SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles

• 类型：arxiv
• 标识：2610.09832
• 链接：https://arxiv.org/abs/2610.09832
• 主分类：agent
• 形态：method
• TLDR：Memory-augmented reinforcement learning strengthens LLM agents' ability to solve complex long-horizon tasks. Skills are one such form of memory, pairing instructions with an applicability condition over task types. However, retaining every skill indiscriminately as the policy improves lets obsolete or harmful entries accumulate and mislead the agent. We propose SkillForge, an agentic RL method that compiles and evolves the skill library through a fitness-driven skill lifecycle of trial, active, stable, and retired states, so that the skills and the model co-evolve throughout training. A pre-RL
• 待LLM分类：否
• 来源文件：
• /inbox/tom/_candidates/2026-10-08-agent-rag-longcontext-candidates.json