检索驱动的记忆再巩固机制用于长期LLM智能体
Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents
- Shanghai Jiao Tong University（上海交通大学）
- National University of Singapore（新加坡国立大学）
- OPPO
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
受认知神经科学启发，提出REALM框架，通过自主组织异质认知图、自适应图搜索和基于检索反馈的记忆再巩固，实现LLM智能体长期记忆的持续演化，在LoCoMo和LongMemEval上分别提升7.17和1.31个百分点。
AI中文摘要：
长期记忆对于在长时间交互中运行的基于LLM的智能体至关重要。现有的记忆系统主要在新信息到达时更新记忆，将检索视为记忆访问的终点，而非记忆演化的驱动力。因此，检索反馈很少被利用来持续重组记忆以服务于未来的访问。此外，大多数现有方法依赖预定义的记忆结构和固定的检索流程，限制了智能体自主组织和演化自身记忆的能力。受认知神经科学中记忆再巩固机制的启发，我们提出了REALM，一个再巩固-演化智能体长期记忆框架。它将长期记忆建模为一个持续的生命周期，通过自主将记忆组织成异质认知图，通过自适应组合的图搜索原子来检索证据，并基于检索反馈持续进行记忆再巩固。REALM在LoCoMo上达到了75.97%的平均准确率，在LongMemEval上达到了65.11%，分别比最强基线高出7.17和1.31个百分点。消融研究证实，记忆再巩固能持续提升性能，进一步的分析表明，它会逐步将相关的记忆单元重组为更连贯的局部结构，以便在推理过程中进行集体证据回忆和利用。这些结果表明，检索驱动的记忆再巩固为LLM智能体中长期记忆的持续演化提供了一种有效机制。
英文摘要：
Long-term memory is essential for LLM-based agents operating over extended interactions. Existing memory systems primarily update memory when new information arrives, treating retrieval as the endpoint of memory access rather than a driver of memory evolution. Consequently, retrieval feedback is rarely exploited to reorganize memory for future access continuously. Moreover, most existing approaches rely on predefined memory structures together with fixed retrieval pipelines, limiting the agent's ability to organize and evolve its own memory autonomously. Inspired by memory reconsolidation in cognitive neuroscience, we propose \textbf{REALM}, a \textbf{r}econsolidation-\textbf{e}volution \textbf{a}gentic \textbf{l}ong-term \textbf{m}emory framework. It models long-term memory as a continual lifecycle by autonomously organizing memories into a heterogeneous cognitive graph, retrieving evidence via adaptively composed graph-search atoms, and continually reconsolidating memories based on retrieval feedback. REALM achieves an average accuracy of 75.97\% on LoCoMo and 65.11\% on LongMemEval, outperforming the strongest baselines by 7.17 and 1.31 points respectively. Ablation studies confirm that memory reconsolidation consistently boosts performance, with further analyses revealing that it progressively reorganizes related memory units into more coherent local structures for collective evidence recall and utilization during reasoning. These results suggest that retrieval-driven memory reconsolidation provides an effective mechanism for continually evolving long-term memory in LLM agents.
