Skill Learning

3 items

RESEARCHarXiv CS.AI·5/9/2026

From History to State: Constant-Context Skill Learning for LLM Agents

This paper proposes constant-context skill learning, a novel framework for LLM agents to manage recurring workflows more efficiently. It addresses privacy, cost, and capability challenges by learning reusable procedures in task-family modules and conditioning inference on a compact state block. Its effectiveness is demonstrated across benchmarks like ALFWorld, WebShop, and SciWorld.

LLM Agents reinforcement learning Skill Learning AI Research

RESEARCHarXiv CS.AI·28d ago

CoCoDA: Co-evolving Compositional DAG for Tool-Augmented Agents

CoCoDA proposes a framework for tool-augmented language models, utilizing a co-evolving compositional code DAG to manage and retrieve tools efficiently. This approach addresses challenges in scaling tool libraries by encoding typed, compositional structures and pruning candidates through symbolic signature unification.

language models Tool-Augmented Agents Compositional AI AI

RESEARCHarXiv CS.AI·4/16/2026

WebXSkill: Skill Learning for Autonomous Web Agents

This content introduces WebXSkill, a system focused on skill learning for autonomous web agents. It aims to enable AI agents to perform complex tasks on the web independently.

machine learning autonomous agents AI Skill Learning