{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:04:46Z","timestamp":1789376686698,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":40,"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_33","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:22:23Z","timestamp":1789374143000},"page":"572-589","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["From Passive Observer to\u00a0Active Critic: Reinforcement Learning Elicits Process Reasoning for\u00a0Robotic Manipulation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2925-7798","authenticated-orcid":false,"given":"Yibin","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5831-2739","authenticated-orcid":false,"given":"Yaxing","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7700-2228","authenticated-orcid":false,"given":"Daqi","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6815-9866","authenticated-orcid":false,"given":"Zhixuan","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1220-7031","authenticated-orcid":false,"given":"Weiliang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3638-6539","authenticated-orcid":false,"given":"Shilong","family":"Mu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0321-021X","authenticated-orcid":false,"given":"Yao","family":"Mu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"33_CR1","unstructured":"Azzolini, A., et al.: Cosmos-Reason1: from physical common sense to embodied reasoning (2025). arXiv preprint arXiv:2503.15558"},{"key":"33_CR2","unstructured":"Bu, Q., et\u00a0al.: AgiBot world Colosseo: a large-scale manipulation platform for scalable and intelligent embodied systems (2025). arXiv preprint arXiv:2503.06669"},{"key":"33_CR3","unstructured":"Chen, T., et\u00a0al.: RoboTwin 2.0: a scalable data generator and benchmark with strong domain randomization for robust bimanual robotic manipulation (2025). arXiv preprint arXiv:2506.18088"},{"issue":"3","key":"33_CR4","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1007\/s11263-025-02676-0","volume":"134","author":"Y Chen","year":"2026","unstructured":"Chen, Y., et al.: EgoPlan-bench: benchmarking multimodal large language models for human-level planning. Int. J. Comput. Vision 134(3), 118 (2026)","journal-title":"Int. J. Comput. Vision"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: GRPO-CARE: consistency-aware reinforcement learning for multimodal reasoning (2025). arXiv preprint arXiv:2506.16141","DOI":"10.18653\/v1\/2026.findings-acl.210"},{"key":"33_CR6","unstructured":"Cheng, Z., et\u00a0al.: VideoLLaMA 2: advancing spatial-temporal modeling and audio understanding in video-LLMs (2024). arXiv preprint arXiv:2406.07476"},{"key":"33_CR7","unstructured":"Chu, T., et al.: SFT memorizes, RL generalizes: a comparative study of foundation model post-training (2025). arXiv preprint arXiv:2501.17161"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Feng, K., et al.: Video-R1: reinforcing video reasoning in MLLMs (2025). arXiv preprint arXiv:2503.21776","DOI":"10.52202\/085713-3310"},{"key":"33_CR9","unstructured":"Ge, H., Wang, Y., Chang, K.W., Wu, H., Cai, Y.: FrameMind: frame-interleaved video reasoning via reinforcement learning (2025). arXiv preprint arXiv:2509.24008"},{"key":"33_CR10","unstructured":"Guo, D., et\u00a0al.: DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning (2025). arXiv preprint arXiv:2501.12948"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Huang, B., Wang, X., Chen, H., Song, Z., Zhu, W.: VTimeLLM: empower LLM to grasp video moments. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14271\u201314280 (2024)","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Ji, Y., et\u00a0al.: RoboBrain: a unified brain model for robotic manipulation from abstract to concrete (2025). arXiv preprint arXiv:2502.21257","DOI":"10.1109\/CVPR52734.2025.00168"},{"key":"33_CR13","unstructured":"Li, C., et\u00a0al.: BEHAVIOR-1K: a benchmark for embodied ai with 1,000 everyday activities and realistic simulation. In: Conference on Robot Learning, pp. 80\u201393. PMLR (2023)"},{"issue":"3","key":"33_CR14","doi-asserted-by":"publisher","first-page":"1832","DOI":"10.1109\/TPAMI.2024.3508072","volume":"47","author":"Y Li","year":"2025","unstructured":"Li, Y., et al.: STAR: a first-ever dataset and a large-scale benchmark for scene graph generation in large-size satellite imagery. IEEE Trans. Pattern Anal. Mach. Intell. 47(3), 1832\u20131849 (2025)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, C., Jia, J.: LLaMA-VID: an image is worth 2 tokens in large language models. In: European Conference on Computer Vision, pp. 323\u2013340. Springer (2024)","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Lin, B., et al.: Video-LLaVA: learning united visual representation by alignment before projection. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 5971\u20135984 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"33_CR17","unstructured":"Liu, Y., et al.: HyCodePolicy: hybrid language controllers for multimodal monitoring and decision in embodied agents (2025). arXiv preprint arXiv:2508.02629"},{"key":"33_CR18","unstructured":"Liu, Z., Bahety, A., Song, S.: REFLECT: summarizing robot experiences for failure explanation and correction (2023). arXiv preprint arXiv:2306.15724"},{"key":"33_CR19","unstructured":"Ma, Y.J., et\u00a0al.: Vision language models are in-context value learners. In: The Thirteenth International Conference on Learning Representations (2024)"},{"key":"33_CR20","unstructured":"Ma, Y.J., Kumar, V., Zhang, A., Bastani, O., Jayaraman, D.: LIV: language-image representations and rewards for robotic control. In: International Conference on Machine Learning, pp. 23301\u201323320. PMLR (2023)"},{"key":"33_CR21","unstructured":"Ma, Y.J., Sodhani, S., Jayaraman, D., Bastani, O., Kumar, V., Zhang, A.: VIP: towards universal visual reward and representation via value-implicit pre-training (2022). arXiv preprint arXiv:2210.00030"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.: Video-ChatGPT: towards detailed video understanding via large vision and language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12585\u201312602 (2024)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Patraucean, V., et al.: Perception test: a diagnostic benchmark for multimodal video models. In: Advances in Neural Information Processing Systems, vol. 36, pp. 42748\u201342761 (2023)","DOI":"10.52202\/075280-1852"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Ren, S., Yao, L., Li, S., Sun, X., Hou, L.: TimeChat: a time-sensitive multimodal large language model for long video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14313\u201314323 (2024)","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Ren, W., Yang, H., Min, J., Wei, C., Chen, W.: VISTA: enhancing long-duration and high-resolution video understanding by video spatiotemporal augmentation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 3804\u20133814 (2025)","DOI":"10.1109\/CVPR52734.2025.00360"},{"key":"33_CR26","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017). arXiv preprint arXiv:1707.06347"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Sermanet, P., et al.: RoboVQA: multimodal long-horizon reasoning for robotics. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 645\u2013652. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610216"},{"key":"33_CR28","unstructured":"Shen, H., et\u00a0al.: VLM-R1: a stable and generalizable R1-style large vision-language model (2025). arXiv preprint arXiv:2504.07615"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Song, E., et\u00a0al.: MovieChat: from dense token to sparse memory for long video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18221\u201318232 (2024)","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Sontakke, S., et al.: RoboCLIP: one demonstration is enough to learn robot policies. In: Advances in Neural Information Processing Systems, vol. 36, vol. 55681\u201355693 (2023)","DOI":"10.52202\/075280-2430"},{"key":"33_CR31","unstructured":"Tan, H., et\u00a0al.: Robo-Dopamine: general process reward modeling for high-precision robotic manipulation (2025). arXiv preprint arXiv:2512.23703"},{"key":"33_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Y., et\u00a0al.: Time-R1: post-training large vision language model for temporal video grounding (2025). arXiv preprint arXiv:2503.13377","DOI":"10.52202\/085713-2793"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Xiao, J., Shang, X., Yao, A., Chua, T.S.: NExT-QA: next phase of question-answering to explaining temporal actions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9777\u20139786 (2021)","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"33_CR34","doi-asserted-by":"crossref","unstructured":"Yang, Y., et\u00a0al.: R1-Onevision: advancing generalized multimodal reasoning through cross-modal formalization (2025). arXiv preprint arXiv:2503.10615","DOI":"10.1109\/ICCV51701.2025.00229"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Yu, S., Cho, J., Yadav, P., Bansal, M.: Self-chained image-language model for video localization and question answering. In: Advances in Neural Information Processing Systems, vol. 36, pp. 76749\u201376771 (2023)","DOI":"10.52202\/075280-3354"},{"key":"33_CR36","unstructured":"Zhai, S., et al.: A vision-language-action-critic model for robotic real-world reinforcement learning (2025). arXiv preprint arXiv:2509.15937"},{"key":"33_CR37","unstructured":"Zhang, J., et al.: ReWiND: language-guided rewards teach robot policies without new demonstrations (2025). arXiv preprint arXiv:2505.10911"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: ProgressLM: towards progress reasoning in vision-language models (2026). arXiv preprint arXiv:2601.15224","DOI":"10.18653\/v1\/2026.acl-long.516"},{"key":"33_CR39","unstructured":"Zhang, P., et al.: Long context transfer from language to vision (2024). arXiv preprint arXiv:2406.16852"},{"key":"33_CR40","unstructured":"Zhang, Y., et al.: SCIZOR: self-supervised data curation for large-scale imitation learning. In: IEEE International Conference on Robotics and Automation (ICRA) (2026)"}],"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_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:22:43Z","timestamp":1789374163000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37383-0_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373823","9783032373830"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37383-0_33","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"}}]}}