通过观察重复交互时机，智能减少大模型调用次数，节省87%记忆构建开销。
RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents
- 仅在语义相似交互持续出现时才触发大模型提取记忆
- 相比现有方法降低87%的令牌消耗，同时准确率更高
- 适合需要长期运行且资源受限的大模型代理场景
记忆系统将用户-代理交互组织为可检索的外部记忆，对克服大语言模型（LLM）上下文窗口限制、支持长周期运行至关重要。然而，现有系统对每次新交互都立即调用LLM进行记忆提取，采用激进的记忆整合策略，导致大量令牌消耗。为此，我们提出RecMem，重新思考记忆整合的时机：将新交互暂存于潜意识记忆层，并使用轻量级嵌入模型进行检索；仅当检测到语义相似交互持续出现时，才调用LLM提取情节和语义记忆。这种基于重复性的整合机制有效，因为持续出现的相似交互构成信息丰富的语义簇，值得摘要提炼。为提升准确性，RecMem还引入语义精炼机制，恢复记忆提取中遗漏的细粒度事实。实验表明，RecMem将三种主流记忆系统的记忆构建令牌成本降低最高达87%，同时超越其准确率。
原文摘要 · Abstract (English)
Memory systems often organize user-agent interactions as retrievable external memory and are crucial for long-running agents by overcoming the limited context windows of LLMs. However, existing memory systems invoke LLMs to process every incoming interaction for memory extraction, and such an eager memory consolidation scheme leads to substantial token consumption. To tackle this problem, we propose RecMem by rethinking when memory consolidation should be conducted. RecMem stores incoming interactions in a subconscious memory layer and encode them using lightweight embedding models for retrieval. LLMs are only invoked to extract episodic and semantic memory when sustained recurrence are observed for semantically similar interactions. Such recurrence-based consolidation works because these interactions correspond to a semantic cluster with rich information and thus are worth extraction and summarization. To improve accuracy, RecMem also incorporates a semantic refinement mechanism that recovers the fine-grained facts omitted by memory extraction. Experiments show that RecMem reduces the memory construction token cost of three SOTA memory systems by up to 87% while exceeding their accuracy.
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。