{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:00:36Z","timestamp":1765339236133,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","funder":[{"name":"Tencent Rhino-Bird Focused Research Program, National Natural Science Foundation of China","award":["62406267"],"award-info":[{"award-number":["62406267"]}]},{"name":"The Guangzhou Municipal Science and Technology Project","award":["2025A04J4070"],"award-info":[{"award-number":["2025A04J4070"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755752","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"5824-5833","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6227-1987","authenticated-orcid":false,"given":"Zheng","family":"Zhang","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3392-8778","authenticated-orcid":false,"given":"Nuoqian","family":"Xiao","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3717-9482","authenticated-orcid":false,"given":"Qi","family":"Chai","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1754-1837","authenticated-orcid":false,"given":"Deheng","family":"Ye","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3086-3128","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2009.07.005"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.85"},{"volume-title":"Cambridge","author":"Bratman Michael","key":"e_1_3_2_1_3_1","unstructured":"Michael Bratman. 1987. Intention, Plans, and Practical Reason. Cambridge, MA: Harvard University Press, Cambridge."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICHMS49158.2020.9209472"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3518"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689092.3689404"},{"key":"e_1_3_2_1_7_1","volume-title":"OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia. arXiv preprint arXiv:2501.13306","author":"Geng Xuelong","year":"2025","unstructured":"Xuelong Geng, Kun Wei, Qijie Shao, Shuiyun Liu, Zhennan Lin, Zhixian Zhao, Guojian Li, Wenjie Tian, Peikun Chen, Yangze Li, Pengcheng Guo, Mingchen Shao, Shuiyuan Wang, Yuang Cao, Chengyou Wang, Tianyi Xu, Yuhang Dai, Xinfa Zhu, Yue Li, Li Zhang, and Lei Xie. 2025. OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia. arXiv preprint arXiv:2501.13306 (2025)."},{"key":"e_1_3_2_1_8_1","volume-title":"Griffiths","author":"Grant Erin","year":"2017","unstructured":"Erin Grant, Aida Nematzadeh, and Thomas L. Griffiths. 2017. How Can Memory-Augmented Neural Networks Pass a False-Belief Task? Cognitive Science (2017). https:\/\/api.semanticscholar.org\/CorpusID:7340345"},{"key":"e_1_3_2_1_9_1","volume-title":"Cyrus Nikolaidis, Damien Allonsius, Daniel Song, Danielle Pintz, Danny Livshits, Danny Wyatt, David Esiobu, Dhruv Choudhary, Dhruv Mahajan, et al.","author":"Grattafiori Aaron","year":"2024","unstructured":"Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao, Aston Zhang, Aurelien Rodriguez, Austen Gregerson, Ava Spataru, Baptiste Roziere, Bethany Biron, Binh Tang, Bobbie Chern, Charlotte Caucheteux, Chaya Nayak, Chloe Bi, Chris Marra, Chris McConnell, Christian Keller, Christophe Touret, Chunyang Wu, Corinne Wong, Cristian Canton Ferrer, Cyrus Nikolaidis, Damien Allonsius, Daniel Song, Danielle Pintz, Danny Livshits, Danny Wyatt, David Esiobu, Dhruv Choudhary, Dhruv Mahajan, et al., 2024. The Llama 3 Herd of Models. arXiv:2407.21783 [cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Yuya Hirata Michimasa Inaba Kenichi Takahashi Fujio Toriumi Hirotaka Osawa Daisuke Katagami and Kousuke Shinoda. 2016. Werewolf Game Modeling Using Action Probabilities Based on Play Log Analysis. In Computers and Games. https:\/\/api.semanticscholar.org\/CorpusID:37838481","DOI":"10.1007\/978-3-319-50935-8_10"},{"key":"e_1_3_2_1_12_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=1f82rnwCbl","author":"Jin Xuanfa","year":"2024","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. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=1f82rnwCbl"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.411"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.7"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2019.8673023"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01382"},{"key":"e_1_3_2_1_17_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=XXOMCwZ6by","author":"Li Zaijing","year":"2024","unstructured":"Zaijing Li, Yuquan Xie, Rui Shao, Gongwei Chen, Dongmei Jiang, and Liqiang Nie. 2024. Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=XXOMCwZ6by"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721121"},{"key":"e_1_3_2_1_19_1","volume-title":"NeurIPS 2023 Foundation Models for Decision Making Workshop. https:\/\/openreview.net\/forum?id=ltUrSryS0K","author":"Light Jonathan","year":"2023","unstructured":"Jonathan Light, Min Cai, Sheng Shen, and Ziniu Hu. 2023. From Text to Tactic: Evaluating LLMs Playing the Game of Avalon. In NeurIPS 2023 Foundation Models for Decision Making Workshop. https:\/\/openreview.net\/forum?id=ltUrSryS0K"},{"key":"e_1_3_2_1_20_1","unstructured":"Weiyu Ma Qirui Mi Yongcheng Zeng Xue Yan Runji Lin Yuqiao Wu Jun Wang and Haifeng Zhang. 2024. Large Language Models Play StarCraft II:Benchmarks and A Chain of Summarization Approach. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=kEPpD7yE\u2122"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7850031"},{"key":"e_1_3_2_1_22_1","unstructured":"OpenAI: Aaron Hurst Adam Lerer Adam P. Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford Aleksander M?dry Alex Baker-Whitcomb Alex Beutel Alex Borzunov Alex Carney Alex Chow Alex Kirillov Alex Nichol Alex Paino Alex Renzin Alex Tachard Passos Alexander Kirillov Alexi Christakis Alexis Conneau Ali Kamali Allan Jabri Allison Moyer Allison Tam Amadou Crookes Amin Tootoochian Amin Tootoonchian Ananya Kumar Andrea Vallone Andrej Karpathy Andrew Braunstein Andrew Cann Andrew Codispoti Andrew Galu Andrew Kondrich Andrew Tulloch Andrey Mishchenko Angela Baek Angela Jiang Antoine Pelisse Antonia Woodford Anuj Gosalia Arka Dhar et al. 2024. GPT-4o System Card. arXiv:2410.21276 [cs.CL] https:\/\/arxiv.org\/abs\/2410.21276"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01543"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","unstructured":"Liang Qiu Yizhou Zhao Yuan Liang Pan Lu Weiyan Shi Zhou Yu and Song-Chun Zhu. 2022. Towards Socially Intelligent Agents with Mental State Transition and Human Value. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue Oliver Lemon Dilek Hakkani-Tur Junyi Jessy Li Arash Ashrafzadeh Daniel Hern\u00e1ndez Garcia Malihe Alikhani David Vandyke and Ond\u0159ej Du\u0161ek (Eds.). Association for Computational Linguistics Edinburgh UK 146-158. doi:10.18653\/v1\/2022.sigdial-1.16","DOI":"10.18653\/v1\/2022.sigdial-1.16"},{"key":"e_1_3_2_1_25_1","unstructured":"Qwen: An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei Huan Lin Jian Yang Jianhong Tu Jianwei Zhang Jianxin Yang Jiaxi Yang Jingren Zhou Junyang Lin Kai Dang Keming Lu Keqin Bao Kexin Yang Le Yu Mei Li Mingfeng Xue Pei Zhang Qin Zhu Rui Men Runji Lin Tianhao Li Tianyi Tang Tingyu Xia Xingzhang Ren Xuancheng Ren Yang Fan Yang Su Yichang Zhang Yu Wan Yuqiong Liu Zeyu Cui Zhenru Zhang and Zihan Qiu. 2025. Qwen2.5 Technical Report. arXiv:2412.15115 [cs.CL] https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"4227","author":"Rabinowitz Neil","year":"2018","unstructured":"Neil Rabinowitz, Frank Perbet, Francis Song, Chiyuan Zhang, S. M. Ali Eslami, and Matthew Botvinick. 2018. Machine Theory of Mind. In Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 80), Jennifer Dy and Andreas Krause (Eds.). PMLR, 4218-4227. https:\/\/proceedings.mlr.press\/v80\/rabinowitz18a.html"},{"key":"e_1_3_2_1_27_1","volume-title":"Tenenbaum","author":"Serrino Jack","year":"2019","unstructured":"Jack Serrino, Max Kleiman-Weiner, David C. Parkes, and Joshua B. Tenenbaum. 2019. Finding friend and foe in multi-agent games. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_2_1_28_1","unstructured":"Xiao Shao Weifu Jiang Fei Zuo and Mengqing Liu. 2024. SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models. arXiv:2401.17749 [cs.AI] https:\/\/arxiv.org\/abs\/2401.17749"},{"key":"e_1_3_2_1_29_1","unstructured":"Zijing Shi Meng Fang Shunfeng Zheng Shilong Deng Ling Chen and Yali Du. 2023. Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game. arXiv:2312.17515 [cs.CL] https:\/\/arxiv.org\/abs\/2312.17515"},{"key":"e_1_3_2_1_30_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_1_31_1","volume-title":"Voyager: An Open-Ended Embodied Agent with Large Language Models. Transactions on Machine Learning Research","author":"Wang Guanzhi","year":"2024","unstructured":"Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2024. Voyager: An Open-Ended Embodied Agent with Large Language Models. Transactions on Machine Learning Research (2024). https:\/\/openreview.net\/forum?id=ehfRiF0R3a"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445645"},{"key":"e_1_3_2_1_33_1","unstructured":"Shenzhi Wang Chang Liu Zilong Zheng Siyuan Qi Shuo Chen Qisen Yang Andrew Zhao Chaofei Wang Shiji Song and Gao Huang. 2023. Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation. arXiv:2310.01320 [cs.AI] https:\/\/arxiv.org\/abs\/2310.01320"},{"key":"e_1_3_2_1_34_1","first-page":"28","volume-title":"Application of Deep Reinforcement Learning in Werewolf Game Agents. 2018 Conference on Technologies and Applications of Artificial Intelligence (TAAI) (2018","author":"Wang Tianhe","year":"2018","unstructured":"Tianhe Wang and Tomoyuki Kaneko. 2018. Application of Deep Reinforcement Learning in Werewolf Game Agents. 2018 Conference on Technologies and Applications of Artificial Intelligence (TAAI) (2018), 28-33. https:\/\/api.semanticscholar.org\/CorpusID:57191228"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.490"},{"key":"e_1_3_2_1_36_1","unstructured":"Shuang Wu Liwen Zhu Tao Yang Shiwei Xu Qiang Fu Yang Wei and Haobo Fu. 2024b. Enhance Reasoning for Large Language Models in the Game Werewolf. arXiv:2402.02330 [cs.AI] https:\/\/arxiv.org\/abs\/2402.02330"},{"key":"e_1_3_2_1_37_1","volume-title":"Exploring large language models for communication games: An empirical study on werewolf. arXiv preprint arXiv:2309.04658","author":"Xu Yuzhuang","year":"2023","unstructured":"Yuzhuang Xu, Shuo Wang, Peng Li, Fuwen Luo, Xiaolong Wang, Weidong Liu, and Yang Liu. 2023. Exploring large language models for communication games: An empirical study on werewolf. arXiv preprint arXiv:2309.04658 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3694355"},{"key":"e_1_3_2_1_39_1","volume-title":"ReAct: Synergizing Reasoning and Acting in Language Models. In International Conference on Learning Representations (ICLR).","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888525"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.624"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T03:59:04Z","timestamp":1765339144000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755752"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":41,"alternative-id":["10.1145\/3746027.3755752","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755752","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}