AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning

Tianhong Gao, Yannian Fu, Weiqun Wu, Haixiao Yue, Shanshan Liu, Gang Zhang

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 0 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
fine-tune with RR strategy on MMAT-1MInternVL2.5-8B · 8 MLLM benchmarks (avg)average score: 60.7 -> 63.4Improved
fine-tune with ORR strategy on MMAT-1MInternVL2.5-8B · 8 MLLM benchmarks (avg)average score: 60.7 -> 62.4Improved
fine-tune with RR on MMAT-1MLlama-3.2-11B-Vision-Instruct · 8 MLLM benchmarks (avg)average score: 52.2 -> 55.3Improved
fine-tune with RR on MMAT-1MMiniCPM-V-2.6 · 8 MLLM benchmarks (avg)average score: 58.0 -> 59.9Improved
fine-tune with RR on MMAT-1MInternVL2.5-2B · Dyn-VQA (Query)F1-Recall: 19.3 -> 30.9Improved
fine-tune with RR on MMAT-1MLlama-3.2-11B-Vision-Instruct · Dyn-VQA (Query)F1-Recall: 29.4 -> 38.0Improved
use RR instead of ORRInternVL2.5-8B · OCRBenchscore: 849 -> 839Hurt
use RR instead of ORRInternVL2.5-2B · OCRBenchscore: 819 -> 799Hurt
add API (tool) operators to RR (ablation)Baseline-RR (InternVL2.5-8B) · avg of 9 benchmarksaverage score: 57.3 -> 61.3Improved
add RAG retrieval to RR (ablation)Baseline-RR (InternVL2.5-8B) · avg of 9 benchmarksaverage score: 59.8 -> 61.3Improved
add SFT on MMAT-1M to RR (ablation)Baseline-RR (InternVL2.5-8B) · avg of 9 benchmarksaverage score: 55.0 -> 61.3Improved
add reflection to rationale (R to RR) (ablation)Baseline-R (InternVL2.5-8B) · avg of 9 benchmarksaverage score: 60.2 -> 61.3Improved

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