Newest papers

MemoryTax: The Bitter Lesson of Agent Memory

Zedong Peng · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29823 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

代理记忆系统如Mem0和Zep决定在任何问题到来之前保留什么;编码代理保留原始历史,让模型用自己的工具搜索它。我们询问设计记忆是否仍然有帮助,一旦模型足够强,以寻找自己。在一个LoCoMo对话(419转,152问题)上,我们运行四种记忆方法(完整的背景,BM25,Mem0,Zep)和三种编码代理(Pi,Codex,Claude Code),每一个具有GPT-4o-mini,GPT-6 Luna和Claude Opus 5.5,并记录每个部署成本是什么。这是一个简短的经验研究,一个对话和一个运行每个细胞。代理记忆是一个弱模型的昂贵补丁:Mem0仅击败了GPT-4o-mini的完整背景证据,并且

Machine translation (Meta M2M100); the English original follows.

Abstract

Agent memory systems such as Mem0 and Zep decide what to keep before any question arrives; coding agents keep the raw history and let the model search it with its own tools. We ask whether designed memory still helps once the model is strong enough to search for itself. On one LoCoMo conversation (419 turns, 152 questions), we run four memory methods (full context, BM25, Mem0, Zep) and three coding agents (Pi, Codex, Claude Code), each with GPT-4o-mini, GPT-6 Luna and Claude Opus 5.5, and record what every rollout costs. This is a short empirical study, with one conversation and one run per cell. Agent memory is a costly patch for a weak model: Mem0 beats full context only with GPT-4o-mini, and its build alone costs more than a whole full-context rollout. Agent memory also has a ceiling, set by the model that writes it: a stronger reader does not recover what a weaker writer left out. With Claude Opus 5.5, Pi tops the cost-accuracy frontier, scoring 99% for less than half the cost of full context; its one miss is a wrong answer key. Part of that lead comes from photo captions that only the agents could read: on the 88 questions whose evidence has no photo, Pi and full context differ by one answer.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Conversation, Computer science, Coding (social sciences), Context (archaeology), Ask price, Set (abstract data type)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange