{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T02:10:03Z","timestamp":1750299003673,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,24]]},"DOI":"10.1145\/3708359.3712119","type":"proceedings-article","created":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T12:50:34Z","timestamp":1742388634000},"page":"70-88","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Framework for Efficient Development and Debugging of Role-Playing Agents with Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7021-3744","authenticated-orcid":false,"given":"Hirohane","family":"Takagi","sequence":"first","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan and Preferred Networks Inc., Tokyo, Japan,"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1459-5845","authenticated-orcid":false,"given":"Shoji","family":"Moriya","sequence":"additional","affiliation":[{"name":"Tohoku University, Sendai, Japan and Preferred Networks Inc., Tokyo, Japan,"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2103-9539","authenticated-orcid":false,"given":"Takuma","family":"Sato","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology, Nara, Japan and Preferred Networks Inc., Tokyo, Japan,"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2888-0014","authenticated-orcid":false,"given":"Manabu","family":"Nagao","sequence":"additional","affiliation":[{"name":"Preferred Networks Inc., Tokyo, Japan,"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6054-8471","authenticated-orcid":false,"given":"Keita","family":"Higuchi","sequence":"additional","affiliation":[{"name":"Preferred Networks Inc., Tokyo, Japan,"}]}],"member":"320","published-online":{"date-parts":[[2025,3,24]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642858"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3635636.3656204"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642016"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"crossref","unstructured":"Luca Beurer-Kellner Marc Fischer and Martin Vechev. 2023. Prompting is programming: A query language for large language models. Proc. ACM Program. Lang. 7 PLDI (June 2023) 1946\u20131969.","DOI":"10.1145\/3591300"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-demo.2"},{"key":"e_1_3_3_3_7_2","unstructured":"Banghao Chen Zhaofeng Zhang Nicolas Langren\u00e9 and Shengxin Zhu. 2024. Unleashing the potential of prompt engineering in Large Language Models: a comprehensive review. arxiv:https:\/\/arXiv.org\/abs\/2310.14735\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2310.14735"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/3"},{"key":"e_1_3_3_3_9_2","unstructured":"Jiangjie Chen Xintao Wang Rui Xu Siyu Yuan Yikai Zhang Wei Shi Jian Xie Shuang Li Ruihan Yang Tinghui Zhu Aili Chen Nianqi Li Lida Chen Caiyu Hu Siye Wu Scott Ren Ziquan Fu and Yanghua Xiao. 2024. From Persona to Personalization: A Survey on Role-Playing Language Agents. arxiv:https:\/\/arXiv.org\/abs\/2404.18231\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2404.18231"},{"key":"e_1_3_3_3_10_2","unstructured":"Yida Chen Aoyu Wu Trevor DePodesta Catherine Yeh Kenneth Li Nicholas\u00a0Castillo Marin Oam Patel Jan Riecke Shivam Raval Olivia Seow Martin Wattenberg and Fernanda Vi\u00e9gas. 2024. Designing a Dashboard for Transparency and Control of Conversational AI. arxiv:https:\/\/arXiv.org\/abs\/2406.07882\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2406.07882"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.870"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"crossref","unstructured":"Kenneth\u00a0Mark Colby Sylvia Weber and Franklin\u00a0Dennis Hilf. 1971. Artificial paranoia. Artificial intelligence 2 1 (1971) 1\u201325.","DOI":"10.1016\/0004-3702(71)90002-6"},{"key":"e_1_3_3_3_13_2","unstructured":"Sirui Hong Mingchen Zhuge Jonathan Chen Xiawu Zheng Yuheng Cheng Ceyao Zhang Jinlin Wang Zili Wang Steven Ka\u00a0Shing Yau Zijuan Lin Liyang Zhou Chenyu Ran Lingfeng Xiao Chenglin Wu and J\u00fcrgen Schmidhuber. 2023. MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework. arxiv:https:\/\/arXiv.org\/abs\/2308.00352\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2308.00352"},{"key":"e_1_3_3_3_14_2","unstructured":"Wenyue Hua Lizhou Fan Lingyao Li Kai Mei Jianchao Ji Yingqiang Ge Libby Hemphill and Yongfeng Zhang. 2024. War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars. arxiv:https:\/\/arXiv.org\/abs\/2311.17227\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2311.17227"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642349"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29802"},{"key":"e_1_3_3_3_17_2","unstructured":"Cheng Li Ziang Leng Chenxi Yan Junyi Shen Hao Wang Weishi MI Yaying Fei Xiaoyang Feng Song Yan HaoSheng Wang Linkang Zhan Yaokai Jia Pingyu Wu and Haozhen Sun. 2023. ChatHaruhi: Reviving Anime Character in Reality via Large Language Model. arxiv:https:\/\/arXiv.org\/abs\/2308.09597\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2308.09597"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.233"},{"key":"e_1_3_3_3_19_2","unstructured":"June\u00a0M. Liu Donghao Li He Cao Tianhe Ren Zeyi Liao and Jiamin Wu. 2023. ChatCounselor: A Large Language Models for Mental Health Support. arxiv:https:\/\/arXiv.org\/abs\/2309.15461\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2309.15461"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"crossref","unstructured":"Pengfei Liu Weizhe Yuan Jinlan Fu Zhengbao Jiang Hiroaki Hayashi and Graham Neubig. 2023. Pre-train prompt and predict: A systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55 9 (Sept. 2023) 1\u201335.","DOI":"10.1145\/3560815"},{"key":"e_1_3_3_3_21_2","unstructured":"Xun Liu and Zhengwei Ni. 2024. Prompt Framework for Role-playing: Generation and Evaluation. arxiv:https:\/\/arXiv.org\/abs\/2406.00627\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2406.00627"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.5555\/2821575"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"crossref","unstructured":"Julia Othlinghaus-Wulhorst and H\u00a0Ulrich Hoppe. 2020. A technical and conceptual framework for serious role-playing games in the area of social skill training. Front. Comput. Sci. 2 (July 2020) 523355.","DOI":"10.3389\/fcomp.2020.00028"},{"key":"e_1_3_3_3_24_2","series-title":"(NIPS \u201922)","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Ouyang Long","year":"2024","unstructured":"Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll\u00a0L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2024. Training language models to follow instructions with human feedback. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS \u201922). Curran Associates Inc., Red Hook, NY, USA, Article 2011, 15\u00a0pages."},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.810"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.772"},{"key":"e_1_3_3_3_28_2","unstructured":"Pranab Sahoo Ayush\u00a0Kumar Singh Sriparna Saha Vinija Jain Samrat Mondal and Aman Chadha. 2024. A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications. arxiv:https:\/\/arXiv.org\/abs\/2402.07927\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2402.07927"},{"key":"e_1_3_3_3_29_2","unstructured":"Victor Sanh Albert Webson Colin Raffel Stephen\u00a0H. Bach Lintang Sutawika Zaid Alyafeai Antoine Chaffin Arnaud Stiegler Teven\u00a0Le Scao Arun Raja Manan Dey M\u00a0Saiful Bari Canwen Xu Urmish Thakker Shanya\u00a0Sharma Sharma Eliza Szczechla Taewoon Kim Gunjan Chhablani Nihal Nayak Debajyoti Datta Jonathan Chang Mike Tian-Jian Jiang Han Wang Matteo Manica Sheng Shen Zheng\u00a0Xin Yong Harshit Pandey Rachel Bawden Thomas Wang Trishala Neeraj Jos Rozen Abheesht Sharma Andrea Santilli Thibault Fevry Jason\u00a0Alan Fries Ryan Teehan Tali Bers Stella Biderman Leo Gao Thomas Wolf and Alexander\u00a0M. Rush. 2022. Multitask Prompted Training Enables Zero-Shot Task Generalization. arxiv:https:\/\/arXiv.org\/abs\/2110.08207\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2110.08207"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.21606\/iasdr.2023.448"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.814"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","unstructured":"Hendrik Strobelt Albert Webson Victor Sanh Benjamin Hoover Johanna Beyer Hanspeter Pfister and Alexander\u00a0M. Rush. 2023. Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models. IEEE Transactions on Visualization and Computer Graphics 29 1 (2023) 1146\u20131156. 10.1109\/TVCG.2022.3209479","DOI":"10.1109\/TVCG.2022.3209479"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642754"},{"key":"e_1_3_3_3_34_2","unstructured":"Hovhannes Tamoyan Hendrik Schuff and Iryna Gurevych. 2024. LLM Roleplay: Simulating Human-Chatbot Interaction. arxiv:https:\/\/arXiv.org\/abs\/2407.03974\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2407.03974"},{"key":"e_1_3_3_3_35_2","unstructured":"Xiangru Tang Anni Zou Zhuosheng Zhang Ziming Li Yilun Zhao Xingyao Zhang Arman Cohan and Mark Gerstein. 2024. MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning. arxiv:https:\/\/arXiv.org\/abs\/2311.10537\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2311.10537"},{"key":"e_1_3_3_3_36_2","unstructured":"Yu-Min Tseng Yu-Chao Huang Teng-Yun Hsiao Wei-Lin Chen Chao-Wei Huang Yu Meng and Yun-Nung Chen. 2024. Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization. arxiv:https:\/\/arXiv.org\/abs\/2406.01171\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2406.01171"},{"key":"e_1_3_3_3_37_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:https:\/\/arXiv.org\/abs\/2305.16291\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2305.16291"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"crossref","unstructured":"Lei Wang Chen Ma Xueyang Feng Zeyu Zhang Hao Yang Jingsen Zhang Zhiyuan Chen Jiakai Tang Xu Chen Yankai Lin Wayne\u00a0Xin Zhao Zhewei Wei and Jirong Wen. 2024. A survey on large language model based autonomous agents. Front. Comput. Sci. 18 6 (Dec. 2024) 1\u201326.","DOI":"10.1007\/s11704-024-40231-1"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.878"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.271"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642803"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"crossref","unstructured":"Joseph Weizenbaum. 1966. ELIZA\u2014a computer program for the study of natural language communication between man and machine. Commun. ACM 9 1 (1966) 36\u201345.","DOI":"10.1145\/365153.365168"},{"key":"e_1_3_3_3_43_2","unstructured":"Cheng-Kuang Wu Wei-Lin Chen and Hsin-Hsi Chen. 2023. Large Language Models Perform Diagnostic Reasoning. arxiv:https:\/\/arXiv.org\/abs\/2307.08922\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2307.08922"},{"key":"e_1_3_3_3_44_2","unstructured":"Qingyun Wu Gagan Bansal Jieyu Zhang Yiran Wu Beibin Li Erkang Zhu Li Jiang Xiaoyun Zhang Shaokun Zhang Jiale Liu Ahmed\u00a0Hassan Awadallah Ryen\u00a0W White Doug Burger and Chi Wang. 2023. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. arxiv:https:\/\/arXiv.org\/abs\/2308.08155\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2308.08155"},{"key":"e_1_3_3_3_45_2","unstructured":"Zhiheng Xi Wenxiang Chen Xin Guo Wei He Yiwen Ding Boyang Hong Ming Zhang Junzhe Wang Senjie Jin Enyu Zhou Rui Zheng Xiaoran Fan Xiao Wang Limao Xiong Yuhao Zhou Weiran Wang Changhao Jiang Yicheng Zou Xiangyang Liu Zhangyue Yin Shihan Dou Rongxiang Weng Wensen Cheng Qi Zhang Wenjuan Qin Yongyan Zheng Xipeng Qiu Xuanjing Huang and Tao Gui. 2023. The Rise and Potential of Large Language Model Based Agents: A Survey. arxiv:https:\/\/arXiv.org\/abs\/2309.07864\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2309.07864"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581388"},{"key":"e_1_3_3_3_47_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zeng Zhiyuan","year":"2024","unstructured":"Zhiyuan Zeng, Jiatong Yu, Tianyu Gao, Yu Meng, Tanya Goyal, and Danqi Chen. 2024. Evaluating Large Language Models at Evaluating Instruction Following. In International Conference on Learning Representations (ICLR)."}],"event":{"name":"IUI '25: 30th International Conference on Intelligent User Interfaces","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"location":"Cagliari Italy","acronym":"IUI '25"},"container-title":["Proceedings of the 30th International Conference on Intelligent User Interfaces"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708359.3712119","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3708359.3712119","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:57:06Z","timestamp":1750298226000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708359.3712119"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,24]]},"references-count":46,"alternative-id":["10.1145\/3708359.3712119","10.1145\/3708359"],"URL":"https:\/\/doi.org\/10.1145\/3708359.3712119","relation":{},"subject":[],"published":{"date-parts":[[2025,3,24]]},"assertion":[{"value":"2025-03-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}