{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T11:58:00Z","timestamp":1773403080262,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650094","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["RRdE: A Decision Making Framework for Language Agents in Interactive Environments"],"prefix":"10.1109","author":[{"given":"Xufeng","family":"Zhou","sequence":"first","affiliation":[{"name":"Institute of Automation,Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linjing","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation,Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel Dajun","family":"Zeng","sequence":"additional","affiliation":[{"name":"Institute of Automation,Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reflexion: Language Agents with Verbal Reinforcement Learning","author":"Shinn"},{"key":"ref2","volume-title":"Cognitive Architectures for Language Agents","author":"Sumers"},{"key":"ref3","doi-asserted-by":"crossref","article-title":"A Survey on Large Language Model based Autonomous Agents","author":"Wang","DOI":"10.1007\/s11704-024-40231-1"},{"key":"ref4","doi-asserted-by":"crossref","volume-title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","author":"Bang","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.acl-long.405","article-title":"MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation","volume-title":"Association for Computational Linguistics","author":"Feng"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"ref7","volume-title":"Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf","author":"Xu"},{"key":"ref8","volume-title":"MemoryBank: Enhancing Large Language Models with Long-Term Memory","author":"Zhong"},{"key":"ref9","article-title":"Swiftsage: A generative agent with fast and slow thinking for complex interactive tasks","volume-title":"Thirtyseventh Conference on Neural Information Processing Systems","author":"Lin"},{"key":"ref10","article-title":"Self-refine: Iterative refinement with self-feedback","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Madaan"},{"key":"ref11","volume-title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","author":"Wang"},{"key":"ref12","article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Yao"},{"key":"ref13","article-title":"React: Synergizing reasoning and acting in language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yao"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1038\/s42256-024-00832-8","article-title":"Augmenting large language models with chemistry tools","volume-title":"NeurIPS 2023 AI for Science Workshop","author":"Bran"},{"key":"ref15","article-title":"OpenAGI: When LLM meets domain experts","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Ge"},{"key":"ref16","volume-title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","author":"Liu"},{"key":"ref17","article-title":"Toolformer: Language models can teach themselves to use tools","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Schick"},{"key":"ref18","article-title":"Alfworld: Aligning text and embodied environments for interactive learning","volume-title":"International Conference on Learning Representations","author":"Shridhar"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2022.emnlp-main.775","article-title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","volume-title":"Conference on Empirical Methods in Natural Language Processing","author":"Wang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/0965431042000194994"},{"key":"ref21","first-page":"873","article-title":"A survey of text games for reinforcement learning informed by natural language","volume-title":"Transactions of the Association for Computational Linguistics","volume":"10","author":"Osborne","year":"2022"},{"key":"ref22","first-page":"1","article-title":"Language understanding for text-based games using deep reinforcement learning","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Narasimhan"},{"key":"ref23","first-page":"1621","article-title":"Deep Reinforcement Learning with a Natural Language Action Space","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"He"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-24337-1_3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6297"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"8736","DOI":"10.18653\/v1\/2020.emnlp-main.704","article-title":"Keep CALM and explore: Language models for action generation in text-based games","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Yao","year":"2020"},{"key":"ref27","article-title":"Graph constrained reinforcement learning for natural language action spaces","volume-title":"International Conference on Learning Representations","author":"Ammanabrolu"},{"key":"ref28","first-page":"3676","article-title":"Grounding large language models in interactive environments with online reinforcement learning","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Carta"},{"key":"ref29","article-title":"ScriptWorld: A Scripts-based RL Environment","author":"Joshi"},{"key":"ref30","first-page":"11","article-title":"Planning Theories: Typologies and Overcrowding","volume-title":"Compromise Planning : A Theoretical Approach from a Distant Corner of Europe","author":"Wassenhoven"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650094.pdf?arnumber=10650094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:23:44Z","timestamp":1725949424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650094\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650094","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}