AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

You Don’t Need Pre-Built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures

Shengyuan Chen, Chuang Zhou, Zheng Yuan, Qinggang Zhang, Zeyang Cui, Hao Chen, Yilin Xiao, Jiannong Cao, Xiao Huang

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 29 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
replace pre-built graph RAG with query-time logic DAG decompositionLogicRAG vs HippoRAG2 · 2WikiMQAstring accuracy: 50.0 -> 64.7Improved
replace pre-built graph RAG with query-time logic DAG decompositionLogicRAG vs HippoRAG2 · MuSiQuestring accuracy: 27.0 -> 30.4Improved
replace pre-built graph RAG with query-time logic DAG decompositionLogicRAG vs HippoRAG2 · HotpotQAstring accuracy: 56.7 -> 54.8 string; 61.9 -> 62.6 LLMMixed
add retrieval over zero-shot GPT-4o-mini (vanilla RAG top-5)GPT-4o-mini · HotpotQAstring accuracy: 38.7 -> 44.1Improved
increase top-k in vanilla RAG (ablation)VanillaRAG · HotpotQA, 2WikiMQA, MuSiQuestring accuracy: HotpotQA 38.4 -> 44.1 (top-1 to top-5)Improved
increase top-k beyond 5 (top-10 to top-20) (ablation)LogicRAG · 2WikiMQAaccuracyNo clear effect
sampling without replacement of subproblem batches instead of with replacement (ablation)LogicRAG · HotpotQA, 2WikiMQA, MuSiQuetoken cost per questionImproved
add graph pruning (merge same-rank subproblems into one query) (ablation)LogicRAG · multi-hop QAretrieval roundsImproved
add context pruning via rolling memory summary (ablation)LogicRAG · multi-hop QAtoken costImproved
use LogicRAG instead of graph-based RAG at query timeGraphRAG/LightRAG/HippoRAG2 · 2WikiMQAaverage tokens: HippoRAG2 2809.2 -> LogicRAG 1777.9Improved

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