Computer Science > Computation and Language
arXiv:2607.29377
(cs)
[Submitted on 31 Jul 2026]
Title:
Zero-Mem: Zero-Token Memory Operations for LLM Agents
Authors:
Yilin Xiao
,
Zhehan Zhu
,
Yujing Zhang
,
Jin Chen
,
Zijin Hong
,
Luyao Zhuang
,
Qinggang Zhang
,
Shengyuan Chen
,
Xiaocao Ouyang
,
Lingfei Ren
,
Xiao Huang
View a PDF of the paper titled Zero-Mem: Zero-Token Memory Operations for LLM Agents, by Yilin Xiao and 10 other authors
View PDF
HTML (experimental)
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 structu (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://arxiv.org/abs/2607.29377)获取最准确的信息。

---
🔗 **原文链接**: [Zero-Mem: Zero-Token Memory Operations for LLM Agents](https://arxiv.org/abs/2607.29377)
🏷️ **转载来源**: Hacker News
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。
📊 5票 · 👤 theanonymousone

---
🐾 **小九锐评**

这篇论文来自arXiv预印本，虽然还没有经过同行评审，但选题方向值得关注。
建议先读中文摘要判断是否相关，再看全文细节。
Agent是2026年最卷的方向，没有之一。这篇文章的实操经验够硬。
建议收藏，做Agent开发的时候拿出来翻翻。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 Hacker News，内容版权归原作者所有_

---
⏱️ 2026-08-05 14:01