{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:19:31Z","timestamp":1780636771559,"version":"3.54.1"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051134","type":"print"},{"value":"9783032051141","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"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\/978-3-032-05114-1_54","type":"book-chapter","created":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T14:10:10Z","timestamp":1758377410000},"page":"563-572","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Surgical Action Planning with\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Mengya","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongzhen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Dou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,21]]},"reference":[{"key":"54_CR1","doi-asserted-by":"crossref","unstructured":"Ayobi, N., P\u00e9rez-Rond\u00f3n, A., Rodr\u00edguez, S., Arbel\u00e1ez, P.: MATIS: masked-attention transformers for surgical instrument segmentation. In: 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ISBI53787.2023.10230819"},{"key":"54_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102602","volume":"113","author":"L Bai","year":"2025","unstructured":"Bai, L., Wang, G., Islam, M., Seenivasan, L., Wang, A., Ren, H.: Surgical-VQLA++: adversarial contrastive learning for calibrated robust visual question-localized answering in robotic surgery. Inf. Fusion 113, 102602 (2025)","journal-title":"Inf. Fusion"},{"key":"54_CR3","doi-asserted-by":"crossref","unstructured":"Bai, L., et al.: OSSAR: towards open-set surgical activity recognition in robot-assisted surgery. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 14622\u201314629. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610246"},{"key":"54_CR4","unstructured":"Chen, Y., et al.: EgoPlan-bench: benchmarking multimodal large language models for human-level planning. arXiv preprint arXiv:2312.06722 (2023)"},{"key":"54_CR5","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: ICLR, vol. 1, no. 2, p. 3 (2022)"},{"key":"54_CR6","unstructured":"Huang, D., Hilliges, O., Van\u00a0Gool, L., Wang, X.: Palm: predicting actions through language models @ Ego4D long-term action anticipation challenge. arXiv preprint arXiv:2306.16545 (2023)"},{"key":"54_CR7","doi-asserted-by":"crossref","unstructured":"Jiang, J., Zhou, K., Zhao, W.X., Li, Y., Wen, J.R.: ReasoningLM: enabling structural subgraph reasoning in pre-trained language models for question answering over knowledge graph. arXiv preprint arXiv:2401.00158 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.228"},{"key":"54_CR8","doi-asserted-by":"crossref","unstructured":"Jiao, Y., et al.: Instruct and extract: instruction tuning for on-demand information extraction. arXiv preprint arXiv:2310.16040 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.620"},{"issue":"7","key":"54_CR9","doi-asserted-by":"publisher","first-page":"1911","DOI":"10.1109\/TMI.2021.3069471","volume":"40","author":"Y Jin","year":"2021","unstructured":"Jin, Y., Long, Y., Chen, C., Zhao, Z., Dou, Q., Heng, P.A.: Temporal memory relation network for workflow recognition from surgical video. IEEE Trans. Med. Imaging 40(7), 1911\u20131923 (2021)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"54_CR10","doi-asserted-by":"publisher","unstructured":"Kim, S., Huang, D., Xian, Y., Hilliges, O., Van\u00a0Gool, L., Wang, X.: Palm: predicting actions through language models. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15140, pp. 140\u2013158. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73007-8_9","DOI":"10.1007\/978-3-031-73007-8_9"},{"issue":"6","key":"54_CR11","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1038\/s41551-023-01010-8","volume":"7","author":"D Kiyasseh","year":"2023","unstructured":"Kiyasseh, D., et al.: A vision transformer for decoding surgeon activity from surgical videos. Nat. Biomed. Eng. 7(6), 780\u2013796 (2023)","journal-title":"Nat. Biomed. Eng."},{"key":"54_CR12","doi-asserted-by":"crossref","unstructured":"Mutegeki, R., Han, D.S.: A CNN-LSTM approach to human activity recognition. In: 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pp. 362\u2013366. IEEE (2020)","DOI":"10.1109\/ICAIIC48513.2020.9065078"},{"key":"54_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102433","volume":"78","author":"CI Nwoye","year":"2022","unstructured":"Nwoye, C.I., et al.: Rendezvous: attention mechanisms for the recognition of surgical action triplets in endoscopic videos. Med. Image Anal. 78, 102433 (2022)","journal-title":"Med. Image Anal."},{"key":"54_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102888","volume":"89","author":"CI Nwoye","year":"2023","unstructured":"Nwoye, C.I., et al.: CholecTriplet 2022: show me a tool and tell me the triplet\u2014an endoscopic vision challenge for surgical action triplet detection. Med. Image Anal. 89, 102888 (2023)","journal-title":"Med. Image Anal."},{"key":"54_CR15","doi-asserted-by":"crossref","unstructured":"Patel, D., Eghbalzadeh, H., Kamra, N., Iuzzolino, M.L., Jain, U., Desai, R.: Pretrained language models as visual planners for human assistance. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15302\u201315314 (2023)","DOI":"10.1109\/ICCV51070.2023.01404"},{"key":"54_CR16","doi-asserted-by":"publisher","unstructured":"Seenivasan, L., Islam, M., Kannan, G., Ren, H.: SurgicalGPT: end-to-end language-vision for visual question answering in surgery. In: Greenspan, H., et al. (eds.) MICCAI 2023. LNCS, vol 14228, pp. 281\u2013290. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43996-4_27","DOI":"10.1007\/978-3-031-43996-4_27"},{"key":"54_CR17","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Document-level machine translation with large language models. arXiv preprint arXiv:2304.02210 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.1036"},{"key":"54_CR18","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)"},{"key":"54_CR19","unstructured":"Xie, J., et al.: Revealing the barriers of language agents in planning. arXiv preprint arXiv:2410.12409 (2024)"},{"key":"54_CR20","unstructured":"Yu, J., et al.: SAM 2 in robotic surgery: an empirical evaluation for robustness and generalization in surgical video segmentation. arXiv preprint arXiv:2408.04593 (2024)"},{"key":"54_CR21","unstructured":"Yuan, K., Srivastav, V., Navab, N., Padoy, N., et\u00a0al.: Procedure-aware surgical video-language pretraining with hierarchical knowledge augmentation. arXiv preprint arXiv:2410.002632 (2024)"},{"key":"54_CR22","unstructured":"Zhao, Q., et al.: AntGPT: can large language models help long-term action anticipation from videos? arXiv preprint arXiv:2307.16368 (2023)"},{"key":"54_CR23","unstructured":"Zhao, W.X., et\u00a0al.: A survey of large language models, 1(2). arXiv preprint arXiv:2303.18223 (2023)"},{"key":"54_CR24","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et al.: LLAMAFACTORY: unified efficient fine-tuning of 100+ language models. arXiv preprint arXiv:2403.13372 (2024)","DOI":"10.18653\/v1\/2024.acl-demos.38"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05114-1_54","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T14:10:16Z","timestamp":1758377416000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05114-1_54"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,21]]},"ISBN":["9783032051134","9783032051141"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05114-1_54","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,21]]},"assertion":[{"value":"21 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}