{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T09:49:24Z","timestamp":1774000164789,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,12]]},"DOI":"10.1145\/3788149.3788184","type":"proceedings-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:35:19Z","timestamp":1773988519000},"page":"602-609","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning-Enhanced Large Language Model Approach for Intelligent Dynamic Weapon-Target Allocation Decision-Making"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5183-9585","authenticated-orcid":false,"given":"Lecong","family":"Cheng","sequence":"first","affiliation":[{"name":"National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2965-8825","authenticated-orcid":false,"given":"Jiongming","family":"Su","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1459-8424","authenticated-orcid":false,"given":"Hongfu","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6151-4375","authenticated-orcid":false,"given":"Jing","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"e_1_3_3_1_1_2","unstructured":"T. Yao Y. Wang and Y. Dong. 2020. Application of Deep Reinforcement Learning in Combat Mission Planning.\u00a0Airborne Missile\u00a0(2020) 16\u201321."},{"key":"e_1_3_3_1_2_2","unstructured":"X. Tang and J. S. Wu. 2022. Distributed Dynamic Fire Allocation Method Based on Multi-agent Proximal Policy Optimization.\u00a0Science and Technology Innovation and Application\u00a012 19 (2022) 13\u201317."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"S. Li X. He and X. Xu. 2023. Weapon-Target Assignment Strategy in Joint Combat Decision-Making based on Multi-head Deep Reinforcement Learning.\u00a0IEEE Access\u00a011 (2023) 113740\u2013113751. DOI: 10.1109\/ACCESS.2023.3324193.","DOI":"10.1109\/ACCESS.2023.3324193"},{"key":"e_1_3_3_1_4_2","volume":"201","author":"Yan D.","unstructured":"D. Yan, H. Su, and J. Zhu. 2019. Research on Fire Distribution Method of Anti-ship Missile Based on DQN.\u00a0Navigation Positioning and Timing\u00a06, 5 (2019), 18\u201324.","journal-title":"J. Zhu."},{"key":"e_1_3_3_1_5_2","volume-title":"In\u00a0Proceedings of the 39th International Conference on Machine Learning\u00a0(ICML'22)","author":"Parisi S.","unstructured":"S. Parisi, A. Rajeswaran, S. Purushwalkam, and S. Gupta. 2022. The unsurprising effectiveness of pre-trained vision models for control. In\u00a0Proceedings of the 39th International Conference on Machine Learning\u00a0(ICML'22).\u00a0Baltimore, Maryland, USA."},{"key":"e_1_3_3_1_6_2","volume-title":"In\u00a0Proceedings of the 39th International Conference on Machine Learning\u00a0(ICML'22)","author":"Huang W. L.","unstructured":"W. L. Huang, P. Abbeel, D. Pathak, and I. Mordatch. 2022. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In\u00a0Proceedings of the 39th International Conference on Machine Learning\u00a0(ICML'22). Baltimore, Maryland, USA."},{"key":"e_1_3_3_1_7_2","unstructured":"Y. X. Sun J. J. Zhao and Y. X. Xie. 2024. Self-generating wargame AI: two-layer agent task planning based on large language model.\u00a0Control and Decision\u00a039 12 (2024) 3927\u20133936."},{"key":"e_1_3_3_1_8_2","unstructured":"Y. Tao R. P. Yang and Y. W. Lu. 2024. Intelligent generation method of joint operation plan based on KG+LLM.\u00a0Journal of Command and Control\u00a010 6 (2024) 699\u2013711."},{"key":"e_1_3_3_1_9_2","volume-title":"In\u00a0International Conference on Learning Representations\u00a0(ICLR'24)","author":"Tan W. H.","unstructured":"W. H. Tan, W. T. Zhang, S. Q. Liu, Z. Wang, and D. Zhao. 2024. True knowledge comes from practice: aligning LLMs with embodied environments via reinforcement learning. In\u00a0International Conference on Learning Representations\u00a0(ICLR'24). Vienna, Austria."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"B. Xiao B. Kantarci and J. W. Kang. 2025. Efficient prompting for LLM-based generative internet of things.\u00a0IEEE Internet of Things Journal\u00a012 1 (2025) 778\u2013791.","DOI":"10.1109\/JIOT.2024.3470210"},{"key":"e_1_3_3_1_11_2","unstructured":"H. W. Chung L. Hou S. Longpre B. Zoph E. Chi J. Dean et al. 2024. Scaling instruction-finetuned language models.\u00a0Journal of Machine Learning Research\u00a025 70 (2024) 1\u201353."},{"key":"e_1_3_3_1_12_2","volume-title":"In\u00a0Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics\u00a0(ACL'24)","author":"Ren M. J.","unstructured":"M. J. Ren, B. X. Cao, H. Y. Lin, and Y. Zhang. 2024. Learning or self-aligning? Rethinking instruction fine-tuning. In\u00a0Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics\u00a0(ACL'24). Amherst, MA, USA."},{"key":"e_1_3_3_1_13_2","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In\u00a0International Conference on Learning Representations\u00a0(ICLR'22)","author":"Edward H.","unstructured":"H. Edward, J. Chen, and L. Wang. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In\u00a0International Conference on Learning Representations\u00a0(ICLR'22)."},{"key":"e_1_3_3_1_14_2","unstructured":"A. Zeng B. Xu W. Zhang B. Wang C. Li and Team GLM. 2024. ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools.\u00a0arXiv preprint arXiv:2403.12345\u00a0(2024). Retrieved from\u00a0https:\/\/arxiv.org\/abs\/2403.12345."}],"event":{"name":"CSAI 2025: 2025 The 9th International Conference on Computer Science and Artificial Intelligence","location":"Beijing China","acronym":"CSAI 2025"},"container-title":["Proceedings of the 2025 9th International Conference on Computer Science and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3788149.3788184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:38:53Z","timestamp":1773988733000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788149.3788184"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,12]]},"references-count":14,"alternative-id":["10.1145\/3788149.3788184","10.1145\/3788149"],"URL":"https:\/\/doi.org\/10.1145\/3788149.3788184","relation":{},"subject":[],"published":{"date-parts":[[2025,12,12]]},"assertion":[{"value":"2026-03-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}