Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents
cs.AI, cs.LG
Submitted: 2026-05-29
Updated: 2026-11-02
Terminology
Sources
- EvoSkill: Automated Skill Discovery for Multi-Agent Systems
- Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study
- CUA-Skill: Develop Skills for Computer Using Agent
- How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study
- AgentOps: Enabling Observability of LLM Agents
- Audited Skill-Graph Self-Improvement for Agentic LLMs via Verifiable Rewards, Experience Synthesis, and Continual Memory
- XSkill: Continual Learning from Experience and Skills in Multimodal Agents
- Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
- SkillNet: Create, Evaluate, and Connect AI Skills
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- Harnessing LLM Agents with Skill Programs
- SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
- "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
- How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
- ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents
- SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
- Skills as Verifiable Artifacts: A Trust Schema and a Biconditional Correctness Criterion for Human-in-the-Loop Agent Runtimes
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents