Zedong Peng · 2026 · arXiv
DOI: 10.48550/arXiv.2610.29823 · open-access PDF
Mem0 및 Zep와 같은 에이전트 메모리 시스템은 질문이 도착하기 전에 무엇을 유지해야하는지 결정합니다; 코딩 에이전트는 원래 기록을 유지하고 모델이 자신의 도구로 검색하도록하십시오. 우리는 모델이 자신을 검색하기에 충분히 강한 경우 설계 메모리가 여전히 도움이되는지 여부를 묻습니다. 하나의 LoCoMo 대화 (419 회, 152 질문)에서 우리는 4 개의 메모리 방법 (완전한 맥락, BM25, Mem0, Zep)과 3 개의 코딩 에이전트 (Pi, Codex, Claude Code)를 실행하고 각각 GPT-4o-mini, GPT-6 Luna 및 Claude Opus 5.5를 사용하여 각 배포 비용을 기록합니다.
Machine translation (Meta M2M100); the English original follows.
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 ce
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29823, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange