arXiv：cs.AI（全量分类）· Mitchell Piehl, Muchao Ye·· 5 小时前AI 评分42
MemFit：高效长期智能体记忆系统
MemFit: Efficient Long-Term Agentic Memory
AI 导读
MemFit 是一个面向对话智能体的长期记忆系统，通过仅追加存储逐字保留每轮对话、以片段摘要索引而非替换原文，实现近乎瞬时且无需 LLM 的写入。它采用无 LLM 的多路径检索策略，结合词汇与语义信号及 cross-encoder 重排序，在 LoCoMo、MemGallery、LongMemEval-S 三个基准上达到 SOTA，同时将记忆构建时间与成本降低数倍。
正文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.00872 [cs.AI] |
| (or arXiv:2610.00872v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00872 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mitchell Piehl [view email]
[v1]
Thu, 1 Oct 2026 00:44:33 UTC (1,012 KB)
来源：arXiv：cs.AI（全量分类） · arxiv.org