{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T07:13:52Z","timestamp":1777187632596,"version":"3.51.4"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF RTML","doi-asserted-by":"publisher","award":["CCF-1937403"],"award-info":[{"award-number":["CCF-1937403"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128105","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1217-1224","source":"Crossref","is-referenced-by-count":3,"title":["Retrieval-Augmented Hierarchical in-Context Reinforcement Learning and Hindsight Modular Reflections for Task Planning with LLMs"],"prefix":"10.1109","author":[{"given":"Chuanneng","family":"Sun","sequence":"first","affiliation":[{"name":"Rutgers University-New Brunswick,Dept. of Electrical and Computer Engineering,NJ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songjun","family":"Huang","sequence":"additional","affiliation":[{"name":"Rutgers University-New Brunswick,Dept. of Electrical and Computer Engineering,NJ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiqiao","family":"Liu","sequence":"additional","affiliation":[{"name":"Rutgers University-New Brunswick,Dept. of Civil and Environmental Engineering,NJ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Gong","sequence":"additional","affiliation":[{"name":"Rutgers University-New Brunswick,Dept. of Civil and Environmental Engineering,NJ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dario","family":"Pompili","sequence":"additional","affiliation":[{"name":"Rutgers University-New Brunswick,Dept. of Electrical and Computer Engineering,NJ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"240","key":"ref2","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","article-title":"Comparative analysis of pooling mechanisms in llms: A sentiment analysis perspective","volume":"abs\/2411.14654","author":"Xing","year":"2024","journal-title":"CoRR"},{"key":"ref4","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Advances in neural infor-mation processing systems"},{"key":"ref6","article-title":"Language-conditioned path planning","volume-title":"7th Annual Conference on Robot Learning","author":"Xie","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611462"},{"key":"ref8","article-title":"Language-guided robot grasping: CLIP-based referring grasp synthe-sis in clutter","volume-title":"7th Annual Conference on Robot Learning","author":"Tziafas","year":"2023"},{"key":"ref9","article-title":"Language embedded radiance fields for zero-shot task-oriented grasping","volume-title":"7th Annual Conference on Robot Learning","author":"Rashid","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00280"},{"key":"ref11","article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning","volume-title":"7th Annual Conference on Robot Learning","author":"Rana","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610065"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611090"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611163"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611164"},{"key":"ref16","article-title":"Scaling up and distilling down: Language-guided robot skill acquisition","volume-title":"7th Annual Conference on Robot Learning","author":"Ha","year":"2023"},{"key":"ref17","article-title":"Bootstrap your own skills: Learning to solve new tasks with large language model guidance","volume-title":"7th Annual Conference on Robot Learning","author":"Zhang","year":"2023"},{"key":"ref18","article-title":"Findthis: Language-driven object disambiguation in indoor environments","volume-title":"7th Annual Conference on Robot Learning","author":"Majumdar","year":"2023"},{"key":"ref19","article-title":"Leveraging language for accelerated learning of tool manipulation","volume-title":"6th Annual Conference on Robot Learning","author":"Ren","year":"2022"},{"key":"ref20","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"6th Annual Conference on Robot Learning","author":"Shridhar","year":"2022"},{"key":"ref21","article-title":"Mod-ularity through attention: Efficient training and transfer of language-conditioned policies for robot manipulation","volume-title":"6th Annual Conference on Robot Learning","author":"Zhou","year":"2022"},{"key":"ref22","article-title":"R3m: A universal visual representation for robot manipulation","volume-title":"6th Annual Conference on Robot Learning","author":"Nair","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610744"},{"key":"ref24","article-title":"LIm-based multi-agent rein-forcement learning: Current and future directions","author":"Sun","year":"2024","journal-title":"ar Xiv preprint ar Xiv: 2405.11106"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/mcte62870.2024.11117238"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCASIT62299.2024.10828100"},{"key":"ref27","article-title":"Optimizing load scheduling in power grids using rein-forcement learning and markov decision processes","author":"Luo","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref28","first-page":"v l","article-title":"Decentralized energy markets: Designing incentive mechanisms for small-scale renewable energy producers","volume":"202411","author":"Luo","year":"2024","journal-title":"Preprints p rep rints"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICAICA63239.2024.10823054"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MASS50613.2020.00030"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/DCOSS-IoT61029.2024.00060"},{"key":"ref32","article-title":"Carl: Cascade reinforcement learning with state space splitting for o-ran based traffic steering","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MASS62177.2024.00064"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"113","DOI":"10.32604\/jai.2020.010137","article-title":"Truly proximal policy optimization","author":"Wang","year":"2020","journal-title":"Uncertainty in artificial intelligence"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/DCOSS-IoT61029.2024.00014"},{"key":"ref37","article-title":"Learning multi-level hierarchies with hindsight","volume-title":"International Conference on Learning Representations","author":"Levy"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref39","article-title":"ALFWorld: Aligning text and embodied environ-ments for interactive learning","volume-title":"International Conference on Learning Representations","author":"Shridhar","year":"2021"},{"key":"ref40","first-page":"20744","article-title":"Webshop: To-wards scalable real-world web interaction with grounded language agents","volume":"35","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"ref42","article-title":"React: Synergizing reasoning and acting in language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yao","year":"2023"},{"key":"ref43","article-title":"Reflexion: Language agents with verbal reinforcement learning","volume":"36","author":"Shinn","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.264"},{"key":"ref45","article-title":"Large language mod-els can implement policy iteration","volume":"36","author":"Brooks","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.507"},{"key":"ref47","article-title":"Rex: Rapid exploration and exploitation for ai agents","volume-title":"ICLR 2024 Workshop on Large Language Model (LLM) Agents","author":"Rithesh"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29936"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.049"},{"key":"ref50","article-title":"Retroformer: Retrospective large language agents with policy gradient optimization","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yao","year":"2023"},{"key":"ref51","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2021"},{"key":"ref52","article-title":"Fgatt: A robust framework for wireless data imputation using fuzzy graph attention networks and transformer encoders","author":"Xing","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Multi-view fuzzy graph attention networks for enhanced graph learning","author":"Xing","year":"2024","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128105.pdf?arnumber=11128105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:06:50Z","timestamp":1756879610000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128105\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128105","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}