{"ID":2830295,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.10696","arxiv_id":"2512.10696","title":"Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution","abstract":"Procedural memory enables large language model (LLM) agents to internalize \"how-to\" knowledge, theoretically reducing redundant trial-and-error. However, existing frameworks predominantly suffer from a \"passive accumulation\" paradigm, treating memory as a static append-only archive. To bridge the gap between static storage and dynamic reasoning, we propose $\\textbf{ReMe}$ ($\\textit{Remember Me, Refine Me}$), a comprehensive framework for experience-driven agent evolution. ReMe innovates across the memory lifecycle via three mechanisms: 1) $\\textit{multi-faceted distillation}$, which extracts fine-grained experiences by recognizing success patterns, analyzing failure triggers and generating comparative insights; 2) $\\textit{context-adaptive reuse}$, which tailors historical insights to new contexts via scenario-aware indexing; and 3) $\\textit{utility-based refinement}$, which autonomously adds valid memories and prunes outdated ones to maintain a compact, high-quality experience pool. Extensive experiments on BFCL-V3 and AppWorld demonstrate that ReMe establishes a new state-of-the-art in agent memory system. Crucially, we observe a significant memory-scaling effect: Qwen3-8B equipped with ReMe outperforms larger, memoryless Qwen3-14B, suggesting that self-evolving memory provides a computation-efficient pathway for lifelong learning. We release our code and the $\\texttt{reme.library}$ dataset to facilitate further research.","short_abstract":"Procedural memory enables large language model (LLM) agents to internalize \"how-to\" knowledge, theoretically reducing redundant trial-and-error. However, existing frameworks predominantly suffer from a \"passive accumulation\" paradigm, treating memory as a static append-only archive. To bridge the gap between static sto...","url_abs":"https://arxiv.org/abs/2512.10696","url_pdf":"https://arxiv.org/pdf/2512.10696v2","authors":"[\"Zouying Cao\",\"Jiaji Deng\",\"Li Yu\",\"Weikang Zhou\",\"Zhaoyang Liu\",\"Bolin Ding\",\"Hai Zhao\"]","published":"2025-12-11T14:40:01Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}