SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

TL;DR

SkillRL introduces a hierarchical skill library and recursive evolution mechanism to improve reinforcement learning agents, enabling better generalization, reduced memory footprint, and state-of-the-art performance across complex tasks.

Contribution

It presents a novel framework combining automatic skill discovery, experience distillation, and recursive evolution to enhance agent learning and generalization.

Findings

Outperforms strong baselines by over 15.3% on multiple tasks.

Reduces token footprint while improving reasoning utility.

Maintains robustness as task complexity increases.

Abstract

Large Language Model (LLM) agents have shown stunning results in complex tasks, yet they often operate in isolation, failing to learn from past experiences. Existing memory-based methods primarily store raw trajectories, which are often redundant and noise-heavy. This prevents agents from extracting high-level, reusable behavioral patterns that are essential for generalization. In this paper, we propose SkillRL, a framework that bridges the gap between raw experience and policy improvement through automatic skill discovery and recursive evolution. Our approach introduces an experience-based distillation mechanism to build a hierarchical skill library SkillBank, an adaptive retrieval strategy for general and task-specific heuristics, and a recursive evolution mechanism that allows the skill library to co-evolve with the agent's policy during reinforcement learning. These innovations significantly reduce the token footprint while enhancing reasoning utility. Experimental results on ALFWorld, WebShop and seven search-augmented tasks demonstrate that SkillRL achieves state-of-the-art performance, outperforming strong baselines over 15.3% and maintaining robustness as task complexity increases. Code is available at this https://github.com/aiming-lab/SkillRL.