SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
Paper • 2605.24117 • Published • 20
Skill
-
-
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
Paper • 2605.27366 • Published • 24 -
SkillGrad: Optimizing Agent Skills Like Gradient Descent
Paper • 2605.27760 • Published • 27 -
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
Paper • 2605.28424 • Published • 27 -
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 213 -
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
Paper • 2605.06130 • Published • 111 -
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 53 -
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 291 -
Memento-Skills: Let Agents Design Agents
Paper • 2603.18743 • Published • 58 -
MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
Paper • 2602.02474 • Published • 63 -
Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
Paper • 2604.05333 • Published • 22 -
Skill Retrieval Augmentation for Agentic AI
Paper • 2604.24594 • Published -
GraSP: Graph-Structured Skill Compositions for LLM Agents
Paper • 2604.17870 • Published -
Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
Paper • 2604.10674 • Published -
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
Paper • 2605.18401 • Published • 126 -
SkillNet: Create, Evaluate, and Connect AI Skills
Paper • 2603.04448 • Published • 94 -
SkillOrchestra: Learning to Route Agents via Skill Transfer
Paper • 2602.19672 • Published • 58 -
SkillOS: Learning Skill Curation for Self-Evolving Agents
Paper • 2605.06614 • Published • 46 -
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Paper • 2604.04804 • Published • 35 -
SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents
Paper • 2604.17308 • Published • 22 -
SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks
Paper • 2604.20087 • Published • 15 -
Toward Scalable Terminal Task Synthesis via Skill Graphs
Paper • 2604.25727 • Published • 11 -
SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
Paper • 2605.05726 • Published • 1 -
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
Paper • 2602.12670 • Published • 62 -
SkillReducer: Optimizing LLM Agent Skills for Token Efficiency
Paper • 2603.29919 • Published -
Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
Paper • 2605.16986 • Published -
SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
Paper • 2605.09341 • Published