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

• URL: http://arxiv.org/abs/2607.16621v1
• Date: Sat, 18 Jul 2026 03:46:22 GMT
• Title: From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents
• Abstract summary: MSCE organizes agent experience into grounded step traces, reusable procedural policies, and declarative environmental cognition.<n>It 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.<n>Experiments on EvoAgentBench and LoCoMo demonstrate that MSCE significantly outperforms state-of-the-art skill-augmented and memory-driven agent baselines.
• Score: 38.90736857557396
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents [16.193335398478386]
  Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts windows.<n>Existing systems treat retention as local and do not model long-term consequences under observability constraints.<n>We propose OSL-MR, a learning-augmented framework that enforces a strict separation between online-observable features and offline-available supervision.
  arXiv  Detail & Related papers  (2026-06-09T09:15:33Z)
• MemEvoBench: Benchmarking Memory MisEvolution in LLM Agents [78.95081012334116]
  Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks.<n> contaminated or biased memory accumulation can trigger abnormal agent behaviors.<n>MemeEvoBench is the first benchmark evaluating memory safety in LLM agents against adversarial memory injection, noisy tool outputs, and biased feedback.
  arXiv  Detail & Related papers  (2026-04-17T07:29:52Z)
• TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking [32.57514611558346]
  Test-time evolution of agent memory serves as a pivotal paradigm for achieving AGI.<n>Agent safety alignment remains vulnerable to a phenomenon known as Agent Memory Misevolution.<n>We propose TAME, a dual-memory evolutionary framework that separately evolves memory to improve task performance.
  arXiv  Detail & Related papers  (2026-02-03T07:52:26Z)
• ProcMEM: Learning Reusable Procedural Memory from Experience via Non-Parametric PPO for LLM Agents [31.24386037416211]
  LLM-driven agents often rely on on-the-fly reasoning, re-deriving solutions even in recurring scenarios.<n>This insufficient experience reuse leads to computational redundancy and execution instability.<n>We propose ProcMEM, a framework that enables agents to autonomously learn procedural memory from interaction experiences without parameter updates.
  arXiv  Detail & Related papers  (2026-02-02T09:43:12Z)
• GLOVE: Global Verifier for LLM Memory-Environment Realignment [15.456830820378656]
  We propose a framework that introduces a new design dimension for Large Language Model memory systems by establishing a relative notion of truth.<n>GLOVE enables memory-environment realignment by verifying and updating memory without access to ground-truth supervision or strong reliance on model introspection.<n>Our results show that GLOVE substantially improves agent success rates, suggesting a robust pathway to cognitive agents capable of self-evolving.
  arXiv  Detail & Related papers  (2026-01-27T06:32:05Z)
• MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory [46.632646462295234]
  We propose MemRL, a framework that enables agents to self-evolve via non-parametric reinforcement learning on episodic memory.<n>MemRL employs a Two-Phase Retrieval mechanism that filters candidates by semantic relevance and then selects them based on learned Q-values.<n>Our analysis experiments confirm that MemRL effectively reconciles the stability-plasticity dilemma, enabling continuous runtime improvement without weight updates.
  arXiv  Detail & Related papers  (2026-01-06T17:14:50Z)
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory [89.65731902036669]
  Evo-Memory is a streaming benchmark and framework for evaluating self-evolving memory in large language model (LLM) agents.<n>We evaluate over ten representative memory modules and evaluate them across 10 diverse multi-turn goal-oriented and single-turn reasoning and QA datasets.
  arXiv  Detail & Related papers  (2025-11-25T21:08:07Z)
• Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent [6.300669721057781]
  Meta-Policy Reflexion (MPR) is a framework that consolidates LLM-generated reflections into a structured, predicate-like Meta-Policy Memory (MPM)<n>MPR externalizes reusable corrective knowledge without model weight updates, enforces domain constraints to reduce unsafe or invalid actions, and retains the adaptability of language-based reflection.<n> Empirical results reported in the supplied material indicate consistent gains in execution accuracy and robustness when compared to Reflexion baselines; rule admissibility further improves stability.
  arXiv  Detail & Related papers  (2025-09-04T08:18:39Z)
• How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior [65.70584076918679]
  Memory is a critical component in large language model (LLM)-based agents.<n>This paper studies how memory management choices impact the LLM agents' behavior, especially their long-term performance.
  arXiv  Detail & Related papers  (2025-05-21T22:35:01Z)
• ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation [91.20492150248106]
  We investigate the internal mechanisms behind unfaithful generation and identify a subset of mid-to-deep feed-forward networks (FFNs) that are disproportionately activated in such cases.<n>We propose Parametric Knowledge Muting through FFN Suppression (ParamMute), a framework that improves contextual faithfulness by suppressing the activation of unfaithfulness-associated FFNs.<n> Experimental results show that ParamMute significantly enhances faithfulness across both CoFaithfulQA and the established ConFiQA benchmark, achieving substantial reductions in reliance on parametric memory.
  arXiv  Detail & Related papers  (2025-02-21T15:50:41Z)
• TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs [50.259001311894295]
  We propose a novel TRansformer-based Attribution framework using Contrastive Embeddings called TRACE. We show that TRACE significantly improves the ability to attribute sources accurately, making it a valuable tool for enhancing the reliability and trustworthiness of large language models.
  arXiv  Detail & Related papers  (2024-07-06T07:19:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.