arXiv cs.CL· Wujiang Xu, Jiaojiao Han, Xi Zhu, Qizheng Zhang, Kaiqu Liang, Yutong Yin, Kai Mei, Dimitris N. Metaxas·· 12 小时前AI 评分38
FlexA-Mem：面向 LLM 智能体的预算自适应智能体记忆
FlexA-Mem: Budget-Adaptive Agentic Memory for LLM Agents
AI 导读
FlexA-Mem 提出一种通用记忆方案，将每段历史一次性写入不可变存储，每次调用时按预算渲染紧凑时间线与细节，无需 LLM 调用。在 AppWorld 4k 挑战任务上，它比第二名方法高 11.5%；在 147 个未使用任务上比带摘要的 A-Mem 高 12.2%。
正文
Abstract:Large language model (LLM) agents work in scenarios with very different memory needs. A question about past conversations needs the exact facts it names, while a multi-step task needs a trace of the steps already taken together with details that the next step cannot name. Existing memories are each designed and tested for one kind of scenario. Retrieval memories such as A-Mem miss steps that the current query does not express, summaries drop exact strings, and pairing the two fixes the split of the budget in advance. We propose FlexA-Mem, a general memory that writes each unit of history once into an immutable store and renders a fresh memory for every call. The rendered memory is a compact timeline of records plus detail that a fixed rule fits into the remaining room without an LLM call. The detail is either relevant units as raw text or excerpts or the verbatim pieces that best match the query. With one store, FlexA-Mem serves both kinds of scenario. On AppWorld challenge tasks at 4k, it outperforms the second-best method by 11.5%, and on 147 unused tasks with predictions fixed in advance it outperforms A-Mem with a summary by 12.2%. On LongMemEval and LoCoMo, it matches a dedicated keyword retriever that writes no memory, while memories built on text written by an LLM fall far behind at tight budgets. Ablations show that the timeline carries AppWorld completion, whereas recovery mainly saves steps there and decides accuracy on exact facts. Code is available at this https URL
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.33274 [cs.CL] |
| (or arXiv:2610.33274v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33274 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wujiang Xu [view email]
[v1]
Fri, 23 Oct 2026 20:34:09 UTC (221 KB)
来源：arXiv cs.CL · arxiv.org