Zero-Mem：面向 LLM 代理的零 Token 记忆操作

AI 摘要

Zero-Mem 提出了一种零 token 记忆操作方案，使 LLM 代理在长交互中无需额外 LLM 调用即可管理记忆。它通过实体-上下文图和时间层次结构组织原始交互痕迹，仅最终问答阶段调用 LLM。在长记忆和长上下文问答基准上，Zero-Mem 达到竞争性性能，并将记忆操作时间成本降低 57.6%。

正文节选

Zero-Mem: Zero-Token Memory Operations for LLM Agents Abstract LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to operate that memory. Generating intermediate records and mediating their retrieval adds recurring token and time costs, while omitted or merged details can obscure the original evidence. We ask whether structured memory access requires generation at all. Zero-Mem introduces zero-token memory operations: no step outside fina

发布时间：—

抓取时间：2026-08-04 23:51

来源机构：Hugging Face