MemMA：通过多智能体推理与原地自进化实现记忆周期协同

摘要

記憶增強型大語言模型代理通過維護外部記憶庫來支持長程交互，但現有系統大多將記憶的構建、檢索與運用視為孤立子流程。這種做法引發了兩個相互關聯的挑戰：在記憶週期的前向路徑上存在策略盲區（構建與檢索僅由局部啟發式規則驅動而缺乏顯式策略推理），以及在後向路徑上存在稀疏延遲監督（下游失誤難以轉化為記憶庫的直接修復）。為解決這些問題，我們提出MemMA——一個即插即用的多智能體框架，可協同管理記憶週期的雙向路徑。在前向路徑中，元思考器生成結構化指導方針，既在記憶構建時引導記憶管理器，又在迭代檢索時指揮查詢推理器。在後向路徑中，MemMA引入原位自演化記憶構建機制，通過合成探針問答對驗證當前記憶狀態，並在記憶固化前將失誤轉化為修復操作。在LoCoMo數據集上的大量實驗表明，MemMA在多種大語言模型基座上均持續優於現有基準方法，並能以即插即用方式提升三種不同存儲後端的性能。代碼已開源於：https://github.com/ventr1c/memma。

English

Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction, yet most existing systems treat construction, retrieval, and utilization as isolated subroutines. This creates two coupled challenges: strategic blindness on the forward path of the memory cycle, where construction and retrieval are driven by local heuristics rather than explicit strategic reasoning, and sparse, delayed supervision on the backward path, where downstream failures rarely translate into direct repairs of the memory bank. To address these challenges, we propose MemMA, a plug-and-play multi-agent framework that coordinates the memory cycle along both the forward and backward paths. On the forward path, a Meta-Thinker produces structured guidance that steers a Memory Manager during construction and directs a Query Reasoner during iterative retrieval. On the backward path, MemMA introduces in-situ self-evolving memory construction, which synthesizes probe QA pairs, verifies the current memory, and converts failures into repair actions before the memory is finalized. Extensive experiments on LoCoMo show that MemMA consistently outperforms existing baselines across multiple LLM backbones and improves three different storage backends in a plug-and-play manner. Our code is publicly available at https://github.com/ventr1c/memma.

MemMA：通过多智能体推理与原地自进化实现记忆周期协同

MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution

摘要

Support