{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:15:35Z","timestamp":1742919335360,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819789627"},{"type":"electronic","value":"9789819789634"}],"license":[{"start":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T00:00:00Z","timestamp":1735084800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T00:00:00Z","timestamp":1735084800000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8963-4_19","type":"book-chapter","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T22:59:56Z","timestamp":1735081196000},"page":"198-207","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Agent-Based Robot via Large Language Model"],"prefix":"10.1007","author":[{"given":"Ziyu","family":"Liu","sequence":"first","affiliation":[]},{"given":"Congzhi","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Ruihang","family":"Ji","sequence":"additional","affiliation":[]},{"given":"Min","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Shuzhi Sam","family":"Ge","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,25]]},"reference":[{"key":"19_CR1","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/s10846-008-9235-4","volume":"53","author":"F Bonin-Font","year":"2008","unstructured":"Bonin-Font, F., Ortiz, A., Oliver, G.: Visual navigation for mobile robots: a survey. J. Intell. Rob. Syst. 53, 263\u2013296 (2008)","journal-title":"J. Intell. Rob. Syst."},{"key":"19_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/978-3-030-58607-2_18","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Qi","year":"2020","unstructured":"Qi, Y., Pan, Z., Zhang, S., van den Hengel, A., Wu, Q.: Object-and-action aware model for visual language navigation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 303\u2013317. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_18"},{"key":"19_CR3","unstructured":"Chen, S., Xiao, A., Hsu, D.: LLM-state: expandable state representation for long-horizon task planning in the open world. arXiv preprint arXiv:2311.17406 (2023)"},{"key":"19_CR4","unstructured":"Sahoo, P., Singh, A.K., Saha, S., Jain, V., Mondal, S., Chadha, A.: A systematic survey of prompt engineering in large language models: techniques and applications. arXiv preprint arXiv:2402.07927 (2024)"},{"issue":"8","key":"19_CR5","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Jeffrey, W., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"19_CR6","unstructured":"Wei, J., et\u00a0al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 24824\u201324837 (2022)"},{"key":"19_CR7","unstructured":"Feng, G., Zhang, B., Gu, Y., Ye, H., He, D., Wang, L.: Towards revealing the mystery behind chain of thought: a theoretical perspective. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"19_CR8","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)"},{"key":"19_CR9","unstructured":"Lyu, Q., et al.: Faithful chain-of-thought reasoning. arXiv preprint arXiv:2301.13379 (2023)"},{"key":"19_CR10","unstructured":"Long, J.: Large language model guided tree-of-thought. arXiv preprint arXiv:2305.08291 (2023)"},{"key":"19_CR11","unstructured":"Liu, H., Sferrazza, C., Abbeel, P.: Chain of hindsight aligns language models with feedback. arXiv preprint arXiv:2302.02676 (2023)"},{"key":"19_CR12","unstructured":"Yao, S., et al.: React: synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2022)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Hotpotqa: a dataset for diverse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600 (2018)","DOI":"10.18653\/v1\/D18-1259"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"H\u00f6ller, D., Behnke, G., Bercher, P., Biundo, S., Fiorino, H., Pellier, D., Alford, R.: HDDL: an extension to PDDL for expressing hierarchical planning problems. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 9883\u20139891 (2020)","DOI":"10.1609\/aaai.v34i06.6542"},{"key":"19_CR15","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":"19_CR16","first-page":"20744","volume":"35","author":"S Yao","year":"2022","unstructured":"Yao, S., Chen, H., Yang, J., Narasimhan, K.: Webshop: towards scalable real-world web interaction with grounded language agents. Adv. Neural. Inf. Process. Syst. 35, 20744\u201320757 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR17","unstructured":"Prasad, A., et al.: Adapt: as-needed decomposition and planning with language models. arXiv preprint arXiv:2311.05772 (2023)"},{"key":"19_CR18","unstructured":"Liu, B., et al.: LLM+ P: empowering large language models with optimal planning proficiency. arXiv preprint arXiv:2304.11477 (2023)"},{"key":"19_CR19","unstructured":"Khot, T., et al.: Decomposed prompting: a modular approach for solving complex tasks. arXiv preprint arXiv:2210.02406 (2022)"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: A survey on large language model based autonomous agents. Front. Comp. Sci. 18(6), 186345 (2024)","DOI":"10.1007\/s11704-024-40231-1"},{"key":"19_CR21","unstructured":"Weng, L.: LLM powered autonomous agents (2023)"},{"key":"19_CR22","unstructured":"Karpas, E., et\u00a0al.: MRKL systems: a modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning. arXiv preprint arXiv:2205.00445 (2022)"},{"key":"19_CR23","unstructured":"Parisi, A., Zhao, Y., Fiedel, N.: TALM: tool augmented language models. arXiv preprint arXiv:2205.12255 (2022)"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Wu, J., et\u00a0al.: Towards open vocabulary learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14393\u201314402 (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"19_CR26","unstructured":"Huang, Z., Zeng, Z., Liu, B., Fu, D., Fu, J.: Pixel-bert: aligning image pixels with text by deep multi-modal transformers. arXiv preprint arXiv:2004.00849 (2020)"},{"key":"19_CR27","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"19_CR28","unstructured":"Zhang, H., et al.: Dino: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Cheng, T., Song, L., Ge, Y., Liu, W., Wang, X., Shan, Y.: Yolo-world: real-time open-vocabulary object detection. arXiv preprint arXiv:2401.17270 (2024)","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"19_CR31","unstructured":"Quigley, M., et\u00a0al.: ROS: an open-source robot operating system. In: ICRA Workshop on Open Source Software, vol.\u00a03, p.\u00a05. Kobe, Japan (2009)"},{"key":"19_CR32","unstructured":"Xue, F., Fu, Y., Zhou, W., Zheng, Z., You, Y.: To repeat or not to repeat: insights from scaling LLM under token-crisis. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"}],"container-title":["Lecture Notes in Computer Science","Social Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8963-4_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T23:03:00Z","timestamp":1735081380000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8963-4_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,25]]},"ISBN":["9789819789627","9789819789634"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8963-4_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,25]]},"assertion":[{"value":"25 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICSR + BioMed","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Social Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 August 2024","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":"socrob2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/robicon2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}