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。
Read on arXiv PDF Hugging Face discussion Code
Topics & disciplines
More on Agents
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲388
- Player-1: Learning to Play from Synthetic Experience ▲347
More on LLMs
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels 2026-10-22 · ▲247
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- OmniEdu: Open Foundation Models for Learning and Teaching 2026-09-19 · ▲240
More from Xi'an Jiaotong University
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.