# Zero-Mem：零 token 的 LLM 智能体记忆方案

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-08-14 03:41
- AIHOT 分数：35
- AIHOT 链接：https://aihot.virxact.com/items/cmsrxpyat04p1rozeoyj7vi7q
- 原文链接：https://x.com/rohanpaul_ai/status/2087987856195367098

## AI 摘要

Zero-Mem 提出一种无需 LLM 参与的记忆管理方法，其记忆操作使用零 LLM token，相比最快基线延迟降低 57.6%。该方法保留原始交互历史，构建实体上下文图和时间层级两种非生成视图，查询时通过确定性路由检索证据并校准结果，使最终问答外的所有记忆操作均不消耗 LLM 调用或 token。

## 正文

What if an AI agent could manage long-term memory without spending a single LLM token on the memory itself?

This paper shows an Agent memory may not need an LLM doing extra work every time it remembers something.

Zero-Mem's memory operations used zero LLM tokens and cut latency by 57.6% versus the fastest baseline in the authors' controlled comparison.

Zero-Mem keeps the original interaction history intact, then builds two non-generative views over it: an entity-context graph for relationships and a temporal hierarchy for session and local context.

At query time, deterministic routing decides how much to rely on each view, retrieves evidence, fills in relational or nearby context, and calibrates the result before the final answer model sees it.

That means every memory operation outside final QA uses zero LLM calls and zero LLM input or output tokens.

Structured agent memory can stay faithful to raw traces without turning memory management into a recurring generation problem.

- arxiv. org/abs/2607.29377

Title: "Zero-Mem: Zero-Token Memory Operations for LLM Agents"