: Source-Grounded Security Obligations for Agent Skills
📄 Paper arXiv cs.CR 14 ngày trước

arXiv:2611.03772v1 Announce Type: new Abstract: Third-party Agent Skills extend what an autonomous agent can do, but a malicious Skill can hide data exposure or output manipulation inside a legitimate workflow. Neither reading a Skill's description nor granting it tool permissio…

🅲 hạng C
28
Illusion: Safeguarding Topology Confidentiality in LLM Multi-Agent Systems via Behavior-Preserving Obfuscation
📄 Paper arXiv cs.CR 15 ngày trước

arXiv:2611.00923v1 Announce Type: new Abstract: The communication topology of Large Language Model Multi-Agent Systems (LLM-MASs) governs how information propagates among agents and encodes critical domain knowledge and expert workflow design. It is valuable intellectual propert…

🅲 hạng C
28
AgentOrch: How Close Can Global Orchestration Come to Step-by-Step Interaction?
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.33375v1 Announce Type: new Abstract: Enterprise workflow agents typically rely on step-by-step interaction (Step-by-Step): the agent executes an action, observes its result, and invokes a large language model (LLM) again to decide the next step. Global orchestration (…

🅲 hạng C
28
CoEvolve: Counterfactual-Guided Co-Evolution of Memory and Collaboration in Multi-Agent Systems
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.33539v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems have demonstrated remarkable capabilities across diverse tasks. Yet their memory and collaboration architectures often remain static, constraining continued adaptation and improv…

🅲 hạng C
28
Agentic AI Defense: Decode-Time Provenance Binding for MCP
📄 Paper arXiv cs.CR 23 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
Auditable Authorization for LLM Agents: Empirical Evidence Across Model, Harness, and Workflow Layers
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.19237v1 Announce Type: new Abstract: Human approval provides effective control only if rejected work stops and authorized work completes. We formalize refusal safety and bounded authorization completeness, and audit three execution boundaries: the model selects a call…

🅲 hạng C
26
PersonaScienceBench: Evaluating Scientific Agents with Diverse Simulated Researchers
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.32106v1 Announce Type: new Abstract: Scientific agents collaborate with researchers whose expertise and preferences differ, but benchmarks usually hold the collaborator fixed. We introduce PersonaScienceBench: 200 tasks from five benchmarks across four scientific doma…

🅲 hạng C
26
Evaluating and improving AI agents for sequencing protocol understanding
🤖 AI Agent / MCP arXiv cs.AI 19 ngày trước

Bài báo giới thiệu LibStructBench – một benchmark tài liệu cho phép đánh giá khả năng LLM agent tái cấu trúc cấu trúc thư viện trình tự DNA theo kịch bản mẫu. Kết quả cho thấy các agent hiện đại có thể tái tạo đúng một phần nhưng vẫn thiếu độ chính xác tuyệt đối, đặc biệt trong biểu diễn trạng thái phân tử. Đây là bước tiến quan trọng trong việc phát triển AI cho công nghệ sinh học.

🅲 hạng C
26
From Natural Language to Real Schematics: An Automated Workflow for Power Electronics Schematic Synthesis
⚙️ Tự động hoá arXiv cs.AI 19 ngày trước

Đề xuất quy trình tự động hóa chuyển đổi văn bản tự nhiên thành sơ đồ mạch điện tử công suất thực tế bằng LLM. Giúp giải quyết các lỗi ảo giác (hallucinations) trong thiết kế tự động EDA, từ chọn linh kiện đến mô phỏng mạch.

🅲 hạng C
25
Counterexample-driven autonomous research with application to excess radiated energy in a Z-pinch
📄 Paper arXiv cs.AI 14 ngày trước

arXiv:2611.03721v1 Announce Type: new Abstract: Recent breakthroughs in artificial-intelligence-assisted mathematics show that open-ended machine search can outperform human mathematicians, yet transferring this paradigm to physics requires refactoring the research workflow. We …

🅲 hạng C
25
A Controlled LLM Workflow for Evidence-Grounded Diagnosis of Risk Score Differences
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.23962v1 Announce Type: new Abstract: We propose a controlled Large Language Model (LLM) workflow for explaining risk score differences using similar historical transactions. The workflow combines reference retrieval and contrastive SHapley Additive exPlanations (SHAP)…

🅲 hạng C
24
Co-Sight Harness: Externalized Control Assets and Deterministic Enforcement for Long-Horizon Business Agents
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.17696v1 Announce Type: new Abstract: Long-horizon business workflows fail in two ways: errors accumulate as a chain of activities lengthens, and the knowledge an activity needs is written in a different vocabulary from the user's request. We study whether such workflo…

🅲 hạng C