会员服务
Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems
Arxiv
0+阅读 · 6月13日
OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models
Arxiv
0+阅读 · 6月15日
Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents
Arxiv
0+阅读 · 6月15日
Skill Is Not Document: A Query-Conditional Benchmark and Two-Stage Retriever for LLM Agent Skill Routing
Arxiv
0+阅读 · 6月14日
Skill Is Not Document: A Query-Conditional Benchmark and Two-Stage Retriever for LLM Agent Skill Routing
Arxiv
0+阅读 · 6月8日
SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows
Arxiv
0+阅读 · 6月6日
Beyond Rubrics: Exploration-Guided Evaluation Skills for Reward Modeling
Arxiv
0+阅读 · 6月11日
Pomona: Continuous Code Quality Improvement via Small, Automated Changes at Bloomberg
Arxiv
0+阅读 · 6月4日
SocialCoach: Personalized Social Skill Learning with RL-based Agentic Tutoring and Practice
Arxiv
0+阅读 · 6月2日
More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries
Arxiv
0+阅读 · 5月21日
When Skills Don't Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity
Arxiv
0+阅读 · 5月24日
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
Arxiv
0+阅读 · 5月31日
MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills
Arxiv
0+阅读 · 6月9日
From Benchmarks to Skills: Low-Rank Factors for LLM Evaluation
Arxiv
0+阅读 · 6月11日
Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills
Arxiv
0+阅读 · 6月10日
参考链接
微信扫码咨询专知VIP会员
Top