发表机构
The University of Iowa（爱荷华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有LLM记忆系统写入成本高的问题，提出MemFit，通过逐字存储与无需LLM的多路径检索，在三个基准上实现最先进性能并大幅降低构建成本。
AI 中文摘要
针对大型语言模型（LLM）的长期记忆系统在扩展跨应用推理能力方面日益流行。当前的记忆系统依赖LLM智能体来组织和整合记忆，导致写入操作成本高昂且效率低下。为解决这一局限，我们提出MemFit，一种面向对话智能体的长期记忆系统，旨在降低记忆操作的成本和延迟。与现有依赖昂贵的LLM调用进行记忆构建或通过压缩丢弃表面细节的系统不同，MemFit将每一轮对话逐字存储于仅追加的存储中，实现近乎即时、无需LLM的插入，并使用分段摘要为对话轮次建立索引，而非替换它们。此外，MemFit采用无需LLM的多路径检索策略，结合词汇和语义信号，并在文本和多模态设置中对带标题增强的情节进行交叉编码器重排序。在三个广泛使用的基准测试（LoCoMo、MemGallery和LongMemEval-S）上的实证结果表明，MemFit在实现最先进性能的同时，将记忆构建时间和成本降低了数倍，为持久智能体记忆提供了可扩展且高效的解决方案。
英文摘要
Long-term memory systems for large language models (LLMs) have gained popularity for extending reasoning capabilities across applications. Current memory systems rely on LLM agents to organize and consolidate memory, resulting in costly, inefficient write operations. To address this limitation, we propose MemFit, a long-term memory system for conversational agents that reduces the cost and latency of memory operations. Unlike existing systems that rely on expensive LLM calls for memory construction or discard surface-level details through compression, MemFit stores each turn verbatim in an append-only store with near-instantaneous, LLM-free insertion, indexing turns with segment summaries rather than replacing them. Additionally, MemFit uses an LLM-free, multi-path retrieval strategy that combines lexical and semantic signals with cross-encoder reranking over caption- augmented episodes in both textual and multimodal settings. Empirical results on three widely used benchmarks, LoCoMo, MemGallery, and LongMemEval-S, show that MemFit achieves state-of-the-art performance while reducing memory construction time and cost several-fold, providing a scalable and efficient solution for persistent agentic memory.
