{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:16Z","timestamp":1777865356985,"version":"3.51.4"},"reference-count":60,"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"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00033","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"273-283","source":"Crossref","is-referenced-by-count":1,"title":["MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI"],"prefix":"10.1109","author":[{"given":"Huanjin","family":"Yao","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxing","family":"Huang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yawen","family":"Qiu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael K.","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenzheng","family":"Liu","sequence":"additional","affiliation":[{"name":"University of California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjie","family":"Zeng","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xikun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"YuXin","family":"Song","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Wu","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref4","author":"Chen","year":"2025","journal-title":"R1-v: Reinforcing super generalization ability in visionlanguage models with less than $ 3"},{"key":"ref5","article-title":"{M}^{3} cot: A novel benchmark for multidomain multi-step multi-modal chain-of-thought","volume-title":"Proc. of ACL","author":"Chen","year":"2024"},{"key":"ref6","article-title":"Gemini 2","author":"Comanici","year":"2025","journal-title":"5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref8","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","author":"Fu","journal-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref11","article-title":"Deepseek-r 1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.211"},{"key":"ref13","article-title":"Visual instruction tuning towards generalpurpose multimodal model: A survey","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3968"},{"key":"ref15","article-title":"Vision-r1: Incentivizing reasoning capability in multimodal large language models","author":"Huang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref17","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Openai o1 system card","author":"Jaech","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Mme-cot: Benchmarking chain-of-thought in large multimodal models for reasoning quality, robustness, and efficiency","author":"Jiang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref22","article-title":"From system 1 to system 2: A survey of reasoning large language models","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref25","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref27","article-title":"OpenAI","year":"2025","journal-title":"Introducing gpt-4.1 in the api"},{"key":"ref28","article-title":"Skywork r1v: Pioneering multimodal reasoning with chain-of-thought","author":"Peng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"We-math: Does your large multimodal model achieve human-like mathematical reasoning?","author":"Qiao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0275"},{"key":"ref31","year":"2025","journal-title":"Claude 3.7 sonnet"},{"key":"ref32","year":"2025","journal-title":"Claude 4 sonnet"},{"key":"ref33","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Kimi k1","author":"Team","year":"2025","journal-title":"5: Scaling reinforcement learning with 11 ms. arXiv preprint arXiv:2501.12599"},{"key":"ref35","year":"2024","journal-title":"Qvq: To see the world with wisdom"},{"key":"ref36","year":"2024","journal-title":"Qwq: Reflect deeply on the boundaries of the unknown"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3014"},{"key":"ref38","article-title":"Enhancing the reasoning ability of multimodal large language models via mixed preference optimization","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","volume-title":"Open-r1-video","author":"Wang","year":"2025"},{"key":"ref40","article-title":"R1-compress: Long chain-of-thought compression via chunk compression and search","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref41","first-page":"113569","article-title":"Charxiv: Charting gaps in realistic chart understanding in multimodal 11 ms","volume":"37","author":"Wang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","article-title":"Boosting multimodal reasoning with mcts-automated structured thinking","author":"Wu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Deepseek-vl 2: Mixture-ofexperts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Logic-rl: Unleashing 11 m reasoning with rule-based reinforcement learning","author":"Xie","year":"2025","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Llava-o1: Let vision language models reason step-by-step","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Mulberry: Empowering mllm with ol-like reasoning and reflection via collective monte carlo tree search","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1043"},{"key":"ref48","article-title":"R1-sharevl: Incentivizing reasoning capability of multimodal large language models via share-grpo","author":"Yao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Mmt-bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask agi","author":"Ying","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Mme-reasoning: A comprehensive benchmark for logical reasoning in mllms","author":"Yuan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.736"},{"key":"ref55","article-title":"Mm1. 5: Methods, analysis & insights from multimodal 11 m fine-tuning","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00181"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_10"},{"key":"ref59","article-title":"Improve vision language model chain-ofthought reasoning","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Dynamath: A dynamic visual benchmark for evaluating mathematical reasoning robustness of vision language models","author":"Zou","year":"2024","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\/11445845.pdf?arnumber=11445845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:05Z","timestamp":1777530005000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445845\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00033","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}