arXiv cs.CL· Xuan He, Sining Zhoubian, Ruozhen Yang, Yuhao Wen, Zhineng Wang, Yuyang Hu, Ke Yang, Yuyu Zhang, Ping Nie, Jiawei Han, ChengXiang Zhai·· 12 小时前AI 评分58
Memory Tax：拆解智能体记忆的净价值
Memory Tax: Dissecting the Net Value of Agent Memory
AI 导读
arXiv 论文 Memory Tax 通过跨多个基准和模型主干的评测发现，许多专用记忆系统在不少情况下不如朴素 RAG，净价值为负。作者以 RAG 为参照，把记忆的净价值拆成相对直接检索的收益与损耗，分别称为 memory benefit 和 memory tax，并重点分析后者如何从系统与评测两侧产生。作者表示将开源代码与结果。
正文
Authors:Xuan He, Sining Zhoubian, Ruozhen Yang, Yuhao Wen, Zhineng Wang, Yuyang Hu, Ke Yang, Yuyu Zhang, Ping Nie, Jiawei Han, ChengXiang Zhai
Abstract:Memory is increasingly used in long-horizon agents, yet the net value of building memory over direct retrieval from raw history remains largely unclear. Through a large-scale evaluation across multiple benchmarks and model backbones, we find many dedicated memory systems underperform naive RAG in many cases, indicating a negative net value. Taking RAG as a reference, we dissect the net value of memory into the gains and losses over direct retrieval, termed memory benefit and memory tax. These gains and losses arise because memory process changes how the raw information is organized and accessed. We view such changes as the double-edged deviations from the raw history. They are originally designed and introduced to benefit the task, for example by reorganizing facts or distilling preferences, but some may also remove or obscure evidence, giving rise to memory tax. Since memory benefit reflects the expected gains of its design, we then focus more on the overlooked memory tax, study how it arises from the system and evaluation side, and generalize the concept to more application scenarios of memory. We hope the notion of memory tax can provide a new lens and shift more attention from standalone performance to the net value of memory, informing more reliable memory designs and evaluations. We will open-source the code and results to the community. Project Page: this https URL
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.34073 [cs.CL] |
| (or arXiv:2610.34073v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34073 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xuan He [view email]
[v1]
Sun, 25 Oct 2026 05:29:05 UTC (10,309 KB)
来源：arXiv cs.CL · arxiv.org