{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:01:26Z","timestamp":1777888886920,"version":"3.51.4"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00146","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1484-1494","source":"Crossref","is-referenced-by-count":0,"title":["MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning"],"prefix":"10.1109","author":[{"given":"Tianhong","family":"Gao","sequence":"first","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yannian","family":"Fu","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiqun","family":"Wu","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haixiao","family":"Yue","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanshan","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"8","key":"ref1","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arxiv 2023","volume":"1","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Fireact: Toward language agent fine-tuning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref5","article-title":"M ${ }^{3}$ cot: A novel benchmark for multidomain multi-step multi-modal chain-of-thought","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.557"},{"key":"ref8","article-title":"Expanding performance boundaries of open-source multi-modal models with model, data, and test-time scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref11","article-title":"Pp-ocr: A practical ultra lightweight ocr system","author":"Du","year":"2020","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref13","article-title":"Assistgpt: A general multi-modal assistant that can plan, execute, inspect, and learn","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Multi-modal agent tuning: Building a vlm-driven agent for efficient tool usage","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Gao"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"issue":"2","key":"ref16","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref17","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref19","article-title":"What matters when building vision-language models?","author":"Lauren\u00e7on","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Benchmarking multi-modal retrieval augmented generation with dynamic vqa dataset and selfadaptive planning agent","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref25","first-page":"arXiv-2305","article-title":"On the hidden mystery of ocr in large multi-modal models","author":"Liu","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref26","article-title":"Dynamic prompt learning via policy gradient for semi-structured mathematical reasoning","author":"Lu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lu"},{"key":"ref28","article-title":"Llama 3.2: Revolutionizing edge ai and vision with open, customizable models","year":"2024","journal-title":"Meta AI Blog"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01367"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.17671\/gazibtd.1399077"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/app14177782"},{"key":"ref32","article-title":"Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning","volume-title":"The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Shao"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1657"},{"key":"ref34","article-title":"Trial and error: Exploration-based trajectory optimization for 11 m agents","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Gemini: a family of highly capable multi-modal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.570"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00650"},{"key":"ref38","first-page":"95095","article-title":"Measuring multi-modal mathematical reasoning with math-vision dataset","volume":"37","author":"Wang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Visual chatgpt: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","volume-title":"X.AI. Grok-1.5 vision preview","year":"2024"},{"key":"ref42","article-title":"Llava-o1: Let vision language models reason step-by-step","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","author":"Xu","year":"2024","journal-title":"Llava-cot: Let vision language models reason step-by-step"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3149"},{"key":"ref45","article-title":"React: Synergizing reasoning and acting in language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Yao"},{"key":"ref46","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.670"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref49","article-title":"Agenttuning: Enabling generalized agent abilities for 11 ms","author":"Zeng","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444389.pdf?arnumber=11444389","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:01:06Z","timestamp":1777611666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444389\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00146","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}