MSCE: Training-Free Memory-Skill Co-Evolution Framework for Long-Horizon LLM Agents
Researchers introduce MSCE, a training-free framework that organizes agent experience into reusable procedural skills and declarative environmental knowledge. MSCE employs reflection-weighted value backfilling to guide the evolution of memory and skills, enabling agents to autonomously crystallize and refine capabilities from experience. Experimental results on EvoAgentBench and LoCoMo show that MSCE significantly outperforms state-of-the-art skill-augmented and memory-driven agent baselines, with strong cross-domain transfer and lifelong learning abilities.
Why it matters: This work advances the autonomous evolution of LLM agent capabilities without retraining, supporting more robust lifelong learning and cross-domain adaptability.
Full story at: arXiv Computation and Language ↗