{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T16:31:33Z","timestamp":1792168293843,"version":"4.4.0"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375162","type":"print"},{"value":"9783032375179","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\/978-3-032-37517-9_28","type":"book-chapter","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:45:27Z","timestamp":1789577127000},"page":"501-520","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["RoboBench: A Comprehensive Evaluation Benchmark for\u00a0Multimodal Large Language Models as\u00a0Embodied Brain"],"prefix":"10.1007","author":[{"given":"Yulin","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun-Kai","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menghang","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayu","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangju","family":"Mi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengdi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo-Wen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Chi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaole","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruichuan","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengping","family":"Che","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoxuan","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guocai","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongxia","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiejun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanghang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"28_CR1","unstructured":"Azzolini, A., et al.: Cosmos-reason1: from physical common sense to embodied reasoning. arXiv preprint arXiv:2503.15558 (2025)"},{"key":"28_CR2","unstructured":"Bjorck, J., et al.: Gr00t n1: an open foundation model for generalist humanoid robots. arXiv preprint arXiv:2503.14734 (2025)"},{"key":"28_CR3","unstructured":"Black, K., et al.: $$\\pi _0$$: a vision-language-action flow model for general robot control (2024). https:\/\/arxiv.org\/abs\/2410.24164"},{"key":"28_CR4","unstructured":"Bu, Q., et\u00a0al.: Agibot world colosseo: a large-scale manipulation platform for scalable and intelligent embodied systems. arXiv preprint arXiv:2503.06669 (2025)"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H., et\u00a0al.: Fast-in-slow: a dual-system foundation model unifying fast manipulation within slow reasoning. arXiv preprint arXiv:2506.01953 (2025)","DOI":"10.52202\/085713-3276"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Chen, K., Xie, S., Ma, Z., Sanketi, P.R., Goldberg, K.: Robo2vlm: Visual question answering from large-scale in-the-wild robot manipulation datasets. arXiv preprint arXiv:2505.15517 (2025)","DOI":"10.52202\/085713-0733"},{"key":"28_CR7","unstructured":"Chen, S., et al.: Exploring embodied multimodal large models: development, datasets, and future directions (2025). https:\/\/arxiv.org\/abs\/2502.15336"},{"key":"28_CR8","unstructured":"Chen, T., et\u00a0al.: Robotwin 2.0: a scalable data generator and benchmark with strong domain randomization for robust bimanual robotic manipulation. arXiv preprint arXiv:2506.18088 (2025)"},{"key":"28_CR9","unstructured":"Chen, Y., et al.: Egoplan-bench: benchmarking multimodal large language models for human-level planning (2024). https:\/\/arxiv.org\/abs\/2312.06722"},{"key":"28_CR10","unstructured":"Cheng, S., et al.: Videgothink: assessing egocentric video understanding capabilities for embodied AI (2024). https:\/\/arxiv.org\/abs\/2410.11623"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, S., et al.: Egothink: evaluating first-person perspective thinking capability of vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14291\u201314302 (2024)","DOI":"10.1109\/CVPR52733.2024.01355"},{"key":"28_CR12","unstructured":"Cheng, Z., et al.: Embodiedeval: Evaluate multimodal llms as embodied agents (2025). https:\/\/arxiv.org\/abs\/2501.11858"},{"key":"28_CR13","unstructured":"Chi, X., et al.: Eva: an embodied world model for future video anticipation (2024). https:\/\/arxiv.org\/abs\/2410.15461"},{"key":"28_CR14","unstructured":"Clark, A.: Being There: Putting Brain, Body, and World Together Again. MIT Press (1998)"},{"key":"28_CR15","unstructured":"Open X-Embodiment Collaboration: Open X-Embodiment: robotic learning datasets and RT-X models (2023). https:\/\/arxiv.org\/abs\/2310.08864"},{"key":"28_CR16","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Dang, R., et al.: ECBench: can multi-modal foundation models understand the egocentric world? a holistic embodied cognition benchmark. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 24593\u201324602 (2025)","DOI":"10.1109\/CVPR52734.2025.02290"},{"key":"28_CR18","unstructured":"Driess, D., et al.: Palm-e: an embodied multimodal language model. In: ICML (2023)"},{"key":"28_CR19","unstructured":"Duan, J., et al.: Aha: a vision-language-model for detecting and reasoning over failures in robotic manipulation. arXiv preprint arXiv:2410.00371 (2024)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Fang, H.S., et al.: Rh20t: a comprehensive robotic dataset for learning diverse skills in one-shot. arXiv preprint arXiv:2307.00595 (2023)","DOI":"10.1109\/ICRA57147.2024.10611615"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Gao, J., et al.: Physically grounded vision-language models for robotic manipulation. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 12462\u201312469. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610090"},{"key":"28_CR22","unstructured":"Huang, W., Wang, C., Li, Y., Zhang, R., Fei-Fei, L.: Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation (2024). https:\/\/arxiv.org\/abs\/2409.01652"},{"key":"28_CR23","unstructured":"Huang, W., Wang, C., Zhang, R., Li, Y., Wu, J., Fei-Fei, L.: Voxposer: composable 3D value maps for robotic manipulation with language models (2023). https:\/\/arxiv.org\/abs\/2307.05973"},{"issue":"2","key":"28_CR24","doi-asserted-by":"publisher","first-page":"3019","DOI":"10.1109\/LRA.2020.2974707","volume":"5","author":"S James","year":"2020","unstructured":"James, S., Ma, Z., Arrojo, D.R., Davison, A.J.: RLBench: the robot learning benchmark & learning environment. IEEE Robot. Autom. Lett. 5(2), 3019\u20133026 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Ji, Y., et\u00a0al.: RoboBrain: a unified brain model for robotic manipulation from abstract to concrete. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 1724\u20131734 (2025)","DOI":"10.1109\/CVPR52734.2025.00168"},{"key":"28_CR26","unstructured":"Lee, J., et\u00a0al.: MolmoAct: action reasoning models that can reason in space. arXiv preprint arXiv:2508.07917 (2025)"},{"key":"28_CR27","unstructured":"Li, B., et al.: Llava-onevision: Easy visual task transfer (2024). https:\/\/arxiv.org\/abs\/2408.03326"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Improving vision-language-action models via chain-of-affordance. arXiv preprint arXiv:2412.20451 (2024)","DOI":"10.1109\/ICCV51701.2025.00910"},{"key":"28_CR29","unstructured":"Li, J., et al.: MMRO: are multimodal LLMs eligible as the brain for in-home robotics? (2024). https:\/\/arxiv.org\/abs\/2406.19693"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Embodied agent interface: benchmarking LLMs for embodied decision making. In: Globerson, A., et al. (eds.) Advances in Neural Information Processing Systems. vol.\u00a037, pp. 100428\u2013100534. Curran Associates, Inc. (2024). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/file\/b631da756d1573c24c9ba9c702fde5a9-Paper-Datasets_and_Benchmarks_Track.pdf","DOI":"10.52202\/079017-3188"},{"key":"28_CR31","first-page":"100428","volume":"37","author":"M Li","year":"2025","unstructured":"Li, M., et al.: Embodied agent interface: benchmarking LLMs for embodied decision making. Adv. Neural. Inf. Process. Syst. 37, 100428\u2013100534 (2025)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR32","unstructured":"Lin, F., Hu, Y., Sheng, P., Wen, C., You, J., Gao, Y.: Data scaling laws in imitation learning for robotic manipulation. arXiv preprint arXiv:2410.18647 (2024)"},{"key":"28_CR33","doi-asserted-by":"publisher","first-page":"44776","DOI":"10.52202\/075280-1939","volume":"36","author":"B Liu","year":"2023","unstructured":"Liu, B., et al.: Libero: benchmarking knowledge transfer for lifelong robot learning. Adv. Neural. Inf. Process. Syst. 36, 44776\u201344791 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Liu, F., Fang, K., Abbeel, P., Levine, S.: Moka: open-vocabulary robotic manipulation through mark-based visual prompting. In: First Workshop on Vision-Language Models for Navigation and Manipulation at ICRA 2024 (2024)","DOI":"10.15607\/RSS.2024.XX.062"},{"key":"28_CR35","unstructured":"Liu, J., et\u00a0al.: Hybridvla: Collaborative diffusion and autoregression in a unified vision-language-action model. arXiv preprint arXiv:2503.10631 (2025)"},{"key":"28_CR36","unstructured":"Liu, S., et al.: RDT-1b: a diffusion foundation model for bimanual manipulation. arXiv preprint arXiv:2410.07864 (2024)"},{"key":"28_CR37","unstructured":"Liu, Y., et al.: Aligning cyber space with physical world: a comprehensive survey on embodied AI (2024). https:\/\/arxiv.org\/abs\/2407.06886"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: MMBench: is your multi-modal model an all-around player? (2024). https:\/\/arxiv.org\/abs\/2307.06281","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"28_CR39","unstructured":"Liu, Z., Bahety, A., Song, S.: Reflect: summarizing robot experiences for failure explanation and correction. arXiv preprint arXiv:2306.15724 (2023)"},{"key":"28_CR40","doi-asserted-by":"crossref","unstructured":"Majumdar, A., et al.: OpenEQA: embodied question answering in the era of foundation models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16488\u201316498 (2024)","DOI":"10.1109\/CVPR52733.2024.01560"},{"issue":"3","key":"28_CR41","doi-asserted-by":"publisher","first-page":"7327","DOI":"10.1109\/LRA.2022.3180108","volume":"7","author":"O Mees","year":"2022","unstructured":"Mees, O., Hermann, L., Rosete-Beas, E., Burgard, W.: Calvin: a benchmark for language-conditioned policy learning for long-horizon robot manipulation tasks. IEEE Robot. Autom. Lett. 7(3), 7327\u20137334 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"28_CR42","doi-asserted-by":"publisher","first-page":"25081","DOI":"10.52202\/075280-1090","volume":"36","author":"Y Mu","year":"2023","unstructured":"Mu, Y., et al.: EmbodiedGPT: vision-language pre-training via embodied chain of thought. Adv. Neural. Inf. Process. Syst. 36, 25081\u201325094 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR43","unstructured":"Qi, Y., et al.: Bear: benchmarking and enhancing multimodal language models for atomic embodied capabilities. arXiv preprint arXiv:2510.08759 (2025)"},{"key":"28_CR44","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":"28_CR45","doi-asserted-by":"crossref","unstructured":"Shridhar, M., et al.: Alfred: a benchmark for interpreting grounded instructions for everyday tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"28_CR46","unstructured":"Shridhar, M., Yuan, X., C\u00f4t\u00e9, M.A., Bisk, Y., Trischler, A., Hausknecht, M.: Alfworld: aligning text and embodied environments for interactive learning. arXiv preprint arXiv:2010.03768 (2020)"},{"key":"28_CR47","doi-asserted-by":"crossref","unstructured":"Song, C.H., Blukis, V., Tremblay, J., Tyree, S., Su, Y., Birchfield, S.: Robospatial: teaching spatial understanding to 2D and 3D vision-language models for robotics. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 15768\u201315780 (2025)","DOI":"10.1109\/CVPR52734.2025.01470"},{"key":"28_CR48","doi-asserted-by":"publisher","unstructured":"Sun, F., Chen, R., Ji, T., Luo, Y., Zhou, H., Liu, H.: A comprehensive survey on embodied intelligence: advancements, challenges, and future perspectives. CAAI Artif. Intell. Res. 3, 9150042 (2024). https:\/\/doi.org\/10.26599\/AIR.2024.9150042, https:\/\/www.sciopen.com\/article\/10.26599\/AIR.2024.9150042","DOI":"10.26599\/AIR.2024.9150042"},{"key":"28_CR49","unstructured":"Team, B.R.: Robobrain 2.0 technical report. arXiv preprint arXiv:2507.02029 (2025)"},{"key":"28_CR50","unstructured":"Team, G.R., et al.: Gemini robotics: bringing AI into the physical world. arXiv preprint arXiv:2503.20020 (2025)"},{"key":"28_CR51","unstructured":"Wang, P., et al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution (2024). https:\/\/arxiv.org\/abs\/2409.12191"},{"key":"28_CR52","unstructured":"Wu, K., et\u00a0al.: Robomind: benchmark on multi-embodiment intelligence normative data for robot manipulation. arXiv preprint arXiv:2412.13877 (2024)"},{"key":"28_CR53","doi-asserted-by":"crossref","unstructured":"Yang, J., Yang, S., Gupta, A.W., Han, R., Fei-Fei, L., Xie, S.: Thinking in space: How multimodal large language models see, remember, and recall spaces (2024). https:\/\/arxiv.org\/abs\/2412.14171","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"28_CR54","unstructured":"Yang, R., et al.: Embodiedbench: comprehensive benchmarking multi-modal large language models for vision-driven embodied agents (2025). https:\/\/arxiv.org\/abs\/2502.09560"},{"key":"28_CR55","unstructured":"Yuan, W., et al.: RoboPoint: a vision-language model for spatial affordance prediction for robotics. arXiv preprint arXiv:2406.10721 (2024)"},{"key":"28_CR56","unstructured":"Zhang, J., et al.: Vlm4vla: revisiting vision-language-models in vision-language-action models. arXiv preprint arXiv:2601.03309 (2026)"},{"key":"28_CR57","unstructured":"Zhang, S., et al.: VLABench: a large-scale benchmark for language-conditioned robotics manipulation with long-horizon reasoning tasks (2024). https:\/\/arxiv.org\/abs\/2412.18194"},{"key":"28_CR58","doi-asserted-by":"crossref","unstructured":"Zhou, E., et\u00a0al.: Roborefer: towards spatial referring with reasoning in vision-language models for robotics. arXiv preprint arXiv:2506.04308 (2025)","DOI":"10.52202\/085713-0957"},{"key":"28_CR59","doi-asserted-by":"crossref","unstructured":"Zhou, E., et al.: Code-as-monitor: constraint-aware visual programming for reactive and proactive robotic failure detection. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 6919\u20136929 (2025)","DOI":"10.1109\/CVPR52734.2025.00649"}],"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\/978-3-032-37517-9_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:45:45Z","timestamp":1789577145000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37517-9_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375162","9783032375179"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37517-9_28","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":"17 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"}}]}}