{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:29:24Z","timestamp":1792600164655,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102128 & 62021001"],"award-info":[{"award-number":["62102128 & 62021001"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680661","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"6969-6978","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2302-8721","authenticated-orcid":false,"given":"Weiye","family":"Xu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3048-6980","authenticated-orcid":false,"given":"Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_2_2_1","unstructured":"Michael Ahn Anthony Brohan Noah Brown Yevgen Chebotar Omar Cortes Byron David Chelsea Finn Chuyuan Fu Keerthana Gopalakrishnan Karol Hausman et al. 2022. Do as i can not as i say: Grounding language in robotic affordances. arXiv preprint arXiv:2204.01691 (2022)."},{"key":"e_1_3_2_2_3_1","volume-title":"Conference on Robot Learning. PMLR, 706--717","author":"Blukis Valts","year":"2022","unstructured":"Valts Blukis, Chris Paxton, Dieter Fox, Animesh Garg, and Yoav Artzi. 2022. A persistent spatial semantic representation for high-level natural language instruction execution. In Conference on Robot Learning. PMLR, 706--717."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526024"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591630"},{"key":"e_1_3_2_2_6_1","volume-title":"Towards personalized review summarization by modeling historical reviews from customer and product separately. arXiv preprint arXiv:2301.11682","author":"Cheng Xin","year":"2023","unstructured":"Xin Cheng, Shen Gao, Yuchi Zhang, Yongliang Wang, Xiuying Chen, Mingzhe Li, Dongyan Zhao, and Rui Yan. 2023. Towards personalized review summarization by modeling historical reviews from customer and product separately. arXiv preprint arXiv:2301.11682 (2023)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-24337-1_3"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3578623"},{"key":"e_1_3_2_2_9_1","volume-title":"Look before you leap: Unveiling the power of gpt-4v in robotic vision-language planning. arXiv preprint arXiv:2311.17842","author":"Hu Yingdong","year":"2023","unstructured":"Yingdong Hu, Fanqi Lin, Tong Zhang, Li Yi, and Yang Gao. 2023. Look before you leap: Unveiling the power of gpt-4v in robotic vision-language planning. arXiv preprint arXiv:2311.17842 (2023)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"e_1_3_2_2_11_1","volume-title":"Conference on Robot Learning","volume":"229","author":"Huang Wenlong","year":"2023","unstructured":"Wenlong Huang, Chen Wang, Ruohan Zhang, Yunzhu Li, Jiajun Wu, and Li Fei-Fei. 2023. VoxPoser: Composable 3D value maps for robotic manipulation with language models. In Conference on Robot Learning, Vol. 229. PMLR, 540--562."},{"key":"e_1_3_2_2_12_1","unstructured":"Wenlong Huang Fei Xia Ted Xiao Harris Chan Jacky Liang Pete Florence Andy Zeng Jonathan Tompson Igor Mordatch Yevgen Chebotar et al. 2022. Inner monologue: Embodied reasoning through planning with language models. arXiv preprint arXiv:2207.05608 (2022)."},{"key":"e_1_3_2_2_13_1","volume-title":"Mini-BEHAVIOR: A Procedurally generated benchmark for long-horizon decision-making in embodied AI. arXiv preprint arXiv:2310.01824","author":"Jin Emily","year":"2023","unstructured":"Emily Jin, Jiaheng Hu, Zhuoyi Huang, Ruohan Zhang, Jiajun Wu, Li Fei-Fei, and Roberto Mart\u00edn-Mart\u00edn. 2023. Mini-BEHAVIOR: A Procedurally generated benchmark for long-horizon decision-making in embodied AI. arXiv preprint arXiv:2310.01824 (2023)."},{"key":"e_1_3_2_2_14_1","volume-title":"Robotgpt: Robot manipulation learning from chatgpt","author":"Jin Yixiang","year":"2024","unstructured":"Yixiang Jin, Dingzhe Li, A Yong, Jun Shi, Peng Hao, Fuchun Sun, Jianwei Zhang, and Bin Fang. 2024. Robotgpt: Robot manipulation learning from chatgpt. IEEE Robotics and Automation Letters (2024)."},{"key":"e_1_3_2_2_15_1","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-Augmented generation for knowledge-intensive NLP Tasks. In Advances in Neural Information Processing Systems, Vol. 33. Curran Associates, Inc., 9459--9474."},{"key":"e_1_3_2_2_16_1","unstructured":"Chengshu Li Ruohan Zhang Josiah Wong Cem Gokmen Sanjana Srivastava Roberto Mart\u00edn-Mart\u00edn Chen Wang Gabrael Levine Wensi Ai Benjamin Martinez et al. 2024. BEHAVIOR-1K: A Human-Centered Embodied AI Benchmark with 1 000 Everyday Activities and Realistic Simulation. arXiv preprint arXiv:2403.09227 (2024)."},{"key":"e_1_3_2_2_17_1","volume-title":"Enhancing robotic manipulation with AI feedback from multimodal large language models. arXiv preprint arXiv:2402.14245","author":"Liu Jinyi","year":"2024","unstructured":"Jinyi Liu, Yifu Yuan, Jianye Hao, Fei Ni, Lingzhi Fu, Yibin Chen, and Yan Zheng. 2024. Enhancing robotic manipulation with AI feedback from multimodal large language models. arXiv preprint arXiv:2402.14245 (2024)."},{"key":"e_1_3_2_2_18_1","volume-title":"Miguel Eckstein, and William Yang Wang.","author":"Lu Yujie","year":"2022","unstructured":"Yujie Lu, Weixi Feng, Wanrong Zhu, Wenda Xu, Xin Eric Wang, Miguel Eckstein, and William Yang Wang. 2022. Neuro-symbolic procedural planning with commonsense prompting. arXiv preprint arXiv:2206.02928 (2022)."},{"key":"e_1_3_2_2_19_1","volume-title":"R3m: A universal visual representation for robot manipulation. arXiv preprint arXiv:2203.12601","author":"Nair Suraj","year":"2022","unstructured":"Suraj Nair, Aravind Rajeswaran, Vikash Kumar, Chelsea Finn, and Abhinav Gupta. 2022. R3m: A universal visual representation for robot manipulation. arXiv preprint arXiv:2203.12601 (2022)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01564"},{"key":"e_1_3_2_2_21_1","series-title":"SIAM review","volume-title":"Fast marching methods","author":"Sethian James A","year":"1999","unstructured":"James A Sethian. 1999. Fast marching methods. SIAM review, Vol. 41, 2 (1999), 199--235."},{"key":"e_1_3_2_2_22_1","volume-title":"Plan Diffuser: Grounding LLM planners with diffusion models for robotic manipulation. In Bridging the Gap between Cognitive Science and Robot Learning in the Real World: Progresses and New Directions.","author":"Sharan SP","year":"2024","unstructured":"SP Sharan, Ruihan Zhao, Zhangyang Wang, Sandeep P Chinchali, et al. 2024. Plan Diffuser: Grounding LLM planners with diffusion models for robotic manipulation. In Bridging the Gap between Cognitive Science and Robot Learning in the Real World: Progresses and New Directions."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"e_1_3_2_2_24_1","volume-title":"Alfworld: Aligning text and embodied environments for interactive learning. arXiv preprint arXiv:2010.03768","author":"Shridhar Mohit","year":"2020","unstructured":"Mohit Shridhar, Xingdi Yuan, Marc-Alexandre C\u00f4t\u00e9, Yonatan Bisk, Adam Trischler, and Matthew Hausknecht. 2020. Alfworld: Aligning text and embodied environments for interactive learning. arXiv preprint arXiv:2010.03768 (2020)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"e_1_3_2_2_26_1","volume-title":"Language-conditional imitation learning","author":"Skirzynski Julian","unstructured":"Julian Skirzynski. 2020. Language-conditional imitation learning. McGill University (Canada)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01504"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1"},{"key":"e_1_3_2_2_31_1","first-page":"5776","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume":"33","author":"Wang Wenhui","year":"2020","unstructured":"Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in Neural Information Processing Systems, Vol. 33 (2020), 5776--5788.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_32_1","volume-title":"International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Xiuying Chen","year":"2022","unstructured":"Chen Xiuying, Alamro Hind, Li Mingzhe, Gao Shen, Yan Rui, Gao Xin, and Zhang Xiangliang. 2022. Target-aware abstractive related work generation with contrastive learning. International ACM SIGIR Conference on Research and Development in Information Retrieval (2022)."},{"key":"e_1_3_2_2_33_1","volume-title":"Conference on Robot Learning. PMLR, 589--603","author":"Yamada Jun","year":"2021","unstructured":"Jun Yamada, Youngwoon Lee, Gautam Salhotra, Karl Pertsch, Max Pflueger, Gaurav Sukhatme, Joseph Lim, and Peter Englert. 2021. Motion planner augmented reinforcement learning for robot manipulation in obstructed environments. In Conference on Robot Learning. PMLR, 589--603."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3607540.3617143"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME55016.2022.00016"},{"key":"e_1_3_2_2_36_1","volume-title":"RAP: Retrieval-Augmented planner for adaptive procedure planning in instructional videos. arXiv preprint arXiv:2403.18600","author":"Zare Ali","year":"2024","unstructured":"Ali Zare, Yulei Niu, Hammad Ayyubi, and Shih-fu Chang. 2024. RAP: Retrieval-Augmented planner for adaptive procedure planning in instructional videos. arXiv preprint arXiv:2403.18600 (2024)."},{"key":"e_1_3_2_2_37_1","volume-title":"Deep RL Workshop of Neural Information Processing Systems Conference.","author":"Zhan Albert","year":"2021","unstructured":"Albert Zhan, Ruihan Zhao, Lerrel Pinto, Pieter Abbeel, and Michael Laskin. 2021. A framework for efficient robotic manipulation. In Deep RL Workshop of Neural Information Processing Systems Conference."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.90"},{"key":"e_1_3_2_2_39_1","volume-title":"Hierarchical task learning from language instructions with unified transformers and self-monitoring. arXiv preprint arXiv:2106.03427","author":"Zhang Yichi","year":"2021","unstructured":"Yichi Zhang and Joyce Chai. 2021. Hierarchical task learning from language instructions with unified transformers and self-monitoring. arXiv preprint arXiv:2106.03427 (2021)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548281"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531366"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680661","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:57Z","timestamp":1750295877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680661"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":40,"alternative-id":["10.1145\/3664647.3680661","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680661","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}