AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

Juyuan Wang, Rongchen Zhao, Wei Wei, Yufeng Wang, Mo Yu, Jie Zhou, Jin Xu, Liyan Xu

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Long-context and personalized retrieval · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add veridical layer to index (ablation)ComoRAG · EN.MCaccuracy: 51.97 -> 72.93Improved
add semantic layer to index (ablation)ComoRAG · EN.MCaccuracy: 64.63 -> 72.93Improved
add episodic layer to index (ablation)ComoRAG · EN.MCaccuracy: 64.63 -> 72.93Improved
add metacognition (memory workspace) (ablation)ComoRAG · EN.QAF1: 26.95 -> 34.52Improved
add regulation (goal-oriented probing queries) (ablation)ComoRAG · EN.MCaccuracy: 55.02 -> 72.93Improved
add both metacognition and regulation (ablation)ComoRAG · EN.MCaccuracy: 54.15 -> 72.93Improved
add ComoRAG loop to RAPTOR (ablation)RAPTOR · EN.MCaccuracy: 57.21 -> 69.00Improved
add ComoRAG loop to HippoRAGv2 (ablation)HippoRAGv2 · EN.MCaccuracy: 60.26 -> 68.56Improved
use GPT-4.1 as LLM agent instead of GPT-4o-mini (ablation)ComoRAG · EN.MCaccuracy: 72.93 -> 78.17Improved
use Qwen3-32B as LLM agent (ablation)ComoRAG · EN.MCaccuracy: 72.93 -> 74.24Improved
larger embedding model (NV-Embed-v2 7B) instead of BGE-M3 for naive RAG vs ComoRAG with BGE-M3 (ablation)naive RAG · EN.MCaccuracy: 61.13 vs 72.93No clear effect
single-step retrieval only (step 0) versus cognitive loop (ablation)ComoRAG · EN.MCaccuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy