{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:01:18Z","timestamp":1790276478930,"version":"4.1.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032384690","type":"print"},{"value":"9783032384706","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-38470-6_30","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:27:28Z","timestamp":1790274448000},"page":"313-322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SurgVLA-Bench: Towards Evaluating Vision-Language-Action Models for\u00a0Laparoscopic Surgical Robotics"],"prefix":"10.1007","author":[{"given":"Jiashuo","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiazheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"issue":"1","key":"30_CR1","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1146\/annurev-control-062420-090543","volume":"4","author":"A Attanasio","year":"2021","unstructured":"Attanasio, A., Scaglioni, B., De Momi, E., Fiorini, P., Valdastri, P.: Autonomy in surgical robotics. Annu. Rev. Control Robot. Auton. Syst. 4(1), 651\u2013679 (2021)","journal-title":"Annu. Rev. Control Robot. Auton. Syst."},{"key":"30_CR2","unstructured":"Black, K., et\u00a0al.: $$\\pi _0 $$: a vision-language-action flow model for general robot control. arXiv preprint arXiv:2410.24164 (2024)"},{"key":"30_CR3","unstructured":"Cen, J., et\u00a0al.: RynnVLA-002: a unified vision-language-action and world model. arXiv preprint arXiv:2511.17502 (2025)"},{"key":"30_CR4","unstructured":"Coumans, E., Bai, Y.: Pybullet, a python module for physics simulation for games, robotics and machine learning (2016). https:\/\/pybullet.org"},{"key":"30_CR5","unstructured":"Driess, D., et al.: PaLM-E: an embodied multimodal language model (2023)"},{"key":"30_CR6","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"30_CR7","unstructured":"Hugging Face Team: LeRobot: A Library for Real-World Robot Learning (2024). https:\/\/github.com\/huggingface\/lerobot. Version 0.4+ includes v3.0 dataset format"},{"key":"30_CR8","unstructured":"Intelligence, P., et\u00a0al.: $$\\pi _{0.5}$$: a vision-language-action model with open-world generalization. $$\\pi _{0.5}$$: a vision-language-action model with open-world generalization (2025)"},{"issue":"2","key":"30_CR9","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":"30_CR10","unstructured":"Karamcheti, S., Nair, S., Balakrishna, A., Liang, P., Kollar, T., Sadigh, D.: Prismatic VLMs: investigating the design space of visually-conditioned language models (2024). https:\/\/arxiv.org\/abs\/2402.07865"},{"key":"30_CR11","unstructured":"Kim, J.W., et al.: Surgical robot transformer (SRT): imitation learning for surgical tasks. arXiv preprint arXiv:2407.12998 (2024)"},{"key":"30_CR12","unstructured":"Kim, M.J., et al.: OpenVLA: an open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)"},{"key":"30_CR13","unstructured":"Kim, Y., et al.: Medical hallucinations in foundation models and their impact on healthcare. arXiv preprint arXiv:2503.05777 (2025)"},{"key":"30_CR14","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Liu, B., et al.: Libero: benchmarking knowledge transfer for lifelong robot learning. Adv. Neural. Inf. Process. Syst. 36, 44776\u201344791 (2023)","DOI":"10.52202\/075280-1939"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Long, Y., et\u00a0al.: Surgical embodied intelligence for generalized task autonomy in laparoscopic robot-assisted surgery. Sci. Robot. 10(104), eadt3093 (2025)","DOI":"10.1126\/scirobotics.adt3093"},{"issue":"3","key":"30_CR17","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":"30_CR18","doi-asserted-by":"crossref","unstructured":"Nwoye, C.I., et al.: Cholectriplet 2021: a benchmark challenge for surgical action triplet recognition. Med. Image Anal. 86, 102803 (2023)","DOI":"10.1016\/j.media.2023.102803"},{"key":"30_CR19","unstructured":"O\u2019Neill, A., et\u00a0al.: Open X-embodiment: robotic learning datasets and RT-X models: Open X-embodiment collaboration 0. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 6892\u20136903. IEEE (2024)"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Pore, A., Tagliabue, E., Piccinelli, M., Dall\u2019Alba, D., Casals, A., Fiorini, P.: Learning from demonstrations for autonomous soft-tissue retraction. In: 2021 International Symposium on Medical Robotics (ISMR), pp.\u00a01\u20137. IEEE (2021)","DOI":"10.1109\/ISMR48346.2021.9661514"},{"key":"30_CR21","unstructured":"Shukor, M., et al.: SmolVLA: a vision-language-action model for affordable and efficient robotics. arXiv preprint arXiv:2506.01844 (2025)"},{"issue":"9","key":"30_CR22","first-page":"30","volume":"93","author":"NJ Soper","year":"2008","unstructured":"Soper, N.J., Fried, G.M.: The fundamentals of laparoscopic surgery: its time has come. Bull. Am. Coll. Surg. 93(9), 30\u201332 (2008)","journal-title":"Bull. Am. Coll. Surg."},{"issue":"1","key":"30_CR23","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., De Mathelin, M., Padoy, N.: EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imaging 36(1), 86\u201397 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"30_CR24","unstructured":"Wang, Y., et\u00a0al.: VLA-adapter: an effective paradigm for tiny-scale vision-language-action model. arXiv preprint arXiv:2509.09372 (2025)"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Xu, J., Li, B., Lu, B., Liu, Y.H., Dou, Q., Heng, P.A.: SurRoL: an open-source reinforcement learning centered and DVRK compatible platform for surgical robot learning. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1821\u20131828. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9635867"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Yu, Q., et al.: Orbit-surgical: an open-simulation framework for learning surgical augmented dexterity. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 15509\u201315516. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10611637"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Yuan, K., Srivastav, V., Navab, N., Padoy, N.: HecVL: hierarchical video-language pretraining for zero-shot surgical phase recognition. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 306\u2013316. Springer (2024)","DOI":"10.1007\/978-3-031-72089-5_29"},{"key":"30_CR28","unstructured":"Zhang, D., et al.: Pure vision language action (VLA) models: a comprehensive survey. arXiv preprint arXiv:2509.19012 (2025)"},{"key":"30_CR29","unstructured":"Zhuoling, L., Liangliang, R., Jinrong, Y., Yong, Z.: VIP: vision instructed pre-training for robotic manipulation. In: ICML (2025)"},{"key":"30_CR30","unstructured":"Zitkovich, B., et\u00a0al.: RT-2: vision-language-action models transfer web knowledge to robotic control. In: Conference on Robot Learning, pp. 2165\u20132183. PMLR (2023)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-38470-6_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:27:37Z","timestamp":1790274457000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38470-6_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"ISBN":["9783032384690","9783032384706"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38470-6_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]},"assertion":[{"value":"25 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"27 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2026\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}