LLM Agent Skill Learning

LLM: Large Language Model

Overview

This field asks how language-model agents can turn experience, demonstrations, external guides, or feedback into reusable procedures for tasks such as tool use, web navigation, coding, and embodied control. Common approaches distill skills from successful and failed trajectories into text, executable programs, or hierarchical libraries, then retrieve, compose, verify, and revise them; other methods train agents to internalize skills through supervised fine-tuning or reinforcement learning. Work is evaluated on interactive benchmarks such as ALFWorld, WebShop, AppWorld, and coding tasks, with attention to success, transfer, token cost, and consistency. A central challenge is that skills can help when relevant but cause regressions when stale, poorly selected, or applied outside their scope, making reliable validation, lifecycle management, and safety essential.

Latest papers

CardsList

428 papers44 papers in the last four weeks, down 42% on the four weeks before. 0.3% of all new papers.

  1. SkillOrchestra: Learning to Route Agents via Skill Transfer

    Feb 23, 2026Jiayu Wang, Yifei Ming, Zixuan Ke +3LLM Agent OrchestrationLLM Agent Routing

  2. Hybrid-Gym: Training Coding Agents to Generalize Across Tasks

    Feb 18, 2026Yiqing Xie, Emmy Liu, Gaokai Zhang +7AI Coding AgentsSoftware Engineering Agents

  3. Evolutionary Context Search for Automated Skill Acquisition

    Feb 18, 2026Qi Sun, Stefan Nielsen, Rio Yokota +1Retrieval-Augmented ICLLLM Agent Skill Learning

  4. SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

    Feb 9, 2026Peng Xia, Jianwen Chen, Hanyang Wang +10LLM Agent Skill LearningRL for LLM Agents

  5. MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

    Feb 2, 2026Haozhen Zhang, Quanyu Long, Jianzhu Bao +4Memory Management for LLM AgentsMemory Consolidation for LLM Agents

  6. SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models

    Jan 7, 2026Yuxuan Jiang, Francis FerraroProcess Reward ModelsRL for Language Model Reasoning

  7. Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization

    Feb 3, 2025Minttu Alakuijala, Ya Gao, Georgy Ananov +4Continual Learning for LLM AgentsLLM Agent Skill Learning