{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T04:00:27Z","timestamp":1781236827621,"version":"3.54.1"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.eswa.2026.133107","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:43:10Z","timestamp":1780674190000},"page":"133107","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Seeing the details to plan ahead: Grounding LLM tree planning in fine-grained perception for embodied agents"],"prefix":"10.1016","volume":"331","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6815-8436","authenticated-orcid":false,"given":"Zihao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7024-2270","authenticated-orcid":false,"given":"Mingsheng","family":"Shang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133107_bib0001","unstructured":"Ahn, M., Brohan, A., Brown, N., Chebotar, Y., Cortes, O., David, B., Finn, C., Fu, C., Gopalakrishnan, K., Hausman, K., & et al., (2022). Do as i can, not as i say: Grounding language in robotic affordances. Technical ReportarXiv: 2204.01691."},{"key":"10.1016\/j.eswa.2026.133107_bib0002","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1016\/j.mee.2010.11.019","article-title":"Design and analysis of the in0.53ga0.47as implant-free quantum-well device structure","volume":"88","author":"Benbakhti","year":"2011","journal-title":"Microelectronic Engineering"},{"key":"10.1016\/j.eswa.2026.133107_bib0003","series-title":"Proceedings of the 5th conference on robot learning, pmlr","first-page":"706","article-title":"A persistent spatial semantic representation for high-level natural language instruction execution","author":"Blukis","year":"2022"},{"key":"10.1016\/j.eswa.2026.133107_bib0004","unstructured":"Brohan, A., Brown, N., Carbajal, J., & et al., (2023). Rt-2: Vision-language-action models transfer web knowledge to robotic control. arxiv: 2307.15818."},{"key":"10.1016\/j.eswa.2026.133107_bib0005","series-title":"Large language models for planning: A comprehensive and systematic survey URL","author":"Cao","year":"2025"},{"key":"10.1016\/j.eswa.2026.133107_bib0006","series-title":"2024 IEEE International Conference on Multimedia and Expo, ICME 2024","article-title":"Common sense language-guided exploration and hierarchical dense perception for instruction following embodied agents","author":"Chen","year":"2024"},{"key":"10.1016\/j.eswa.2026.133107_bib0007","series-title":"The thirteenth international conference on learning representations","article-title":"Scaling autonomous agents via automatic reward modeling and planning","author":"Chen","year":"2025"},{"key":"10.1016\/j.eswa.2026.133107_bib0008","series-title":"2015 6th international conference on power electronics systems and applications (pesa)","first-page":"1","article-title":"Zero emission electric vessel development","author":"Cheng","year":"2015"},{"key":"10.1016\/j.eswa.2026.133107_bib0009","series-title":"Proceedings of the 2023 conference on empirical methods in natural language processing","first-page":"8154","article-title":"Reasoning with language model is planning with world model","author":"Hao","year":"2023"},{"key":"10.1016\/j.eswa.2026.133107_bib0010","series-title":"International conference on learning representations","first-page":"48669","article-title":"Tree-planner: Efficient close-loop task planning with large language models","author":"Hu","year":"2024"},{"key":"10.1016\/j.eswa.2026.133107_bib0011","series-title":"Proceedings of the 39th international conference on machine learning","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","author":"Huang","year":"2022"},{"key":"10.1016\/j.eswa.2026.133107_bib0012","series-title":"Inner monologue: Embodied reasoning through planning with language models 205","author":"Huang","year":"2023"},{"key":"10.1016\/j.eswa.2026.133107_bib0013","doi-asserted-by":"crossref","DOI":"10.1049\/ell2.12758","article-title":"Vector quantization using k-means clustering neural network","volume":"59","author":"Im","year":"2023","journal-title":"Electronics Letters"},{"key":"10.1016\/j.eswa.2026.133107_bib0014","series-title":"Prompter: Utilizing large language model prompting for a data efficient embodied instruction following URL","author":"Inoue","year":"2024"},{"key":"10.1016\/j.eswa.2026.133107_bib0015","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"10936","article-title":"Context-aware planning and environment-aware memory for instruction following embodied agents","author":"Kim","year":"2023"},{"key":"10.1016\/j.eswa.2026.133107_bib0016","series-title":"Proceedings of the aaai conference on artificial intelligence","first-page":"4329","article-title":"Multi-modal grounded planning and efficient replanning for learning embodied agents with a few examples","author":"Kim","year":"2025"},{"key":"10.1016\/j.eswa.2026.133107_bib0017","series-title":"Technical Report","article-title":"Tree search for language model agents","author":"Koh","year":"2024"},{"key":"10.1016\/j.eswa.2026.133107_bib0018","doi-asserted-by":"crossref","first-page":"1413","DOI":"10.3109\/10715762.2012.721928","article-title":"The involvement of serotonin metabolism in cigarette smoke-induced oxidative stress in rat lung in vivo","volume":"46","author":"Lau","year":"2012","journal-title":"Free Radical Research"},{"key":"10.1016\/j.eswa.2026.133107_bib0019","series-title":"Advances in neural information processing systems","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","author":"Li","year":"2020"},{"key":"10.1016\/j.eswa.2026.133107_bib0020","series-title":"Large model empowered embodied ai: A survey on decision-making and embodied learning URL","author":"Liang","year":"2025"},{"key":"10.1016\/j.eswa.2026.133107_bib0021","series-title":"Workshop at the conference on computer vision and pattern recognition (cvpr)","article-title":"A planning based neural-symbolic approach for embodied instruction following","author":"Liu","year":"2022"},{"key":"10.1016\/j.eswa.2026.133107_bib0022","series-title":"International conference on learning representations","article-title":"Film: Following instructions in language with modular methods","author":"Min","year":"2022"},{"key":"10.1016\/j.eswa.2026.133107_bib0023","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"15942","article-title":"Episodic transformer for vision-and-language navigation","author":"Pashevich","year":"2021"},{"key":"10.1016\/j.eswa.2026.133107_bib0024","series-title":"International conference on learning representations","first-page":"92439","article-title":"Discriminator-guided embodied planning for llm agent","author":"Qian","year":"2025"},{"key":"10.1016\/j.eswa.2026.133107_bib0025","series-title":"Advances in neural information processing systems","first-page":"114843","article-title":"Agent planning with world knowledge model","author":"Qiao","year":"2024"},{"key":"10.1016\/j.eswa.2026.133107_bib0026","series-title":"U-net: Convolutional networks for biomedical image segmentation","first-page":"234","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.eswa.2026.133107_bib0027","series-title":"Advances in neural information processing systems","first-page":"8634","article-title":"Reflexion: Language agents with verbal reinforcement learning","author":"Shinn","year":"2023"},{"key":"10.1016\/j.eswa.2026.133107_bib0028","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","article-title":"Alfred: A benchmark for interpreting grounded instructions for everyday tasks","author":"Shridhar","year":"2020"},{"key":"10.1016\/j.eswa.2026.133107_bib0029","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1007\/s10514-023-10135-3","article-title":"ProgPrompt: program generation for situated robot task planning using large language models","volume":"47","author":"Singh","year":"2023","journal-title":"Autonomous Robots"},{"key":"10.1016\/j.eswa.2026.133107_bib0030","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"15482","article-title":"One step at a time: Long-horizon vision-and-language navigation with milestones","author":"Song","year":"2022"},{"key":"10.1016\/j.eswa.2026.133107_bib0031","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"2998","article-title":"Llm-planner: Few-shot grounded planning for embodied agents with large language models","author":"Song","year":"2023"},{"key":"10.1016\/j.eswa.2026.133107_bib0032","series-title":"Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations","author":"Sudre","year":"2017"},{"key":"10.1016\/j.eswa.2026.133107_bib0033","series-title":"2024 international conference on advances in data engineering and intelligent computing systems (adics)","first-page":"1","article-title":"Yolov8: A novel object detection algorithm with enhanced performance and robustness","author":"Varghese","year":"2024"},{"key":"10.1016\/j.eswa.2026.133107_bib0034","series-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2026.133107_bib0035","series-title":"PlanGenLLMs: A modern survey of LLM planning capabilities","author":"Wei","year":"2025"},{"key":"10.1016\/j.eswa.2026.133107_bib0036","series-title":"Proceedings of the 36th international conference on neural information processing systems","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022"},{"key":"10.1016\/j.eswa.2026.133107_bib0037","series-title":"Mldt: Multi-level decomposition for complex long-horizon robotic task planning with open-source large language model","first-page":"251","author":"Wu","year":"2024"},{"key":"10.1016\/j.eswa.2026.133107_bib0038","series-title":"Computer vision - eccv 2024","first-page":"108","article-title":"Disco: Embodied navigation and interaction via differentiable scene semantics and dual-level control","author":"Xu","year":"2025"},{"key":"10.1016\/j.eswa.2026.133107_bib0039","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"17675","article-title":"Mc-bench: A benchmark for multi-context visual grounding in the era of mllms","author":"Xu","year":"2025"},{"key":"10.1016\/j.eswa.2026.133107_bib0040","series-title":"Advances in neural information processing systems","first-page":"11809","article-title":"Tree of thoughts: Deliberate problem solving with large language models","author":"Yao","year":"2023"},{"key":"10.1016\/j.eswa.2026.133107_bib0041","series-title":"International conference on learning representations (iclr)","article-title":"React: Synergizing reasoning and acting in language models","author":"Yao","year":"2023"},{"key":"10.1016\/j.eswa.2026.133107_bib0042","series-title":"International conference on learning representations","first-page":"65157","article-title":"Exact: Teaching ai agents to explore with reflective-mcts and exploratory learning","author":"Yu","year":"2025"},{"key":"10.1016\/j.eswa.2026.133107_bib0043","series-title":"Advances in neural information processing systems","first-page":"31967","article-title":"Large language models as commonsense knowledge for large-scale task planning","author":"Zhao","year":"2023"},{"key":"10.1016\/j.eswa.2026.133107_bib0044","doi-asserted-by":"crossref","first-page":"8574","DOI":"10.1109\/TCYB.2021.3095305","article-title":"Enhancing geometric factors in model learning and inference for object detection and instance segmentation","volume":"52","author":"Zheng","year":"2022","journal-title":"IEEE Transactions on Cybernetics"},{"key":"10.1016\/j.eswa.2026.133107_bib0045","series-title":"Proceedings of the 41st international conference on machine learning","first-page":"62138","article-title":"Language agent tree search unifies reasoning, acting, and planning in language models","author":"Zhou","year":"2024"},{"key":"10.1016\/j.eswa.2026.133107_bib0046","series-title":"International conference on learning representations","first-page":"4524","article-title":"Toolchain* : Efficient action space navigation in large language models with a* search","author":"Zhuang","year":"2024"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742602018X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742602018X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T03:48:08Z","timestamp":1781236088000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095741742602018X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":46,"alternative-id":["S095741742602018X"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133107","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Seeing the details to plan ahead: Grounding LLM tree planning in fine-grained perception for embodied agents","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133107","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133107"}}