{"slug": "from-memory-to-skills-evidence-grounded-co-evolution-governance-for-long-horizon", "title": "From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents", "summary": "A new training-free framework, Memory--Skill Co-Evolution (MSCE), enables long-horizon LLM agents to convert passive memory traces into reusable skills, outperforming state-of-the-art baselines on EvoAgentBench and LoCoMo benchmarks. The method, detailed in arXiv:2607.16621v1, uses evidence-grounded policies and reflection-weighted value backfilling to govern co-evolution of memory and skills, demonstrating strong cross-domain transferability.", "body_md": "arXiv:2607.16621v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/from-memory-to-skills-evidence-grounded-co-evolution-governance-for-long-horizon", "canonical_source": "https://arxiv.org/abs/2607.16621", "published_at": "2026-07-21 04:00:00+00:00", "updated_at": "2026-07-21 04:22:36.115490+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research"], "entities": ["MSCE", "EvoAgentBench", "LoCoMo"], "alternates": {"html": "https://wpnews.pro/news/from-memory-to-skills-evidence-grounded-co-evolution-governance-for-long-horizon", "markdown": "https://wpnews.pro/news/from-memory-to-skills-evidence-grounded-co-evolution-governance-for-long-horizon.md", "text": "https://wpnews.pro/news/from-memory-to-skills-evidence-grounded-co-evolution-governance-for-long-horizon.txt", "jsonld": "https://wpnews.pro/news/from-memory-to-skills-evidence-grounded-co-evolution-governance-for-long-horizon.jsonld"}}