{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:13:52Z","timestamp":1764785632010,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T00:00:00Z","timestamp":1744675200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,15]]},"DOI":"10.1145\/3723498.3723702","type":"proceedings-article","created":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T12:04:41Z","timestamp":1746792281000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Evaluating Large Language Models through Communication Games: An Agent-Based Framework Using Werewolf in Unity"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6050-4363","authenticated-orcid":false,"given":"Christian","family":"Poglitsch","sequence":"first","affiliation":[{"name":"University of Technology Graz, Graz, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2486-2826","authenticated-orcid":false,"given":"Fabian","family":"Szak\u00e1cs","sequence":"additional","affiliation":[{"name":"University of Technology Graz, Graz, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0336-0592","authenticated-orcid":false,"given":"Johanna","family":"Pirker","sequence":"additional","affiliation":[{"name":"University of Technology Graz, Graz, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,5,9]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Suma Bailis Jane Friedhoff and Feiyang Chen. 2024. Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction. arxiv:https:\/\/arXiv.org\/abs\/2407.13943\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2407.13943"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","unstructured":"Bahar Bateni and Jim Whitehead. 2024. Language-Driven Play: Large Language Models as Game-Playing Agents in Slay the Spire. 1\u201310. 10.1145\/3649921.3650013","DOI":"10.1145\/3649921.3650013"},{"key":"e_1_3_3_2_4_2","unstructured":"Prajjwal Bhargava and Vincent Ng. 2022. Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey. arxiv:https:\/\/arXiv.org\/abs\/2201.12438\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2201.12438"},{"key":"e_1_3_3_2_5_2","unstructured":"Marc Cavazza Fred Charles and Steven Mead. 2002. Sex Lies and Video Games: an Interactive Storytelling Prototype. (10 2002)."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Banghao Chen Zhaofeng Zhang Nicolas Langren\u00e9 and Shengxin Zhu. 2024. Unleashing the potential of prompt engineering: a comprehensive review. arxiv:https:\/\/arXiv.org\/abs\/2310.14735\u00a0[cs.CL]","DOI":"10.1016\/j.patter.2025.101260"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.699"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Thilo Hagendorff and Sarah Fabi. 2023. Human-Like Intuitive Behavior and Reasoning Biases Emerged in Language Models \u2013 and Disappeared in GPT-4.","DOI":"10.1038\/s43588-023-00527-x"},{"key":"e_1_3_3_2_9_2","unstructured":"Jie Huang and Kevin Chen-Chuan Chang. 2023. Towards Reasoning in Large Language Models: A Survey. arxiv:https:\/\/arXiv.org\/abs\/2212.10403\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2212.10403"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Natalie Jones Helen Ross Tim Lynam Pascal Perez and Anne Leitch. 2011. Mental Models: An Interdisciplinary Synthesis of Theory and Methods. Ecology and Society 16 (03 2011). 10.5751\/ES-03802-160146","DOI":"10.5751\/ES-03802-160146"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Anne Kearney and Stephen Kaplan. 1997. Toward a Methodology for the Measurement of Knowledge Structures of Ordinary PeopleThe Conceptual Content Cognitive Map (3CM). Environment and Behavior - ENVIRON BEHAV 29 (09 1997) 579\u2013617. 10.1177\/0013916597295001","DOI":"10.1177\/0013916597295001"},{"key":"e_1_3_3_2_12_2","unstructured":"Mosh Levy Alon Jacoby and Yoav Goldberg. 2024. Same Task More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2402.14848\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2402.14848"},{"key":"e_1_3_3_2_13_2","unstructured":"Jijia Liu Chao Yu Jiaxuan Gao Yuqing Xie Qingmin Liao Yi Wu and Yu Wang. 2024. LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination. arxiv:https:\/\/arXiv.org\/abs\/2312.15224\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2312.15224"},{"key":"e_1_3_3_2_14_2","unstructured":"Zabir\u00a0Al Nazi and Wei Peng. 2023. Large language models in healthcare and medical domain: A review. arxiv:https:\/\/arXiv.org\/abs\/2401.06775\u00a0[cs.CL]"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Don Nutbeam. 2023. Artificial intelligence and health literacy\u2014proceed with caution. Health Literacy and Communication Open 1 1 (2023) 2263355. 10.1080\/28355245.2023.2263355","DOI":"10.1080\/28355245.2023.2263355"},{"key":"e_1_3_3_2_16_2","unstructured":"Joon\u00a0Sung Park Joseph\u00a0C. O\u2019Brien Carrie\u00a0J. Cai Meredith\u00a0Ringel Morris Percy Liang and Michael\u00a0S. Bernstein. 2023. Generative Agents: Interactive Simulacra of Human Behavior. arxiv:https:\/\/arXiv.org\/abs\/2304.03442\u00a0[cs.HC]"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CoG60054.2024.10645560"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Christian Poglitsch Saeed Safikhani Erin List and Johanna Pirker. 2024. XR technologies to enhance the emotional skills of people with autism spectrum disorder: A systematic review. Computers & Graphics 121 (2024) 103942. 10.1016\/j.cag.2024.103942","DOI":"10.1016\/j.cag.2024.103942"},{"key":"e_1_3_3_2_19_2","unstructured":"Dan Qiao Chenfei Wu Yaobo Liang Juntao Li and Nan Duan. 2023. GameEval: Evaluating LLMs on Conversational Games. arxiv:https:\/\/arXiv.org\/abs\/2308.10032\u00a0[cs.CL]"},{"key":"e_1_3_3_2_20_2","unstructured":"Samsung. 2024. Galaxy AI. https:\/\/www.samsung.com\/us\/galaxy-ai\/#faq. Online; accessed May 20 2024."},{"key":"e_1_3_3_2_21_2","unstructured":"Karthik Sreedhar and Lydia Chilton. 2024. Simulating Human Strategic Behavior: Comparing Single and Multi-agent LLMs. arxiv:https:\/\/arXiv.org\/abs\/2402.08189\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2402.08189"},{"key":"e_1_3_3_2_22_2","volume-title":"Psychology of Reasoning: Structure and Content","author":"Wason Peter\u00a0Cathcart","year":"1972","unstructured":"Peter\u00a0Cathcart Wason and Philip\u00a0Nicholas Johnson-Laird. 1972. Psychology of Reasoning: Structure and Content. Harvard University Press, Cambridge, MA, USA."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Sarah Wiseman and Kevin Lewis. 2019. What Data do Players Rely on in Social Deduction Games?781\u2013787. 10.1145\/3341215.3356272","DOI":"10.1145\/3341215.3356272"},{"key":"e_1_3_3_2_24_2","unstructured":"Yuzhuang Xu Shuo Wang Peng Li Fuwen Luo Xiaolong Wang Weidong Liu and Yang Liu. 2024. Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf. arxiv:https:\/\/arXiv.org\/abs\/2309.04658\u00a0[cs.CL]"},{"key":"e_1_3_3_2_25_2","unstructured":"Zhongshen Zeng Yinhong Liu Yingjia Wan Jingyao Li Pengguang Chen Jianbo Dai Yuxuan Yao Rongwu Xu Zehan Qi Wanru Zhao Linling Shen Jianqiao Lu Haochen Tan Yukang Chen Hao Zhang Zhan Shi Bailin Wang Zhijiang Guo and Jiaya Jia. 2024. MR-BEN: A Comprehensive Meta-Reasoning Benchmark for Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2406.13975\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2406.13975"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","unstructured":"C. Zhang K. Yang S. Hu Z. Wang G. Li Y. Sun C. Zhang Z. Zhang A. Liu S. Zhu X. Chang J. Zhang F. Yin Y. Liang and Y. Yang. 2024. Proagent: building proactive cooperative agents with large language models. Proceedings of the AAAI Conference on Artificial Intelligence 38 (2024) 17591\u201317599. Issue 16. 10.1609\/aaai.v38i16.29710","DOI":"10.1609\/aaai.v38i16.29710"},{"key":"e_1_3_3_2_27_2","unstructured":"Zirui Zhao Wee\u00a0Sun Lee and David Hsu. 2023. Large Language Models as Commonsense Knowledge for Large-Scale Task Planning. arxiv:https:\/\/arXiv.org\/abs\/2305.14078\u00a0[cs.RO] https:\/\/arxiv.org\/abs\/2305.14078"}],"event":{"name":"FDG '25: International Conference on the Foundations of Digital Games","acronym":"FDG '25","location":"Vienna & Graz Austria"},"container-title":["Proceedings of the 20th International Conference on the Foundations of Digital Games"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3723498.3723702","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3723498.3723702","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:56:45Z","timestamp":1750298205000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3723498.3723702"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,15]]},"references-count":26,"alternative-id":["10.1145\/3723498.3723702","10.1145\/3723498"],"URL":"https:\/\/doi.org\/10.1145\/3723498.3723702","relation":{},"subject":[],"published":{"date-parts":[[2025,4,15]]},"assertion":[{"value":"2025-05-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}