arXiv AI
Aug 13
Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents
arXiv:2608. 11888v1 Announce Type: new Abstract: Agent skills are the de facto mechanism for extending LLM agents with reusable guidance.
Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents
Agent skills are the de facto mechanism for extending LLM agents with reusable guidance. A skill can shape the agent's task execution, including planning, tool use, problem-solving, and validation.
Related stories
arXiv AI
Jul 7
Skill Coverage: A Test Adequacy Metric for Agent Skills
arXiv:2606. 20659v2 Announce Type: replace Abstract: Agent skills encode reusable procedural knowledge for large language model (LLM) agents, and existing benchmarks show that such skills can improve task-level performance.
Hugging Face Trending Papers
Aug 18
TRUSS: Towards Task-Reliable and User-Safe Automated Agent Skill Generation
TRUSS is a framework that generates and verifies automated agent skills, ensuring they are both functionally effective and safe. It first checks functional claims against evidence and evaluates artifacts against nine safety properties, then tests admitted skills in a controlled environment to capture execution traces and identify failures. The approach achieves perfect precision and recall in vulnerability detection, significantly reduces attack success rates, and boosts task effectiveness and security rates in skill generation benchmarks.
arXiv AI
Jun 2
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
arXiv:2606. 01139v1 Announce Type: new Abstract: Agent skills are procedural artifacts that enable LLM agents to execute workflows, verify constraints, and recover from failures.
arXiv AI
Aug 11
SkillSentry: Reliable Skill Execution for LLM Agents via Runtime Assurance
arXiv:2608. 09253v1 Announce Type: new Abstract: LLM agents are increasingly equipped with skills to perform complex tasks through multi-step reasoning and tool use.
arXiv AI
Aug 19
TRUSS: Towards Task-Reliable and User-Safe Automated Agent Skill Generation
TRUSS is a framework that generates and verifies automated agent skills, ensuring they are both functionally effective and safe. It evaluates candidate skills against source evidence and nine safety properties, then tests them in a controlled environment to capture execution traces and identify failures. The system iteratively refines skills based on these results, achieving high precision in vulnerability detection and significantly improving task performance and security rates.
arXiv AI
Aug 17
Demystifying Agent Skills: Why They Work-Until They Don't
arXiv:2608. 14036v1 Announce Type: new Abstract: Skills have emerged as a practical and effective approach for enhancing LLM agents at inference time through structured packages of knowledge.
arXiv Computation and Language
Aug 25
Signal or Noise? A Benchmark Study of Agent Skills in Web Development
arXiv:2608.23067v1 Announce Type: new Abstract: Agent Skills are reusable procedural modules that are increasingly injected into coding-agent sessions to encode framework conventions, anti-patterns,...
Hugging Face Trending Papers
Jul 7
Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents
Large language model (LLM) agents are increasingly evaluated on their ability to use tools, plan multi-step tasks, coordinate with other agents, and operate over extended horizons. Reported benchmark gains often obscure recurring failure modes documented across otherwise unrelated evaluation efforts.
arXiv AI
Aug 11
FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents
arXiv:2608. 08570v1 Announce Type: new Abstract: Rejection sampling fine-tuning (RFT) is widely used to train code agents by generating trajectories on verifiable software engineering tasks, retaining those that pass the tests, and fine-tuning on the successful rollouts.
arXiv AI
2d ago
SkillMaster: Toward Autonomous Skill Mastery in LLM Agents
arXiv:2605.08693v3 Announce Type: replace Abstract: Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and...
arXiv AI
Jul 8
Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents
arXiv:2607. 05775v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly evaluated on their ability to use tools, plan multi-step tasks, coordinate with other agents, and operate over extended horizons.