Research map / Large language models / Retrieval and knowledge
EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval
Jiashi Lin, Changhong Jiang, Xiangru Lin, Ruifei Zhang, Xinyi Zhu, Jiyao Liu, Cheng Tang, Ye Du, Shujian Gao, Junzhi Ning, Lihao Liu, Ziyan Huang and 3 more
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 multimodal hypergraph (ablation) | EvoGraph-R1 · 2WikiMultiHopQA | F1: 63.1 -> 68.5 | Improved |
| add multimodal hypergraph (ablation) | EvoGraph-R1 · E-VQA | accuracy: 38.8 -> 43.6 | Improved |
| add INSERT graph edit (ablation) | EvoGraph-R1 · 2WikiMultiHopQA | F1: 60.1 -> 68.5 | Improved |
| add INSERT graph edit (ablation) | EvoGraph-R1 · E-VQA | accuracy: 36.8 -> 43.6 | Improved |
| add UPDATE graph edit (ablation) | EvoGraph-R1 · 2WikiMultiHopQA | F1: 63.0 -> 68.5 | Improved |
| add UPDATE graph edit (ablation) | EvoGraph-R1 · E-VQA | accuracy: 39.7 -> 43.6 | Improved |
| add DELETE graph edit (ablation) | EvoGraph-R1 · 2WikiMultiHopQA | F1: 66.1 -> 68.5 | Improved |
| add DELETE graph edit (ablation) | EvoGraph-R1 · E-VQA | accuracy: 42.1 -> 43.6 | Improved |
| add WebSearch action (ablation) | EvoGraph-R1 · 2WikiMultiHopQA | F1: 58.9 -> 68.5 | Improved |
| add WebSearch action (ablation) | EvoGraph-R1 · E-VQA | accuracy: 32.4 -> 43.6 | Improved |
| add INSERT graph edit (ablation) | EvoGraph-R1 · 2WikiMultiHopQA | retrieval rounds: 3.48 -> 2.57 | Improved |
| add WebSearch action (ablation) | EvoGraph-R1 · 2WikiMultiHopQA | retrieval rounds: 3.17 -> 2.57 | Improved |
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 0.91)
- MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains (ICLR 2026 · similarity 0.91)
- Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation (ICLR 2025 · similarity 0.90)
- Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph (ICML 2026 · similarity 0.89)
- HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation (NeurIPS 2025 · similarity 0.89)
- MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs (NeurIPS 2026 · similarity 0.89)
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.
