Study: Plain RAG Beats Complex Agentic Memory on Most Benchmarks

A paper from Xi'an Jiaotong University and collaborators shows that a plain RAG pipeline with dense retrieval and reranking over raw conversations beats complex agentic memory systems on 6 of 7 long-term memory benchmarks.

2026-10-23 ~ 2026-10-23 · 2 related posts

• Naive RAG beats complex agentic memory on 6 of 7 benchmarks, XJTU study finds — XianJiaotongUniversity · 2026-10-23
• Raw-RAG beats complex agentic memory systems on 6 of 7 long-term memory benchmarks — omarsar0 · 2026-10-23