Research map / Graph learning / Knowledge and temporal graphs
Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning
Junnan Dong, Siyu An, Yifei Yu, Qian-Wen Zhang, Linhao Luo, Xiao Huang, di yin, Yunsheng Wu, Xing Sun
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add iterative reasoning and reflection agent (ablation) | Youtu-GraphRAG · 2Wiki (reject) | top-20 accuracy: 57.80 -> 77.60 | Improved |
| add iterative reasoning and reflection agent (ablation) | Youtu-GraphRAG · MuSiQue (reject) | top-20 accuracy: 40.00 -> 47.50 | Improved |
| add iterative reasoning and reflection agent (ablation) | Youtu-GraphRAG · HotpotQA (reject) | top-20 accuracy: 75.30 -> 81.20 | Improved |
| add community detection (knowledge tree) (ablation) | Youtu-GraphRAG · HotpotQA (reject) | top-20 accuracy: 79.50 -> 81.20 | Improved |
| add community detection (knowledge tree) (ablation) | Youtu-GraphRAG · 2Wiki (reject) | top-20 accuracy: 75.10 -> 77.60 | Improved |
| add schema guidance for extraction and decomposition (ablation) | Youtu-GraphRAG · AnonyRAG-CHS (open) | top-20 accuracy: 35.61 -> 42.88 | Improved |
| add schema guidance for extraction and decomposition (ablation) | Youtu-GraphRAG · AnonyRAG-ENG (open) | top-20 accuracy: 40.32 -> 43.26 | Mixed |
| add schema guidance (ablation) | Youtu-GraphRAG · MuSiQue (reject) | top-20 accuracy: 45.60 -> 47.50 | Improved |
| use Youtu-GraphRAG without agent versus strongest baselines | Youtu-GraphRAG w/o Agent · HotpotQA, MuSiQue, G-Bench (open) | top-20 accuracy: HotpotQA 81.80 (HippoRAG2) -> 83.70 | Improved |
| use Youtu-GraphRAG instead of graph baselines for graph construction token cost | Youtu-GraphRAG · six benchmarks (construction tokens) | top-20 accuracy: up to 90.71% token saving | Improved |
| use reject mode instead of open mode (disallow parametric knowledge) | Naive RAG · 2Wiki | top-20 accuracy: 70.3 -> 38.9 | Hurt |
Closest papers by meaning
- Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation (ICLR 2025 · similarity 0.90)
- Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation (ICLR 2025 · similarity 0.89)
- Talk like a Graph: Encoding Graphs for Large Language Models (ICLR 2024 · similarity 0.89)
- Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models (ICML 2025 · similarity 0.89)
- Fast Think-on-Graph: Wider, Deeper and Faster Reasoning of Large Language Model on Knowledge Graph (AAAI 2025 · similarity 0.88)
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.88)
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.
