{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T05:44:02Z","timestamp":1773899042673,"version":"3.50.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031334689","type":"print"},{"value":"9783031334696","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-33469-6_23","type":"book-chapter","created":{"date-parts":[[2023,5,23]],"date-time":"2023-05-23T21:02:01Z","timestamp":1684875721000},"page":"222-232","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Evaluation of Pretrained Large Language Models in Embodied Planning Tasks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5537-6000","authenticated-orcid":false,"given":"Christina","family":"Sarkisyan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7710-6052","authenticated-orcid":false,"given":"Alexandr","family":"Korchemnyi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2180-0990","authenticated-orcid":false,"given":"Alexey K.","family":"Kovalev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9747-3837","authenticated-orcid":false,"given":"Aleksandr I.","family":"Panov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,24]]},"reference":[{"key":"23_CR1","unstructured":"Ahn, M., Brohan, A., Brown, N., Chebotar, Y., et al.: Do as i can and not as i say: grounding language in robotic affordances (2022)"},{"key":"23_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Anderson","year":"2016","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: semantic propositional image caption evaluation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Black, S., Biderman, S., Hallahan, E., Anthony, Q., et al.: GPT-NeoX-20B: an open-source autoregressive language model (2022)","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"23_CR4","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"23_CR5","unstructured":"Chowdhery, A., Narang, S., Devlin, J., Bosma, M., et al.: PaLM: scaling language modeling with pathways (2022)"},{"key":"23_CR6","unstructured":"Driess, D., Xia, F., Sajjadi, M.S.M., Lynch, C., et al.: PaLM-E: an embodied multimodal language model (2023)"},{"key":"23_CR7","unstructured":"Gao, L., Biderman, S., Black, S., Golding, L., et al.: The pile: an 800GB dataset of diverse text for language modeling (2020)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Gramopadhye, M., Szafir, D.: Generating executable action plans with environmentally-aware language models (2022)","DOI":"10.1109\/IROS55552.2023.10341989"},{"key":"23_CR9","unstructured":"Huang, W., Abbeel, P., Pathak, D., Mordatch, I.: Language models as zero-shot planners: extracting actionable knowledge for embodied agents. In: ICML (2022)"},{"key":"23_CR10","unstructured":"Kolve, E., Mottaghi, R., Han, W., VanderBilt, E., et al.: AI2-THOR: an interactive 3D environment for visual AI (2017)"},{"issue":"S1","key":"23_CR11","doi-asserted-by":"publisher","first-page":"S85","DOI":"10.1134\/S1064562422060138","volume":"106","author":"AK Kovalev","year":"2022","unstructured":"Kovalev, A.K., Panov, A.I.: Application of pretrained large language models in embodied artificial intelligence. Doklady Math. 106(S1), S85\u2013S90 (2022). https:\/\/doi.org\/10.1134\/S1064562422060138","journal-title":"Doklady Math."},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Lin, B.Y., Huang, C., Liu, Q., Gu, W., Sommerer, S., Ren, X.: On grounded planning for embodied tasks with language models (2022)","DOI":"10.1609\/aaai.v37i11.26549"},{"key":"23_CR13","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., et al.: RoBERTa: a robustly optimized BERT pretraining approach (2019)"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Logeswaran, L., Fu, Y., Lee, M., Lee, H.: Few-shot subgoal planning with language models (2022)","DOI":"10.18653\/v1\/2022.naacl-main.402"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Mackenzie, J., Benham, R., Petri, M., Trippas, J.R., et al.: CC-News-En: a large English news corpus. In: CIKM (2020)","DOI":"10.1145\/3340531.3412762"},{"key":"23_CR16","unstructured":"Min, S.Y., Chaplot, D.S., Ravikumar, P., Bisk, Y., Salakhutdinov, R.: FILM: following instructions in language with modular methods (2021)"},{"key":"23_CR17","unstructured":"OpenAI: Introducing ChatGPT (2022). https:\/\/openai.com\/blog\/chatgpt"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (2019). https:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"23_CR19","unstructured":"Shibata, Y., Kida, T., Fukamachi, S., Takeda, M., et al.: Byte pair encoding: a text compression scheme that accelerates pattern matching (1999)"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Shridhar, M., Thomason, J., Gordon, D., Bisk, Y., et al.: ALFRED: a benchmark for interpreting grounded instructions for everyday tasks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Singh, I., Blukis, V., Mousavian, A., Goyal, A., et al.: ProgPrompt: generating situated robot task plans using large language models (2022)","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Song, C.H., Wu, J., Washington, C., Sadler, B.M., et al.: LLM-planner: few-shot grounded planning for embodied agents with large language models (2022)","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Vemprala, S., Bonatti, R., Bucker, A., Kapoor, A.: ChatGPT for robotics: design principles and model abilities. Tech. rep., Microsoft (2023)","DOI":"10.1109\/ACCESS.2024.3387941"},{"key":"23_CR25","unstructured":"Wang, B., Komatsuzaki, A.: GPT-J-6B: a 6 billion parameter autoregressive language model (2021). https:\/\/github.com\/kingoflolz\/mesh-transformer-jax"},{"key":"23_CR26","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners (2021)"},{"key":"23_CR27","unstructured":"Wei, J., et al.: Chain of thought prompting elicits reasoning in large language models (2022)"},{"key":"23_CR28","unstructured":"Zhang, S., Roller, S., Goyal, N., Artetxe, M., et al.: OPT: open pre-trained transformer language models (2022)"}],"container-title":["Lecture Notes in Computer Science","Artificial General Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-33469-6_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T23:44:36Z","timestamp":1729467876000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-33469-6_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031334689","9783031334696"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-33469-6_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"24 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial General Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Stockholm","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 June 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 June 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"agi2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/agi-conf.org\/2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"72","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}