Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2512.10696 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913031612530688 |
|---|---|
| author | Cao, Zouying Deng, Jiaji Yu, Li Zhou, Weikang Liu, Zhaoyang Ding, Bolin Zhao, Hai |
| author_facet | Cao, Zouying Deng, Jiaji Yu, Li Zhou, Weikang Liu, Zhaoyang Ding, Bolin Zhao, Hai |
| contents | 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scenario-aware indexing; and 3) $\textit{utility-based refinement}$, which autonomously adds valid memories and prunes outdated ones to maintain a compact, high-quality experience pool.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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_10696 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution Cao, Zouying Deng, Jiaji Yu, Li Zhou, Weikang Liu, Zhaoyang Ding, Bolin Zhao, Hai Artificial Intelligence Computation and Language 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. |
| title | Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2512.10696 |