Research map / Vision-language and multimodal / Multimodal LLMs
Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown
Bowen Wang, Zhouqiang Jiang, Yasuaki Susumu, Shotaro Miwa, Tianwei Chen, Yuta Nakashima
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 graph knowledge retrieval (multi-agent, unaided-online) over vanilla | GPT-4o · MH Benchmark | accuracy: .3122 -> .5105 | Improved |
| add human captions instead of images (Vanilla+) | GPT-4o · MH Benchmark | accuracy: .3122 -> .3924 | Improved |
| provide annotated subgraph (Knowledgeable) | GPT-4o · MH Benchmark | accuracy: .3924 -> .8565 | Improved |
| generate captions online during retrieval rather than offline | GPT-4o · MH Benchmark | accuracy: .4050 -> .5105 | Improved |
| generate captions online rather than offline | GPT-4o mini · MH Benchmark | accuracy: .4514 -> .3544 | Hurt |
| generate captions online rather than offline | Claude 3.7 Sonnet · MH Benchmark | accuracy: .3628 -> .4388 | Improved |
| use human-selected keyframes instead of equal-interval sampling (ablation) | GPT-4o · MH Benchmark Unaided-Online | accuracy: .4840 -> .5105 | Improved |
| add monster name to question (ablation) | GPT-4o Unaided-Online · MH Benchmark | accuracy: .3781 -> .5105 | Improved |
| add extra information to question (ablation) | GPT-4o Unaided-Online · MH Benchmark | accuracy: .4075 -> .5105 | Improved |
| use InternVL as Validation agent instead of GPT-4o (ablation) | GPT-4o pipeline · MH Benchmark | accuracy: .5105 -> .4128 | Hurt |
| use InternVL as Summarizer instead of GPT-4o (ablation) | GPT-4o pipeline · MH Benchmark | accuracy: .5105 -> .4864 | Hurt |
| replace offline captions with InternVideo2.5 captions (ablation) | GPT-4o Unaided-Offline · MH Benchmark | accuracy: .4050 -> .3697 | Hurt |
Closest papers by meaning
- MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains (ICLR 2026 · similarity 0.89)
- MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models (AAAI 2026 · similarity 0.88)
- Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph (ICML 2026 · similarity 0.88)
- Play to Generalize: Learning to Reason Through Game Play (ICLR 2026 · similarity 0.86)
- Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent (ICLR 2025 · similarity 0.86)
- CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning (CVPR 2026 · similarity 0.86)
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.
