提出一种高效记忆检索框架，提升大模型长期交互能力。
Exploratory and Assimilating Reflection: Reflective Recall Cycle for Long-term Memory
- 通过探索与吸收双重反思机制，动态优化记忆检索。
- 在两个对话基准上检索准确率提升最高达17.9%。
- 适合需要低样本适应和抗噪声反馈的长期交互场景。
基于大语言模型的自主代理需要外部记忆来克服其状态缺失和上下文窗口有限的问题，以实现长期交互与动态知识推理。然而，现有记忆检索方法往往适应性差、样本效率低，难以从异构存储中精准召回混合记忆。本文提出探索-吸收式反思（EAR）框架，实现高初始检索性能与高效的样本适应。EAR结合两种机制：探索性反思通过迭代搜索为每个查询启动检索并收集有用经验；吸收性反思则从经验缓冲区回放这些经验，更高效地优化全局重排序器，优于仅依赖即时奖励的方法。实验表明，EAR在两个长期对话基准上相较基线检索器最高提升17.9%。同时，EAR表现出极高的样本效率，并对噪声反馈具有鲁棒性。
原文摘要 · Abstract (English)
LLM-based autonomous agents require external memory to overcome their statelessness and limited context window for long-term interaction and dynamic knowledge reasoning. However, existing memory retrieval methods often lack adaptability and sample efficiency, and struggle to retrieve the right mixture of memories from heterogeneous stores. We propose Exploratory-Assimilating Reflection (EAR), a framework for high initial retrieval performance and sample-efficient adaptation. EAR combines two mechanisms: Exploratory Reflection, which performs iterative search to bootstrap retrieval and collect useful experiences for each query, and Assimilating Reflection, which replays these experiences from an Experience Buffer to refine a global reranker more efficiently than methods relying only on immediate rewards. Experiments show that EAR improves retrieval by up to 17.9% over the baseline retriever on two long-term dialogue benchmarks. We also show that EAR is highly sample-efficient and robust to noisy feedback.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。