Skip to content
English

Switch theme

arXiv 2610.30755 · cs.AI · 2026-10-22

Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought

Zhengye Bao, Shengtao Zhang, Haokai Zhang, Shiqi Lou, Muning Wen, Minnan Luo

Xi'an Jiaotong University

In latest · #295 Added on 2026-10-26

One-line takeaway

A naive RAG baseline (dense retrieval plus reranking over raw history) ranks first in six of seven settings across LoCoMo, LongMemEval, MEME and MemoryAgentBench, beating the strongest agentic memory system by 0.13–5.53 points thanks to higher evidence coverage.

论文发现朴素 RAG(对原始对话历史做稠密检索加重排)在 LoCoMo、LongMemEval 等长期记忆评测的 7 个设置里 6 个排第一,比最强的复杂智能体记忆系统高 0.13–5.53 分,原因是它对必要证据的覆盖更高。

27HF upvotes
27GitHub stars
0Citations (Semantic Scholar)
45.0Buzz score

Read on arXiv PDF Hugging Face discussion Code

About this data

Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.

The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.

Data updated: Latest AI papers(UTC+8)