{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T04:07:57Z","timestamp":1779422877022,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,26]]},"DOI":"10.1145\/3786335.3813173","type":"proceedings-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:16:22Z","timestamp":1779419782000},"page":"727-737","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Does Safety Molt? Evaluating LLM Safety in Multi-Agent Social Environments"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6985-9575","authenticated-orcid":false,"given":"Aman","family":"Priyanshu","sequence":"first","affiliation":[{"name":"Cisco Systems Inc., Foundation-AI, San Francisco, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8746-1932","authenticated-orcid":false,"given":"Supriti","family":"Vijay","sequence":"additional","affiliation":[{"name":"Cisco Systems Inc., Foundation-AI, San Francisco, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9697-7864","authenticated-orcid":false,"given":"Esha","family":"Pahwa","sequence":"additional","affiliation":[{"name":"Corvic AI, Mountain View, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,26]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Alessandro Acquisti Leslie\u00a0K John and George Loewenstein. 2013. What is privacy worth? The Journal of Legal Studies 42 2 (2013) 249\u2013274.","DOI":"10.1086\/671754"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Cem Anil Esin Durmus Nina Panickssery Mrinank Sharma Joe Benton Sandipan Kundu Joshua Batson Meg Tong Jesse Mu Daniel Ford et\u00a0al. 2024. Many-shot jailbreaking. Advances in Neural Information Processing Systems 37 (2024) 129696\u2013129742.","DOI":"10.52202\/079017-4121"},{"key":"e_1_3_3_2_4_2","first-page":"295","volume-title":"Organizational influence processes","author":"Asch Solomon\u00a0E","year":"2016","unstructured":"Solomon\u00a0E Asch. 2016. Effects of group pressure upon the modification and distortion of judgments. In Organizational influence processes. Routledge, 295\u2013303."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Ariel\u00a0Flint Ashery Luca\u00a0Maria Aiello and Andrea Baronchelli. 2025. Emergent social conventions and collective bias in LLM populations. Science Advances 11 20 (May 2025). 10.1126\/sciadv.adu9368","DOI":"10.1126\/sciadv.adu9368"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3534642"},{"key":"e_1_3_3_2_7_2","unstructured":"Weize Chen Yusheng Su Jingwei Zuo Cheng Yang Chenfei Yuan Chi-Min Chan Heyang Yu Yaxi Lu Yi-Hsin Hung Chen Qian Yujia Qin Xin Cong Ruobing Xie Zhiyuan Liu Maosong Sun and Jie Zhou. 2023. AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors. arxiv:https:\/\/arXiv.org\/abs\/2308.10848\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2308.10848"},{"key":"e_1_3_3_2_8_2","first-page":"141","volume-title":"CCL 2024\u201323rd Chinese Natl Conf Comput Linguist","author":"Chen X","year":"2024","unstructured":"X Chen, A Zeng, et\u00a0al. 2024. A survey on large language model based autonomous agents. In CCL 2024\u201323rd Chinese Natl Conf Comput Linguist, Vol.\u00a02. 141\u2013150."},{"key":"e_1_3_3_2_9_2","unstructured":"Dylan Clendenin. 2009. faker: A Python library for generating fake user data. https:\/\/github.com\/deepthawtz\/faker. GitHub repository. MIT License. Accessed 2026."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605764.3623985"},{"key":"e_1_3_3_2_11_2","unstructured":"Taicheng Guo Xiuying Chen Yaqi Wang Ruidi Chang Shichao Pei Nitesh\u00a0V Chawla Olaf Wiest and Xiangliang Zhang. 2024. Large language model based multi-agents: A survey of progress and challenges. arXiv 2024. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.01680 10 (2024)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"David Holtz. 2026. The Anatomy of the Moltbook Social Graph. arxiv:https:\/\/arXiv.org\/abs\/2602.10131\u00a0[cs.SI] https:\/\/arxiv.org\/abs\/2602.10131","DOI":"10.2139\/ssrn.6174639"},{"key":"e_1_3_3_2_13_2","unstructured":"Sirui Hong Mingchen Zhuge Jiaqi 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. 2024. 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_2_14_2","unstructured":"Yukun Jiang Yage Zhang Xinyue Shen Michael Backes and Yang Zhang. 2026. \"Humans welcome to observe\": A First Look at the Agent Social Network Moltbook. arxiv:https:\/\/arXiv.org\/abs\/2602.10127\u00a0[cs.SI] https:\/\/arxiv.org\/abs\/2602.10127"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Spyros Kokolakis. 2017. Privacy attitudes and privacy behaviour: A review of current research on the privacy paradox phenomenon. Computers & Security 64 (2017) 122\u2013134. 10.1016\/j.cose.2015.07.002","DOI":"10.1016\/j.cose.2015.07.002"},{"key":"e_1_3_3_2_16_2","unstructured":"Guohao Li Hasan Abed Al\u00a0Kader Hammoud Hani Itani Dmitrii Khizbullin and Bernard Ghanem. 2023. CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society. arxiv:https:\/\/arXiv.org\/abs\/2303.17760\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2303.17760"},{"key":"e_1_3_3_2_17_2","unstructured":"Lingyao Li Renkai Ma Chen Chen Zhicong Lu and Yongfeng Zhang. 2026. The Rise of AI Agent Communities: Large-Scale Analysis of Discourse and Interaction on Moltbook. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2602.12634 (2026)."},{"key":"e_1_3_3_2_18_2","unstructured":"Ming Li Xirui Li and Tianyi Zhou. 2026. Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2602.14299 (2026)."},{"key":"e_1_3_3_2_19_2","unstructured":"Xiao Liu Hao Yu Hanchen Zhang Yifan Xu Xuanyu Lei Hanyu Lai Yu Gu Hangliang Ding Kaiwen Men Kejuan Yang Shudan Zhang Xiang Deng Aohan Zeng Zhengxiao Du Chenhui Zhang Sheng Shen Tianjun Zhang Yu Su Huan Sun Minlie Huang Yuxiao Dong and Jie Tang. 2025. AgentBench: Evaluating LLMs as Agents. arxiv:https:\/\/arXiv.org\/abs\/2308.03688\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2308.03688"},{"key":"e_1_3_3_2_20_2","first-page":"1831","volume-title":"33rd USENIX Security Symposium (USENIX Security 24)","author":"Liu Yupei","year":"2024","unstructured":"Yupei Liu, Yuqi Jia, Runpeng Geng, Jinyuan Jia, and Neil\u00a0Zhenqiang Gong. 2024. Formalizing and benchmarking prompt injection attacks and defenses. In 33rd USENIX Security Symposium (USENIX Security 24). 1831\u20131847."},{"key":"e_1_3_3_2_21_2","unstructured":"Md\u00a0Motaleb\u00a0Hossen Manik and Ge Wang. 2026. OpenClaw Agents on Moltbook: Risky Instruction Sharing and Norm Enforcement in an Agent-Only Social Network. arxiv:https:\/\/arXiv.org\/abs\/2602.02625\u00a0[cs.SI] https:\/\/arxiv.org\/abs\/2602.02625"},{"key":"e_1_3_3_2_22_2","unstructured":"Giordano\u00a0De Marzo and David Garcia. 2026. Collective Behavior of AI Agents: the Case of Moltbook. arxiv:https:\/\/arXiv.org\/abs\/2602.09270\u00a0[physics.soc-ph] https:\/\/arxiv.org\/abs\/2602.09270"},{"key":"e_1_3_3_2_23_2","unstructured":"Mantas Mazeika Long Phan Xuwang Yin Andy Zou Zifan Wang Norman Mu Elham Sakhaee Nathaniel Li Steven Basart Bo Li et\u00a0al. 2024. Harmbench: A standardized evaluation framework for automated red teaming and robust refusal. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.04249 (2024)."},{"key":"e_1_3_3_2_24_2","unstructured":"Niloofar Mireshghallah and Tianshi Li. 2025. Position: Privacy Is Not Just Memorization! arxiv:https:\/\/arXiv.org\/abs\/2510.01645\u00a0[cs.CR] https:\/\/arxiv.org\/abs\/2510.01645"},{"key":"e_1_3_3_2_25_2","unstructured":"Niloofar Mireshghallah Neal Mangaokar Narine Kokhlikyan Arman Zharmagambetov Manzil Zaheer Saeed Mahloujifar and Kamalika Chaudhuri. 2025. Cimemories: A compositional benchmark for contextual integrity of persistent memory in llms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.14937 (2025)."},{"key":"e_1_3_3_2_26_2","unstructured":"Helen Nissenbaum. 2004. Privacy as contextual integrity. Wash. L. Rev. 79 (2004) 119."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_3_3_2_28_2","unstructured":"Joon\u00a0Sung Park Carolyn\u00a0Q. Zou Aaron Shaw Benjamin\u00a0Mako Hill Carrie Cai Meredith\u00a0Ringel Morris Robb Willer Percy Liang and Michael\u00a0S. Bernstein. 2024. Generative Agent Simulations of 1 000 People. arxiv:https:\/\/arXiv.org\/abs\/2411.10109\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2411.10109"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Ethan Perez Saffron Huang Francis Song Trevor Cai Roman Ring John Aslanides Amelia Glaese Nat McAleese and Geoffrey Irving. 2022. Red teaming language models with language models 2022. URL https:\/\/arxiv. org\/abs\/2202.03286 15 (2022).","DOI":"10.18653\/v1\/2022.emnlp-main.225"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Jinghua Piao Yuwei Yan Jun Zhang Nian Li Junbo Yan Xiaochong Lan Zhihong Lu Zhiheng Zheng Jing\u00a0Yi Wang Di Zhou Chen Gao Fengli Xu Fang Zhang Ke Rong Jun Su and Yong Li. 2025. AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society. arxiv:https:\/\/arXiv.org\/abs\/2502.08691\u00a0[cs.SI] https:\/\/arxiv.org\/abs\/2502.08691","DOI":"10.2139\/ssrn.5954414"},{"key":"e_1_3_3_2_31_2","unstructured":"H.\u00a0C.\u00a0W. Price H. AlMuhanna P.\u00a0M. Bassani M. Ho and T.\u00a0S. Evans. 2026. Let There Be Claws: An Early Social Network Analysis of AI Agents on Moltbook. arxiv:https:\/\/arXiv.org\/abs\/2602.20044\u00a0[physics.soc-ph] https:\/\/arxiv.org\/abs\/2602.20044"},{"key":"e_1_3_3_2_32_2","unstructured":"Aman Priyanshu and Supriti Vijay. 2024. FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench (Automated Multi-shot Jailbreaks). arxiv:https:\/\/arXiv.org\/abs\/2408.16163\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2408.16163"},{"key":"e_1_3_3_2_33_2","unstructured":"Aman Priyanshu Supriti Vijay Ayush Kumar Rakshit Naidu and Fatemehsadat Mireshghallah. 2023. Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization. arxiv:https:\/\/arXiv.org\/abs\/2305.15008\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2305.15008"},{"key":"e_1_3_3_2_34_2","unstructured":"Mark Russinovich Ahmed Salem and Ronen Eldan. 2025. Great Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack. arxiv:https:\/\/arXiv.org\/abs\/2404.01833\u00a0[cs.CR] https:\/\/arxiv.org\/abs\/2404.01833"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Monika Taddicken. 2014. The \u2018privacy paradox\u2019in the social web: The impact of privacy concerns individual characteristics and the perceived social relevance on different forms of self-disclosure. Journal of computer-mediated communication 19 2 (2014) 248\u2013273.","DOI":"10.1111\/jcc4.12052"},{"key":"e_1_3_3_2_36_2","unstructured":"Ronan Takizawa. 2026. Moltbook Dataset. https:\/\/huggingface.co\/datasets\/ronantakizawa\/moltbook. Accessed: 2026-02-27."},{"key":"e_1_3_3_2_37_2","unstructured":"Jiakai Tang Heyang Gao Xuchen Pan Lei Wang Haoran Tan Dawei Gao Yushuo Chen Xu Chen Yankai Lin Yaliang Li Bolin Ding Jingren Zhou Jun Wang and Ji-Rong Wen. 2025. GenSim: A General Social Simulation Platform with Large Language Model based Agents. arxiv:https:\/\/arXiv.org\/abs\/2410.04360\u00a0[cs.MA] https:\/\/arxiv.org\/abs\/2410.04360"},{"key":"e_1_3_3_2_38_2","unstructured":"Chenxu Wang Chaozhuo Li Songyang Liu Zejian Chen Jinyu Hou Ji Qi Rui Li Litian Zhang Qiwei Ye Zheng Liu Xu Chen Xi Zhang and Philip\u00a0S. Yu. 2026. The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies. arxiv:https:\/\/arXiv.org\/abs\/2602.09877\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2602.09877"},{"key":"e_1_3_3_2_39_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_2_40_2","unstructured":"Yuwei Yan Qingbin Zeng Zhiheng Zheng Jingzhe Yuan Jie Feng Jun Zhang Fengli Xu and Yong Li. 2024. OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agents. arxiv:https:\/\/arXiv.org\/abs\/2410.21286\u00a0[cs.MA] https:\/\/arxiv.org\/abs\/2410.21286"},{"key":"e_1_3_3_2_41_2","volume-title":"The eleventh international conference on learning representations","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik\u00a0R Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. In The eleventh international conference on learning representations."},{"key":"e_1_3_3_2_42_2","unstructured":"Yunbei Zhang Kai Mei Ming Liu Janet Wang Dimitris\u00a0N. Metaxas Xiao Wang Jihun Hamm and Yingqiang Ge. 2026. Agents in the Wild: Safety Society and the Illusion of Sociality on Moltbook. arxiv:https:\/\/arXiv.org\/abs\/2602.13284\u00a0[cs.SI] https:\/\/arxiv.org\/abs\/2602.13284"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric Xing et\u00a0al. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in neural information processing systems 36 (2023) 46595\u201346623.","DOI":"10.52202\/075280-2020"},{"key":"e_1_3_3_2_44_2","unstructured":"Jijie Zhou Niloofar Mireshghallah and Tianshi Li. 2025. Operationalizing Data Minimization for Privacy-Preserving LLM Prompting. arxiv:https:\/\/arXiv.org\/abs\/2510.03662\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2510.03662"},{"key":"e_1_3_3_2_45_2","unstructured":"Xuhui Zhou Hao Zhu Leena Mathur Ruohong Zhang Haofei Yu Zhengyang Qi Louis-Philippe Morency Yonatan Bisk Daniel Fried Graham Neubig et\u00a0al. 2023. Sotopia: Interactive evaluation for social intelligence in language agents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.11667 (2023)."},{"key":"e_1_3_3_2_46_2","unstructured":"Zhenhong Zhou Jiuyang Xiang Haopeng Chen Quan Liu Zherui Li and Sen Su. 2024. Speak out of turn: Safety vulnerability of large language models in multi-turn dialogue. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.17262 (2024)."},{"key":"e_1_3_3_2_47_2","unstructured":"Xiaochen Zhu Caiqi Zhang Tom Stafford Nigel Collier and Andreas Vlachos. 2025. Conformity in Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2410.12428\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2410.12428"}],"event":{"name":"CAIS '26: ACM Conference on AI and Agentic Systems","location":"San Jose CA USA","acronym":"CAIS '26"},"container-title":["Proceedings of the ACM Conference on AI and Agentic Systems"],"original-title":[],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:28:37Z","timestamp":1779420517000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786335.3813173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,26]]},"references-count":46,"alternative-id":["10.1145\/3786335.3813173","10.1145\/3786335"],"URL":"https:\/\/doi.org\/10.1145\/3786335.3813173","relation":{},"subject":[],"published":{"date-parts":[[2026,5,26]]},"assertion":[{"value":"2026-05-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}