{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:04:40Z","timestamp":1789376680583,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373823","type":"print"},{"value":"9783032373830","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37383-0_24","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:27:19Z","timestamp":1789374439000},"page":"410-428","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AnE: Pushing the\u00a0Reasoning Frontier of\u00a0Multimodal LLMs via\u00a0Anchor Evolution"],"prefix":"10.1007","author":[{"given":"Zehao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihan","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zidong","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanfan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8025-346X","authenticated-orcid":false,"given":"Hongzhi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3330-783X","authenticated-orcid":false,"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"24_CR1","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"24_CR2","unstructured":"Chen, H., et al.: SFT or RL? An early investigation into training R1-like reasoning large vision-language models. arXiv preprint arXiv:2504.11468 (2025)"},{"key":"24_CR3","unstructured":"Chen, J., et al.: Step-wise adaptive integration of supervised fine-tuning and reinforcement learning for task-specific LLMs. arXiv preprint arXiv:2505.13026 (2025)"},{"key":"24_CR4","unstructured":"Chen, J., et al.: The synergy dilemma of long-CoT SFT and RL: Investigating post-training techniques for reasoning VLMs. arXiv preprint arXiv:2507.07562 (2025)"},{"key":"24_CR5","doi-asserted-by":"publisher","first-page":"27056","DOI":"10.52202\/079017-0850","volume":"37","author":"L Chen","year":"2024","unstructured":"Chen, L., et al.: Are we on the right way for evaluating large vision-language models? Adv. Neural. Inf. Process. Syst. 37, 27056\u201327087 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR6","unstructured":"Chen, S., et al.: Advancing multimodal reasoning: From optimized cold start to staged reinforcement learning. arXiv preprint arXiv:2506.04207 (2025)"},{"key":"24_CR7","unstructured":"Chen, X., et al.: C2-Evo: Co-evolving multimodal data and model for self-improving reasoning. arXiv preprint arXiv:2507.16518 (2025)"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Chia, Y.K., Toh, V., Ghosal, D., Bing, L., Poria, S.: PuzzleVQA: diagnosing multimodal reasoning challenges of language models with abstract visual patterns. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 16259\u201316273 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.962"},{"key":"24_CR9","unstructured":"Chu, T., et al.: SFT memorizes, RL generalizes: A comparative study of foundation model post-training. arXiv preprint arXiv:2501.17161 (2025)"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Deng, Y., Bansal, H., Yin, F., Peng, N., Wang, W., Chang, K.W.: OpenVLThinker: Complex vision-language reasoning via iterative SFT-RL cycles. arXiv preprint arXiv:2503.17352 (2025)","DOI":"10.52202\/085713-4126"},{"key":"24_CR11","unstructured":"Gandhi, K., Chakravarthy, A., Singh, A., Lile, N., Goodman, N.D.: Cognitive behaviors that enable self-improving reasoners, or, four habits of highly effective stars. arXiv preprint arXiv:2503.01307 (2025)"},{"key":"24_CR12","unstructured":"Ghosal, D., Han, V.T.Y., Ken, C.Y., Poria, S.: Are language models puzzle prodigies? Algorithmic puzzles unveil serious challenges in multimodal reasoning. arXiv preprint arXiv:2403.03864 (2024)"},{"key":"24_CR13","unstructured":"Guo, D., et\u00a0al.: DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"24_CR14","unstructured":"Guo, D., et al.: Seed1.5-VL technical report. arXiv preprint arXiv:2505.07062 (2025)"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: MAmmoTH-VL: eliciting multimodal reasoning with instruction tuning at scale. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 13869\u201313920 (2025)","DOI":"10.18653\/v1\/2025.acl-long.680"},{"key":"24_CR16","unstructured":"Hao, Y., et al.: Can MLLMs reason in multimodality? EMMA: An enhanced multimodal reasoning benchmark. arXiv preprint arXiv:2501.05444 (2025)"},{"key":"24_CR17","unstructured":"Huang, W., et al.: Vision-R1: Incentivizing reasoning capability in multimodal large language models. arXiv preprint arXiv:2503.06749 (2025)"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: European Conference on Computer Vision, pp. 235\u2013251. Springer (2016)","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Seo, M., Schwenk, D., Choi, J., Farhadi, A., Hajishirzi, H.: Are you smarter than a sixth grader? Textbook question answering for multimodal machine comprehension. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4999\u20135007 (2017)","DOI":"10.1109\/CVPR.2017.571"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Koh, W., et al.: AdaSTaR: Adaptive data sampling for training self-taught reasoners. arXiv preprint arXiv:2505.16322 (2025)","DOI":"10.52202\/085713-3061"},{"key":"24_CR21","unstructured":"Leng, S., et\u00a0al.: MMR1: Enhancing multimodal reasoning with variance-aware sampling and open resources. arXiv preprint arXiv:2509.21268 (2025)"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: ReflectEvo: improving meta introspection of small LLMs by learning self-reflection. In: Findings of the Association for Computational Linguistics: ACL 2025, pp. 16948\u201316966 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.871"},{"key":"24_CR23","unstructured":"Li, J., et\u00a0al.: Xiaomi MiMo-VL-Miloco technical report. arXiv preprint arXiv:2512.17436 (2025)"},{"key":"24_CR24","unstructured":"Li, X., et\u00a0al.: MiroMind-M1: An open-source advancement in mathematical reasoning via context-aware multi-stage policy optimization. arXiv preprint arXiv:2507.14683 (2025)"},{"key":"24_CR25","unstructured":"Li, Y., et\u00a0al.: Perception, reason, think, and plan: A survey on large multimodal reasoning models. arXiv preprint arXiv:2505.04921 (2025)"},{"key":"24_CR26","unstructured":"Liu, W., et al.: Automated optimization modeling via a localizable error-driven perspective. arXiv preprint arXiv:2602.11164 (2026)"},{"key":"24_CR27","unstructured":"Liu, Z., et al.: Spark: Synergistic policy and reward co-evolving framework. arXiv preprint arXiv:2509.22624 (2025)"},{"key":"24_CR28","unstructured":"Lu, A., Feng, T., Yuan, H., Li, W., Sun, Y.: Why does RL generalize better than SFT? A data-centric perspective on VLM post-training. arXiv preprint arXiv:2602.10815 (2026)"},{"key":"24_CR29","unstructured":"Lu, P., et al.: MathVista: Evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255 (2023)"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Inter-GPS: interpretable geometry problem solving with formal language and symbolic reasoning. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 6774\u20136786 (2021)","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"24_CR31","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.52202\/068431-0182","volume":"35","author":"P Lu","year":"2022","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. Adv. Neural. Inf. Process. Syst. 35, 2507\u20132521 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Luo, R., et al.: MMEvol: empowering multimodal large language models with Evol-instruct. In: Findings of the Association for Computational Linguistics: ACL 2025, pp. 19655\u201319682 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.1009"},{"key":"24_CR33","unstructured":"Ma, L., et\u00a0al.: Learning what reinforcement learning can\u2019t: Interleaved online fine-tuning for hardest questions. arXiv preprint arXiv:2506.07527 (2025)"},{"key":"24_CR34","unstructured":"Meng, F., et al.: MM-Eureka: Exploring the frontiers of multimodal reasoning with rule-based reinforcement learning. arXiv preprint arXiv:2503.07365 (2025)"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Qiao, R., et\u00a0al.: We-Math: does your large multimodal model achieve human-like mathematical reasoning? In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 20023\u201320070 (2025)","DOI":"10.18653\/v1\/2025.acl-long.983"},{"key":"24_CR36","unstructured":"Qiao, R., et\u00a0al.: We-Math 2.0: A versatile MathBook system for incentivizing visual mathematical reasoning. arXiv preprint arXiv:2508.10433 (2025)"},{"key":"24_CR37","unstructured":"Qiu, H., et al.: Metis-RISE: RL incentivizes and SFT enhances multimodal reasoning model learning. arXiv preprint arXiv:2506.13056 (2025)"},{"key":"24_CR38","unstructured":"Sheng, G., et al.: HybridFlow: A flexible and efficient RLHF framework. arXiv preprint arXiv: 2409.19256 (2024)"},{"key":"24_CR39","unstructured":"Thawakar, O., et al.: EvoLMM: Self-evolving large multimodal models with continuous rewards. arXiv preprint arXiv:2511.16672 (2025)"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Wan, Z., et al.: SRPO: Enhancing multimodal LLM reasoning via reflection-aware reinforcement learning. arXiv preprint arXiv:2506.01713 (2025)","DOI":"10.52202\/085713-5139"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"Wang, H., Qu, C., Huang, Z., Chu, W., Lin, F., Chen, W.: VL-rethinker: Incentivizing self-reflection of vision-language models with reinforcement learning. arXiv preprint arXiv:2504.08837 (2025)","DOI":"10.52202\/085713-1037"},{"key":"24_CR42","doi-asserted-by":"publisher","first-page":"95095","DOI":"10.52202\/079017-3014","volume":"37","author":"K Wang","year":"2024","unstructured":"Wang, K., et al.: Measuring multimodal mathematical reasoning with math-vision dataset. Adv. Neural. Inf. Process. Syst. 37, 95095\u201395169 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR43","unstructured":"Wang, X., et al.: LlaVA-Critic-R1: Your critic model is secretly a strong policy model. arXiv preprint arXiv:2509.00676 (2025)"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: SoTA with less: MCTS-guided sample selection for data-efficient visual reasoning self-improvement. arXiv preprint arXiv:2504.07934 (2025)","DOI":"10.52202\/085713-3964"},{"key":"24_CR45","doi-asserted-by":"crossref","unstructured":"Wei, Y., et al.: Open vision reasoner: Transferring linguistic cognitive behavior for visual reasoning. arXiv preprint arXiv:2507.05255 (2025)","DOI":"10.52202\/085713-0158"},{"key":"24_CR46","unstructured":"Wiedmann, L., et al.: FineVision: Open data is all you need. arXiv preprint arXiv:2510.17269 (2025)"},{"key":"24_CR47","unstructured":"Xiao, Y., Sun, E., Liu, T., Wang, W.: LogicVista: Multimodal LLM logical reasoning benchmark in visual contexts. arXiv preprint arXiv:2407.04973 (2024)"},{"key":"24_CR48","doi-asserted-by":"crossref","unstructured":"Xu, G., et al.: LLaVA-CoT: let vision language models reason step-by-step. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2087\u20132098 (2025)","DOI":"10.1109\/ICCV51701.2025.00202"},{"key":"24_CR49","doi-asserted-by":"crossref","unstructured":"Yao, H., et\u00a0al.: Mulberry: Empowering MLLM with o1-like reasoning and reflection via collective monte Carlo tree search. arXiv preprint arXiv:2412.18319 (2024)","DOI":"10.52202\/085713-1004"},{"key":"24_CR50","doi-asserted-by":"crossref","unstructured":"Yue, X., et\u00a0al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9556\u20139567 (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"24_CR51","unstructured":"Zhang, F., et al.: ADHint: Adaptive hints with difficulty priors for reinforcement learning. arXiv preprint arXiv:2512.13095 (2025)"},{"key":"24_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, K., et\u00a0al.: LMMS-EVAL: reality check on the evaluation of large multimodal models. In: Findings of the Association for Computational Linguistics: NAACL 2025, pp. 881\u2013916 (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.51"},{"key":"24_CR53","unstructured":"Zhang, K., et al.: OpenMMReasoner: Pushing the frontiers for multimodal reasoning with an open and general recipe. arXiv preprint arXiv:2511.16334 (2025)"},{"key":"24_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, R., et\u00a0al.: MathVerse: does your multi-modal LLM truly see the diagrams in visual math problems? In: European Conference on Computer Vision, pp. 169\u2013186. Springer (2024)","DOI":"10.1007\/978-3-031-73242-3_10"},{"key":"24_CR55","unstructured":"Zhang, Y., et\u00a0al.: Qwen3 embedding: Advancing text embedding and reranking through foundation models. arXiv preprint arXiv:2506.05176 (2025)"},{"key":"24_CR56","unstructured":"Zheng, C., et\u00a0al.: Group sequence policy optimization. arXiv preprint arXiv:2507.18071 (2025)"},{"key":"24_CR57","unstructured":"Zhou, G., et al.: Reinforced MLLM: A survey on RL-based reasoning in multimodal large language models. arXiv preprint arXiv:2504.21277 (2025)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37383-0_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:27:47Z","timestamp":1789374467000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37383-0_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373823","9783032373830"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37383-0_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"15 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}