From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents

2026-07-17

AI Summary

This work proposes the MSCE framework, which introduces the first training-free mechanism for the co-evolution of memory and skills in long-horizon LLM agents. Unlike existing memory systems that treat historical trajectories as passive context, MSCE actively structures experience into concrete step-wise trajectories, reusable procedural policies, and environmental knowledge. It dynamically distills, validates, and retrieves reliable skills through evidence-anchored L2 policy crystallization and reflection-weighted value backfilling. The framework enables precise skill boundary delineation, decision guidance, and reliability estimation. Evaluated on EvoAgentBench and LoCoMo benchmarks, MSCE significantly outperforms current skill-augmented and memory-driven approaches, demonstrating exceptional cross-domain transfer and continual evolution capabilities.

Abstract

Existing memory systems for long-horizon LLM agents often retrieve prior traces as passive context rather than converting them into executable capabilities. In this paper, we propose MSCE, a training-free Memory--Skill Co-Evolution framework that organizes agent experience into grounded step traces, reusable procedural policies, and declarative environmental cognition. MSCE crystallizes evidence-backed L2 policies with positive estimated gain into callable skills that retain evidence links, applicability boundaries, decision guidance, verification rules, and reliability estimates. It further introduces reflection-weighted value backfilling, which propagates sparse terminal feedback through dense local self-reflections to produce evidence-calibrated trace values for governing memory and skill evolution. Experiments on EvoAgentBench and LoCoMo demonstrate that MSCE significantly outperforms state-of-the-art skill-augmented and memory-driven agent baselines, exhibiting strong cross-domain transferability and lifelong-evolution capabilities.

Problem

• long-horizon LLM agents
• memory systems
• executable capabilities
• skill acquisition
• experience utilization

Innovation

• Memory-Skill Co-Evolution
• Evidence-Grounded Skills
• Reflection-Weighted Value Backfilling
• Long-Horizon LLM Agents
• Training-Free Framework