AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning

Haoran Luo, Haihong E, Guanting Chen, Qika Lin, Yikai Guo, Fangzhi Xu, Zemin Kuang, Meina Song, Xiaobao Wu, Yifan Zhu, Anh Tuan Luu

ICML 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation

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 knowledge construction (K.C.) of a hypergraph (ablation)Graph-R1 · Ablation (Figure)F1Improved
add multi-turn interaction (M.I.) with the graph (ablation)Graph-R1 · Ablation (Figure)F1Improved
add end-to-end reinforcement learning (R.L.) (ablation)Graph-R1 · Ablation (Figure)F1Improved
add RL training with hypergraph retrieval to graph-based RAGHyperGraphRAG · Average over 6 QA datasets, 7BF1: 29.40 -> 57.82Improved
use hypergraph knowledge with RL instead of chunk-based Search-R1Search-R1 · Average over 6 QA datasets, 7BF1: 46.19 -> 57.82Improved
scale base model from 1.5B to 3B to 7BGraph-R1 · Average over 6 QA datasetsF1: 40.09 -> 51.26 -> 57.82Improved
use graph structure with prompt-only (no RL) instead of StandardRAGStandardRAG · Average over 6 QA datasets, GPT-4o-miniF1: 32.05 -> 24.87Hurt
train Graph-R1 on Qwen3-4B (already RL-trained) instead of Qwen2.5Graph-R1 · Base model comparisonF1Hurt
use GRPO instead of REINFORCE++ or PPO (ablation)Graph-R1 · RL algorithm comparisonF1Improved
use hypergraph knowledge instead of binary-relation graph or chunks, with RLGraph-R1 · Knowledge representation comparisonF1Improved
simplified hypergraph construction versus GraphRAGGraphRAG · Construction costseconds per 1K tokens: 8.04 -> 5.69Improved
use Graph-R1 localized retrieval instead of HyperGraphRAGHyperGraphRAG · Query timeseconds per query: 9.6 -> 7.0Improved

Later papers that compared with this method

2 later accepted papers report Graph-R1 as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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