记忆是重构的，而非检索的：面向LLM智能体的图记忆

摘要

尽管近期取得了一定进展，但大语言模型（LLM）智能体在处理长交互历史推理时仍面临挑战。当前基于记忆增强的智能体依赖静态"检索-推理"范式，这种僵化的流水线设计使其无法根据推理过程中发现的中间证据动态调整记忆访问。为解决这一局限，我们提出MRAgent框架，该框架将联想记忆图与主动重构机制相结合。我们将记忆表示为线索-标签-内容图，其中联想标签作为语义桥梁，连接细粒度线索与记忆内容。基于此结构，主动重构机制将LLM推理直接融入记忆访问过程，使智能体能够基于累积证据迭代式地探索和修剪检索路径。这确保记忆检索能根据推理上下文动态调整，同时避免无约束扩展导致的组合爆炸问题。在LoCoMo基准和LongMemEval基准上的实验表明，该方法相比强基线模型取得了显著提升（最高达23%），同时大幅降低了令牌消耗与运行时间成本，凸显了主动联想重构在长跨度记忆推理中的有效性。

English

Despite recent progress, LLM agents still struggle with reasoning over long interaction histories. While current memory-augmented agents rely on a static retrieve-then-reason paradigm, this rigid pipeline design prevents them from dynamically adapting memory access to intermediate evidence discovered during inference. To bridge this gap, we propose MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism. We represent memory as a Cue-Tag-Content graph, where associative tags serve as semantic bridges connecting fine-grained cues to memory contents. Operating on this structure, our active reconstruction mechanism integrates LLM reasoning directly into memory access, allowing the agent to iteratively explore and prune retrieval paths based on accumulated evidence. This ensures that memory retrieval is dynamically adapted to the reasoning context while avoiding combinatorial explosion caused by unconstrained expansion. Experiments on the LoCoMo benchmark and LongMemEval benchmark demonstrate significant improvements over strong baselines (up to 23%), while substantially reducing token and runtime cost, highlighting the effectiveness of active and associative reconstruction for long-horizon memory reasoning.