{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T10:36:41Z","timestamp":1758191801330,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,18]]},"DOI":"10.1145\/3719545.3721029","type":"proceedings-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T09:38:41Z","timestamp":1758015521000},"page":"22-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Command : Real-Time Policy Adjustment via Language Models in StarCraft II"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7359-1753","authenticated-orcid":false,"given":"Weiyu","family":"Ma","sequence":"first","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4169-7577","authenticated-orcid":false,"given":"Dongyu","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3159-8685","authenticated-orcid":false,"given":"Shu","family":"Lin","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4502-1760","authenticated-orcid":false,"given":"Haifeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4021-4228","authenticated-orcid":false,"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"University College London, London, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et\u00a0al. 2023. Qwen technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.16609 (2023)."},{"key":"e_1_3_3_2_3_2","first-page":"1989","volume-title":"International Conference on Machine Learning","author":"Christianos Filippos","year":"2021","unstructured":"Filippos Christianos, Georgios Papoudakis, Muhammad\u00a0A Rahman, and Stefano\u00a0V Albrecht. 2021. Scaling multi-agent reinforcement learning with selective parameter sharing. In International Conference on Machine Learning. PMLR, 1989\u20131998."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-24337-1_3"},{"key":"e_1_3_3_2_5_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et\u00a0al. 2024. The llama 3 herd of models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.21783 (2024)."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Xueyang Feng Zhi-Yuan Chen Yujia Qin Yankai Lin Xu Chen Zhiyuan Liu and Ji-Rong Wen. 2024. Large Language Model-based Human-Agent Collaboration for Complex Task Solving. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.12914 (2024).","DOI":"10.18653\/v1\/2024.findings-emnlp.72"},{"key":"e_1_3_3_2_7_2","unstructured":"Ran Gong Qiuyuan Huang Xiaojian Ma Hoi Vo Zane Durante Yusuke Noda Zilong Zheng Song-Chun Zhu Demetri Terzopoulos Li Fei-Fei et\u00a0al. 2023. MindAgent: Emergent Gaming Interaction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.09971 (2023)."},{"key":"e_1_3_3_2_8_2","unstructured":"Lei Han Jiechao Xiong Peng Sun Xinghai Sun Meng Fang Qingwei Guo Qiaobo Chen Tengfei Shi Hongsheng Yu Xipeng Wu et\u00a0al. 2020. Tstarbot-x: An open-sourced and comprehensive study for efficient league training in starcraft ii full game. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2011.13729 (2020)."},{"key":"e_1_3_3_2_9_2","unstructured":"Shengchao Hu Li Shen Ya Zhang and Dacheng Tao. 2024. Learning multi-agent communication from graph modeling perspective. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.08550 (2024)."},{"key":"e_1_3_3_2_10_2","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Huang Ruozi","year":"2023","unstructured":"Ruozi Huang, Xipeng Wu, Hongsheng Yu, Zhong Fan, Haobo Fu, QIANG FU, and Yang Wei. 2023. A Robust and Opponent-Aware League Training Method for StarCraft II. In Thirty-seventh Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Hao Jiang Dianxi Shi Chao Xue Yajie Wang Gongju Wang and Yongjun Zhang. 2021. Multi-agent deep reinforcement learning with type-based hierarchical group communication. Applied Intelligence 51 (2021) 5793\u20135808.","DOI":"10.1007\/s10489-020-02065-9"},{"key":"e_1_3_3_2_12_2","unstructured":"Xuanfa Jin Ziyan Wang Yali Du Meng Fang Haifeng Zhang and Jun Wang. 2024. Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.19946 (2024)."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Ruo-Ze Liu Haifeng Guo Xiaozhong Ji Yang Yu Zhen-Jia Pang Zitai Xiao Yuzhou Wu and Tong Lu. 2021. Efficient reinforcement learning for starcraft by abstract forward models and transfer learning. IEEE Transactions on Games 14 2 (2021) 294\u2013307.","DOI":"10.1109\/TG.2021.3071162"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Ruo-Ze Liu Zhen-Jia Pang Zhou-Yu Meng Wenhai Wang Yang Yu and Tong Lu. 2022. On efficient reinforcement learning for full-length game of starcraft ii. Journal of Artificial Intelligence Research 75 (2022) 213\u2013260.","DOI":"10.1613\/jair.1.13743"},{"key":"e_1_3_3_2_15_2","unstructured":"Ruo-Ze Liu Wenhai Wang Yanjie Shen Zhiqi Li Yang Yu and Tong Lu. 2021. An Introduction of mini-AlphaStar. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.06890 (2021)."},{"key":"e_1_3_3_2_16_2","unstructured":"Xiao Liu Hao Yu Hanchen Zhang Yifan Xu Xuanyu Lei Hanyu Lai Yu Gu Hangliang Ding Kaiwen Men Kejuan Yang et\u00a0al. 2023. Agentbench: Evaluating llms as agents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.03688 (2023)."},{"key":"e_1_3_3_2_17_2","unstructured":"Weiyu Ma Qirui Mi Yongcheng Zeng Xue Yan Yuqiao Wu Runji Lin Haifeng Zhang and Jun Wang. 2024. Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach. arxiv:https:\/\/arXiv.org\/abs\/2312.11865\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2312.11865"},{"key":"e_1_3_3_2_18_2","volume-title":"Deep RL Workshop NeurIPS 2021","author":"Mathieu Michael","year":"2021","unstructured":"Michael Mathieu, Sherjil Ozair, Srivatsan Srinivasan, Caglar Gulcehre, Shangtong Zhang, Ray Jiang, Tom Le\u00a0Paine, Konrad Zolna, Richard Powell, Julian Schrittwieser, et\u00a0al. 2021. Starcraft ii unplugged: Large scale offline reinforcement learning. In Deep RL Workshop NeurIPS 2021."},{"key":"e_1_3_3_2_19_2","unstructured":"OpenAI. 2023. GPT-4 Technical Report. ArXiv abs\/2303.08774 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257532815"},{"key":"e_1_3_3_2_20_2","unstructured":"Peng Peng Ying Wen Yaodong Yang Quan Yuan Zhenkun Tang Haitao Long and Jun Wang. 2017. Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play starcraft combat games. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1703.10069 (2017)."},{"key":"e_1_3_3_2_21_2","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:https:\/\/arXiv.org\/abs\/2010.03768 (2020)."},{"key":"e_1_3_3_2_22_2","unstructured":"Weihao Tan Ziluo Ding Wentao Zhang Boyu Li Bohan Zhou Junpeng Yue Haochong Xia Jiechuan Jiang Longtao Zheng Xinrun Xu et\u00a0al. 2024. Towards general computer control: A multimodal agent for red dead redemption ii as a case study. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.03186 (2024)."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Oriol Vinyals Igor Babuschkin Wojciech\u00a0M Czarnecki Micha\u00ebl Mathieu Andrew Dudzik Junyoung Chung David\u00a0H Choi Richard Powell Timo Ewalds Petko Georgiev et\u00a0al. 2019. Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575 7782 (2019) 350\u2013354.","DOI":"10.1038\/s41586-019-1724-z"},{"key":"e_1_3_3_2_24_2","unstructured":"Oriol Vinyals Timo Ewalds Sergey Bartunov Petko Georgiev Alexander\u00a0Sasha Vezhnevets Michelle Yeo Alireza Makhzani Heinrich K\u00fcttler John Agapiou Julian Schrittwieser et\u00a0al. 2017. Starcraft ii: A new challenge for reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1708.04782 (2017)."},{"key":"e_1_3_3_2_25_2","unstructured":"Guanzhi Wang Yuqi Xie Yunfan Jiang Ajay Mandlekar Chaowei Xiao Yuke Zhu Linxi Fan and Anima Anandkumar. 2023. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.16291 (2023)."},{"key":"e_1_3_3_2_26_2","first-page":"10905","volume-title":"International conference on machine learning","author":"Wang Xiangjun","year":"2021","unstructured":"Xiangjun Wang, Junxiao Song, Penghui Qi, Peng Peng, Zhenkun Tang, Wei Zhang, Weimin Li, Xiongjun Pi, Jujie He, Chao Gao, et\u00a0al. 2021. SCC: An efficient deep reinforcement learning agent mastering the game of StarCraft II. In International conference on machine learning. PMLR, 10905\u201310915."},{"key":"e_1_3_3_2_27_2","first-page":"10905","volume-title":"International conference on machine learning","author":"Wang Xiangjun","year":"2021","unstructured":"Xiangjun Wang, Junxiao Song, Penghui Qi, Peng Peng, Zhenkun Tang, Wei Zhang, Weimin Li, Xiongjun Pi, Jujie He, Chao Gao, et\u00a0al. 2021. SCC: An efficient deep reinforcement learning agent mastering the game of StarCraft II. In International conference on machine learning. PMLR, 10905\u201310915."},{"key":"e_1_3_3_2_28_2","unstructured":"Xuezhi Wang Jason Wei Dale Schuurmans Quoc Le Ed Chi Sharan Narang Aakanksha Chowdhery and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.11171 (2022)."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1117\/12.2519138"},{"key":"e_1_3_3_2_30_2","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le Denny Zhou et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022) 24824\u201324837."},{"key":"e_1_3_3_2_31_2","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang et\u00a0al. 2024. Qwen2 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.10671 (2024)."},{"key":"e_1_3_3_2_32_2","unstructured":"Shunyu Yao Jeffrey Zhao Dian Yu Nan Du Izhak Shafran Karthik Narasimhan and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.03629 (2022)."},{"key":"e_1_3_3_2_33_2","unstructured":"Xizhou Zhu Yuntao Chen Hao Tian Chenxin Tao Weijie Su Chenyu Yang Gao Huang Bin Li Lewei Lu Xiaogang Wang et\u00a0al. 2023. Ghost in the Minecraft: Generally Capable Agents for Open-World Enviroments via Large Language Models with Text-based Knowledge and Memory. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.17144 (2023)."}],"event":{"name":"DAI '24: 6th International Conference on Distributed Artificial Intelligences","acronym":"DAI '24","location":"Singapore Singapore"},"container-title":["Proceedings of the 2024 Sixth International Conference on Distributed Artificial Intelligences"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3719545.3721029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T13:13:16Z","timestamp":1758114796000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3719545.3721029"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,18]]},"references-count":32,"alternative-id":["10.1145\/3719545.3721029","10.1145\/3719545"],"URL":"https:\/\/doi.org\/10.1145\/3719545.3721029","relation":{},"subject":[],"published":{"date-parts":[[2024,12,18]]},"assertion":[{"value":"2025-09-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}