{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:24:56Z","timestamp":1778171096093,"version":"3.51.4"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tcsvt.2025.3538860","type":"journal-article","created":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T13:47:34Z","timestamp":1738936054000},"page":"6481-6493","source":"Crossref","is-referenced-by-count":3,"title":["Visual Environment-Interactive Planning for Embodied Complex-Question Answering"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3584-8540","authenticated-orcid":false,"given":"Ning","family":"Lan","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baoshan","family":"Ou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7857-0845","authenticated-orcid":false,"given":"Xuemei","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2179-3292","authenticated-orcid":false,"given":"Guangming","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3401451"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233554"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3324380"},{"key":"ref5","article-title":"Embodied LLM agents learn to cooperate in organized teams","author":"Guo","year":"2024","journal-title":"arXiv:2403.12482"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref7","first-page":"1","article-title":"SayPlan: Grounding large language models using 3D scene graphs for scalable robot task planning","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Rana"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.112"},{"key":"ref9","article-title":"From LLM to conversational agent: A memory enhanced architecture with fine-tuning of large language models","author":"Liu","year":"2024","journal-title":"arXiv:2401.02777"},{"key":"ref10","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","author":"Ramakrishnan","year":"2021","journal-title":"arXiv:2109.08238"},{"key":"ref11","first-page":"53","article-title":"Neural modular control for embodied question answering","volume-title":"Proc. Conf. Robot Learn.","author":"Das"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00976"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_39"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00682"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801314"},{"key":"ref18","article-title":"Embodied question answering via multi-LLM systems","author":"Patel","year":"2024","journal-title":"arXiv:2406.10918"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.089"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26889-2_13"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.079"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812179"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01670-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3291131"},{"key":"ref25","article-title":"GRID: Scene-Graph-based instruction-driven robotic task planning","author":"Ni","year":"2023","journal-title":"arXiv:2309.07726"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v34i1.31506"},{"key":"ref27","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref28","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lee"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2024.1455375"},{"key":"ref30","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022","journal-title":"arXiv:2207.05608"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref34","article-title":"LLM+P: Empowering large language models with optimal planning proficiency","author":"Liu","year":"2023","journal-title":"arXiv:2304.11477"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611163"},{"key":"ref36","article-title":"ReAct: Synergizing reasoning and acting in language models","author":"Yao","year":"2022","journal-title":"arXiv:2210.03629"},{"key":"ref37","article-title":"Language agent tree search unifies reasoning acting and planning in language models","author":"Zhou","year":"2023","journal-title":"arXiv:2310.04406"},{"key":"ref38","first-page":"1","article-title":"Reflexion: Language agents with verbal reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Shinn"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.448"},{"key":"ref40","first-page":"1","article-title":"AgentVerse: Facilitating multi-agent collaboration and exploring emergent behaviors","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3347722"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3053577"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11071401\/10877885.pdf?arnumber=10877885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:40:40Z","timestamp":1767638440000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10877885\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":42,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3538860","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}