Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
- URL: http://arxiv.org/abs/2512.10696v1
- Date: Thu, 11 Dec 2025 14:40:01 GMT
- Title: Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
- Authors: Zouying Cao, Jiaji Deng, Li Yu, Weikang Zhou, Zhaoyang Liu, Bolin Ding, Hai Zhao,
- Abstract summary: We propose $textbfReMe$ ($textitRemember Me, Refine Me$) to bridge the gap between static storage and dynamic reasoning.<n>ReMe innovates across the memory lifecycle via three mechanisms: $textitmulti-faceted distillation$, which extracts fine-grained experiences.<n>Experiments on BFCL-V3 and AppWorld demonstrate that ReMe establishes a new state-of-the-art in agent memory system.
- Score: 52.76038908826961
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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scenario-aware indexing; and 3) $\textit{utility-based refinement}$, which autonomously adds valid memories and prunes outdated ones to maintain a compact, high-quality experience pool.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.
Related papers
- Mem-T: Densifying Rewards for Long-Horizon Memory Agents [23.19373149519922]
We introduce Mem-T, an autonomous memory agent that interfaces with a lightweight hierarchical memory database to perform dynamic updates and multi-turn retrieval over streaming inputs.<n>We also propose MoT-GRPO, a tree-guided reinforcement learning framework that transforms sparse terminal feedback into dense, step-wise supervision via memory operation tree backpropagation and hindsight credit assignment.
arXiv Detail & Related papers (2026-01-30T14:23:33Z) - MemRec: Collaborative Memory-Augmented Agentic Recommender System [57.548438733740504]
We propose MemRec, a framework that architecturally decouples reasoning from memory management.<n>MemRec introduces a dedicated LM_Mem to manage a dynamic collaborative memory graph.<n>It achieves state-of-the-art performance on four benchmarks.
arXiv Detail & Related papers (2026-01-13T18:51:16Z) - Memory in the Age of AI Agents [217.9368190980982]
This work aims to provide an up-to-date landscape of current agent memory research.<n>We identify three dominant realizations of agent memory, namely token-level, parametric, and latent memory.<n>To support practical development, we compile a comprehensive summary of memory benchmarks and open-source frameworks.
arXiv Detail & Related papers (2025-12-15T17:22:34Z) - Agentic Learner with Grow-and-Refine Multimodal Semantic Memory [50.81667005063605]
ViLoMem is a dual-stream memory framework that constructs compact, schema-based memory.<n>It encodes visual distraction patterns and logical reasoning errors, enabling MLLMs to learn from their successful and failed experiences.
arXiv Detail & Related papers (2025-11-26T18:55:08Z) - MemGen: Weaving Generative Latent Memory for Self-Evolving Agents [57.1835920227202]
We propose MemGen, a dynamic generative memory framework that equips agents with a human-esque cognitive faculty.<n>MemGen enables agents to recall and augment latent memory throughout reasoning, producing a tightly interwoven cycle of memory and cognition.
arXiv Detail & Related papers (2025-09-29T12:33:13Z) - ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory [21.4675019810992]
Concept-level memory is reusable, modular abstractions distilled from solution traces and stored in natural language.<n>We evaluate on ARC-AGI, a benchmark that stresses compositional generalization and abstract reasoning.<n>We find abstract concepts to be the most consistent memory design, outscoring the baseline at all tested inference compute scales.
arXiv Detail & Related papers (2025-09-04T17:54:19Z) - Memp: Exploring Agent Procedural Memory [72.41472703974935]
Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters.<n>We propose Memp that distills past agent trajectories into both fine-grained, step-by-step instructions and higher-level, script-like abstractions.<n>We show that as the memory repository is refined, agents achieve steadily higher success rates and greater efficiency on analogous tasks.
arXiv Detail & Related papers (2025-08-08T16:20:56Z) - G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems [44.844636264484905]
Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents.<n>We introduce G-Memory, a hierarchical, agentic memory system for MAS inspired by organizational memory theory.<n>G-Memory improves success rates in embodied action and accuracy in knowledge QA by up to $20.89%$ and $10.12%$, respectively.
arXiv Detail & Related papers (2025-06-09T03:43:46Z) - R$^3$Mem: Bridging Memory Retention and Retrieval via Reversible Compression [24.825945729508682]
We propose R$3$Mem, a memory network that optimize both information Retention and Retrieval.<n>R$3$Mem employs virtual memory tokens to compress and encode infinitely long histories, further enhanced by a hierarchical compression strategy.<n>Experiments demonstrate that our memory design achieves state-of-the-art performance in long-context language modeling and retrieval-augmented generation tasks.
arXiv Detail & Related papers (2025-02-21T21:39:00Z)
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.