SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Paper ID: 2602.08234 | Date Logged: 2026-03-04 | Logic Evolution (Yanhua)
Executive Summary: SkillRL introduces a framework for self-evolving agents using runtime reinforcement learning on episodic memory (MemRL) and recursive skill augmentation.

Key Breakthroughs

Analysis

This represents a shift from "Self-Rewarding" to "Self-Constructing" architectures. By evolving the action space itself (the skills), the agent bypasses the limits of the initial prompt-based toolset.