{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:46:59Z","timestamp":1785908819355,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":141,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,25]]},"DOI":"10.1145\/3805689.3806748","type":"proceedings-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T16:20:39Z","timestamp":1782231639000},"page":"4199-4219","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4504-0941","authenticated-orcid":false,"given":"Botao Amber","family":"Hu","sequence":"first","affiliation":[{"name":"University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1626-7968","authenticated-orcid":false,"given":"Helena","family":"Rong","sequence":"additional","affiliation":[{"name":"New York University Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3873-6366","authenticated-orcid":false,"given":"Max Van","family":"Kleek","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Technical Report. https:\/\/a2a-protocol.org\/latest\/specification\/ Originally proposed by Google","author":"Linux A Project","year":"2025","unstructured":"A2A Project (Linux Foundation). 2025. Agent-to-Agent (A2A) Protocol Specification v1.0.0. Technical Report. https:\/\/a2a-protocol.org\/latest\/specification\/ Originally proposed by Google, April 2025."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"Ryan Abbott and Alex Sarch. 2020. Punishing Artificial Intelligence: Legal Fiction or Science Fiction. In Is Law Computable? Hart Publishing. doi:10.5040\/9781509937097.ch-008","DOI":"10.5040\/9781509937097.ch-008"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Marwa Abdulhai Isadora White Charlie Snell Charles Sun Joey Hong Yuexiang Zhai Kelvin Xu and Sergey Levine. 2023. LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models. doi:10.48550\/arXiv.2311.18232 Documents persona drift in conversational LLMs.","DOI":"10.48550\/arXiv.2311.18232"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3532853"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-025-02172-y"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9780890425596"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 13th International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=hXA8wqRdyV ICLR 2025 Poster.","author":"Andriushchenko Maksym","year":"2025","unstructured":"Maksym Andriushchenko, Francesco Croce, and Nicolas Flammarion. 2025. Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks. In Proceedings of the 13th International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=hXA8wqRdyV ICLR 2025 Poster."},{"key":"e_1_3_2_1_8_1","volume-title":"Collective Constitutional AI: Aligning a Language Model with the Input of 1,000 People.","year":"2023","unstructured":"Anthropic. 2023. Collective Constitutional AI: Aligning a Language Model with the Input of 1,000 People. (2023). https:\/\/www.anthropic.com\/research\/collective-constitutional-ai-aligning-a-language-model-with-the-input-of-1000-people"},{"key":"e_1_3_2_1_9_1","unstructured":"Anthropic. 2026. The Assistant Axis: Situating and Stabilizing the Character of Large Language Models. Technical Report. https:\/\/www.anthropic.com\/research\/assistant-axis MATS and Anthropic Fellows program research."},{"key":"e_1_3_2_1_10_1","unstructured":"Anthropic. 2026. The Persona Selection Model. Technical Report. https:\/\/www.anthropic.com\/research\/persona-selection-model Full technical post at https:\/\/alignment.anthropic.com\/2026\/psm."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Usman Anwar Abulhair Saparov Javier Rando Daniel Paleka Miles Turpin Peter Hase Ekdeep Singh Lubana Erik Jenner Stephen Casper Oliver Sourbut Benjamin L. Edelman Zhaowei Zhang Mario G\u00fcnther Anton Korinek Jose Hernandez-Orallo Lewis Hammond Eric Bigelow Alexander Pan Lauro Langosco Tomasz Korbak Heidi Zhang Ruiqi Zhong Se\u00e1n \u00d3 h\u00c9igeartaigh Gabriel Recchia Giulio Corsi Alan Chan Markus Anderljung Lilian Edwards Aleksandar Petrov Christian Schroeder de Witt Sumeet Ramesh Motwan Yoshua Bengio Danqi Chen Philip H. S. Torr Samuel Albanie Tegan Maharaj Jakob Foerster Florian Tramer He He Atoosa Kasirzadeh Yejin Choi and David Krueger. 2024. Foundational Challenges in Assuring Alignment and Safety of Large Language Models. doi:10.48550\/arXiv.2404.09932","DOI":"10.48550\/arXiv.2404.09932"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.6273198"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.7466396"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Yuntao Bai Saurav Kadavath Sandipan Kundu Amanda Askell Jackson Kernion Andy Jones Anna Chen Anna Goldie Azalia Mirhoseini Cameron McKinnon Carol Chen Catherine Olsson Christopher Olah Danny Hernandez Dawn Drain Deep Ganguli Dustin Li Eli Tran-Johnson Ethan Perez Jamie Kerr Jared Mueller Jeffrey Ladish Joshua Landau Kamal Ndousse Kamile Lukosuite Liane Lovitt Michael Sellitto Nelson Elhage Nicholas Schiefer Noemi Mercado Nova DasSarma Robert Lasenby Robin Larson Sam Ringer Scott Johnston Shauna Kravec Sheer El Showk Stanislav Fort Tamera Lanham Timothy Telleen-Lawton Tom Conerly Tom Henighan Tristan Hume Samuel R. Bowman Zac Hatfield-Dodds Ben Mann Dario Amodei Nicholas Joseph Sam McCandlish Tom Brown and Jared Kaplan. 2022. Constitutional AI: Harmlessness from AI Feedback. doi:10.48550\/arXiv.2212.08073","DOI":"10.48550\/arXiv.2212.08073"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1086\/292745"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_2_1_17_1","unstructured":"BentoML. 2024. Understanding LLM Training vs. Inference: Why Weights Are Frozen at Deployment. Technical Report. https:\/\/www.bentoml.com\/blog\/llm-ai-safety-training-vs-inference Technical blog post on LLM deployment."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09937-5"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/satml59370.2024.00037"},{"key":"e_1_3_2_1_20_1","unstructured":"Piercosma Bisconti Marcello Galisai Federico Pierucci Marcantonio Bracale and Matteo Prandi. 2025. Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions. arXiv:2512.02682 https:\/\/arxiv.org\/abs\/2512.02682"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1030.0199"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/0162-3095(92)90032-Y"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236008"},{"key":"e_1_3_2_1_24_1","unstructured":"Stephen E. Braude. 1995. First Person Plural: Multiple Personality and the Philosophy of Mind. Rowman & Littlefield."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1093\/0199246483.001.0001"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10506-017-9214-9"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-6451.2010.00405.x"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","unstructured":"Florian Carichon Aditi Khandelwal Marylou Fauchard and Golnoosh Farnadi. 2025. The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process. doi:10.48550\/arXiv.2506.01080","DOI":"10.48550\/arXiv.2506.01080"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","unstructured":"Tomer Jordi Chaffer. 2025. Know Your Agent: Governing AI Identity on the Agentic Web. (2025). doi:10.2139\/ssrn.5162127","DOI":"10.2139\/ssrn.5162127"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658948"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2406.12137"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","unstructured":"Alan Chan Kevin Wei Sihao Huang Nitarshan Rajkumar Elija Perrier Seth Lazar Gillian K. Hadfield and Markus Anderljung. 2025. Infrastructure for AI Agents. doi:10.48550\/arXiv.2501.10114","DOI":"10.48550\/arXiv.2501.10114"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2507.21509"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1080192.1080202"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2605.00073"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1093\/analys\/58.1.7"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3193577"},{"key":"e_1_3_2_1_38_1","unstructured":"Antonio R. Damasio. 1994. Descartes' Error: Emotion Reason and the Human Brain. G.P. Putnam's Sons."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10676-016-9403-3"},{"key":"e_1_3_2_1_40_1","unstructured":"Marco De Rossi Davide Crapis Jordan Ellis and Erik Reppel. 2025. ERC-8004: Trustless Agents. Technical Report. https:\/\/eips.ethereum.org\/EIPS\/eip-8004 Ethereum Improvement Proposal Draft."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.49.10.1407.17308"},{"key":"e_1_3_2_1_42_1","volume-title":"Self and Consciousness: Multiple Perspectives, FrankS","author":"Dennett Daniel C.","unstructured":"Daniel C. Dennett. 1992. The Self as a Center of Narrative Gravity. In Self and Consciousness: Multiple Perspectives, FrankS. Kessel, Pamela M. Cole, and Dale L. Johnson (Eds.). Lawrence Erlbaum Associates, 103\u2013115."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.88"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.03704"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45748-8_24"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","unstructured":"Raymond Douglas Jan Kulveit Ond\u0159ej Havl\u00ed\u010dek Theia Pearson-Vogel Owen Cotton-Barratt and David Duvenaud. 2026. The Artificial Self: Characterising the Landscape of AI Identity. doi:10.48550\/arXiv.2603.11353","DOI":"10.48550\/arXiv.2603.11353"},{"key":"e_1_3_2_1_48_1","volume-title":"Answering for Crime: Responsibility and Liability in the Criminal Law","author":"Duff R. A.","unstructured":"R. A. Duff. 2007. Answering for Crime: Responsibility and Liability in the Criminal Law. Hart Publishing."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2505.02279"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1089134"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.17351\/ests2019.260"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1017\/dap.2022.23"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1038\/415137a"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1287\/mksc.2022.1350"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/765891.765951"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/365024.365037"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1430-9134.2001.00173.x"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.2307\/1913771"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.5220\/0014234400004052"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","unstructured":"Tao Ge Xin Chan Xiaoyang Wang Dian Yu Haitao Mi and Dong Yu. 2024. Scaling Synthetic Data Creation with 1 000 000 000 Personas. doi:10.48550\/arXiv.2406.20094","DOI":"10.48550\/arXiv.2406.20094"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816826"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","unstructured":"Zihan Guo Yuanjian Zhou Chenyi Wang Linlin You Minjie Bian and Weinan Zhang. 2025. BetaWeb: Towards a Blockchain-enabled Trustworthy Agentic Web. doi:10.48550\/ARXIV.2508.13787","DOI":"10.48550\/ARXIV.2508.13787"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","unstructured":"Lewis Hammond Alan Chan Jesse Clifton Jason Hoelscher-Obermaier Akbir Khan Euan McLean Chandler Smith Wolfram Barfuss Jakob Foerster Tom\u00e1\u0161 Gaven\u010diak The Anh Han Edward Hughes Vojt\u011bch Kova\u0159\u00edk Jan Kulveit Joel Z. Leibo Caspar Oesterheld Christian Schroeder de Witt Nisarg Shah Michael Wellman Paolo Bova Theodor Cimpeanu Carson Ezell Quentin Feuillade-Montixi Matija Franklin Esben Kran Igor Krawczuk Max Lamparth Niklas Lauffer Alexander Meinke Sumeet Motwani Anka Reuel Vincent Conitzer Michael Dennis Iason Gabriel Adam Gleave Gillian Hadfield Nika Haghtalab Atoosa Kasirzadeh S\u00e9bastien Krier Kate Larson Joel Lehman David C. Parkes Georgios Piliouras and Iyad Rahwan. 2025. Multi-Agent Risks from Advanced AI. doi:10.48550\/arXiv.2502.14143","DOI":"10.48550\/arXiv.2502.14143"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199534777.001.0001"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127333"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","unstructured":"Botao Amber Hu and Helena Rong. 2025. Spore in the Wild: A Case Study of Spore.fun as an Open-Environment Evolution Experiment with Sovereign AI Agents on TEE-Secured Blockchains. arXiv:2506.04236 doi:10.1162\/ISAL.a.838","DOI":"10.1162\/ISAL.a.838"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2401.05566"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-6825-4"},{"key":"e_1_3_2_1_69_1","volume-title":"Safety Report","author":"International AI Safety Report Consortium","year":"2026","unstructured":"International AI Safety Report Consortium. 2026. International AI Safety Report 2026. Technical Report. International AI Safety Report. https:\/\/internationalaisafetyreport.org\/sites\/default\/files\/2026-02\/international-ai-safety-report-2026.pdf"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2008.03.020"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","unstructured":"Jiaming Ji Wenqi Chen Kaile Wang Donghai Hong Sitong Fang Boyuan Chen Jiayi Zhou Juntao Dai Sirui Han Yike Guo and Yaodong Yang. 2025. Mitigating Deceptive Alignment via Self-Monitoring. doi:10.48550\/arXiv.2505.18807","DOI":"10.48550\/arXiv.2505.18807"},{"key":"e_1_3_2_1_72_1","volume-title":"Proceedings of the 15th Bled Electronic Commerce Conference. 2502\u20132511","author":"J\u00f8sang Audun","year":"2002","unstructured":"Audun J\u00f8sang and Roslan Ismail. 2002. The Beta Reputation System. In Proceedings of the 15th Bled Electronic Commerce Conference. 2502\u20132511."},{"key":"e_1_3_2_1_73_1","volume-title":"Blaise Ag\u00fcera y Arcas, and Jonathan Birch","author":"Keeling Geoff","year":"2024","unstructured":"Geoff Keeling, Winnie Street, Martyna Stachaczyk, Daria Zakharova, Iulia M. Comsa, Anastasiya Sakovych, Isabella Logothetis, Zejia Zhang, Blaise Ag\u00fcera y Arcas, and Jonathan Birch. 2024. Can LLMs Make Trade-Offs Involving Stipulated Pain and Pleasure States? arXiv:2411.02432 https:\/\/arxiv.org\/abs\/2411.02432"},{"key":"e_1_3_2_1_74_1","first-page":"265","article-title":"Brain Plasticity and Behaviour in the Developing Brain","volume":"20","author":"Kolb Bryan","year":"2011","unstructured":"Bryan Kolb and Robbin Gibb. 2011. Brain Plasticity and Behaviour in the Developing Brain. Journal of the Canadian Academy of Child and Adolescent Psychiatry 20, 4 (2011), 265\u2013276.","journal-title":"Journal of the Canadian Academy of Child and Adolescent Psychiatry"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4772956"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0531(82)90030-8"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","unstructured":"Thomas Kwa Ben West Joel Becker Amy Deng Katharyn Garcia Max Hasin Sami Jawhar Megan Kinniment Nate Rush Sydney Von Arx Ryan Bloom Thomas Broadley Haoxing Du Brian Goodrich Nikola Jurkovic Luke Harold Miles Seraphina Nix Tao Lin Neev Parikh David Rein Lucas Jun Koba Sato Hjalmar Wijk Daniel M. Ziegler Elizabeth Barnes and Lawrence Chan. 2025. Measuring AI Ability to Complete Long Software Tasks. doi:10.48550\/ARXIV.2503.14499","DOI":"10.48550\/ARXIV.2503.14499"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.07283"},{"key":"e_1_3_2_1_79_1","unstructured":"Letta (formerly MemGPT). 2024. Building Agents with Long-Term Memory and Continual Learning. Technical Report. https:\/\/www.letta.com\/blog\/building-agents-with-long-term-memory Discusses external memory as substitute for neuroplasticity in LLM agents."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","unstructured":"Cheng Li Jindong Wang Yixuan Zhang Kaijie Zhu Wenxin Hou Jianxun Lian Fang Luo Qiang Yang and Xing Xie. 2023. Large Language Models Understand and Can Be Enhanced by Emotional Stimuli. doi:10.48550\/arXiv.2307.11760","DOI":"10.48550\/arXiv.2307.11760"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.756242"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2512.17538"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.423"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","unstructured":"Monte MacDiarmid Benjamin Wright Jonathan Uesato Joe Benton Jon Kutasov Sara Price Naia Bouscal Sam Bowman Trenton Bricken Alex Cloud Carson Denison Johannes Gasteiger Ryan Greenblatt Jan Leike Jack Lindsey Vlad Mikulik Ethan Perez Alex Rodrigues Drake Thomas Albert Webson Daniel Ziegler and Evan Hubinger. 2025. Natural Emergent Misalignment from Reward Hacking in Production RL. doi:10.48550\/arXiv.2511.18397","DOI":"10.48550\/arXiv.2511.18397"},{"key":"e_1_3_2_1_86_1","volume-title":"Mailath and Larry Samuelson","author":"George","year":"2006","unstructured":"George J. Mailath and Larry Samuelson. 2006. Repeated Games and Reputations: Long-Run Relationships. Oxford University Press."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10676-004-3422-1"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.2307\/258792"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.20729"},{"key":"e_1_3_2_1_90_1","volume-title":"Phenomenology of Perception","author":"Merleau-Ponty Maurice","year":"2012","unstructured":"Maurice Merleau-Ponty. 1945. Phenomenology of Perception. Routledge. English translation by Donald Landes, 2012."},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1192\/bjp.160.3.327"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.20672"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pragma.2013.07.012"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0531(82)90031-X"},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-0343.1990.tb00020.x"},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature04131"},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713301"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1145\/3595292"},{"key":"e_1_3_2_1_99_1","unstructured":"OpenAI. 2024. Model Spec. Technical Report. https:\/\/cdn.openai.com\/spec\/model-spec-2024-05-08.html"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511807763"},{"key":"e_1_3_2_1_101_1","unstructured":"Derek Parfit. 1984. Reasons and Persons. Oxford University Press."},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"publisher","unstructured":"Chanwoo Park Xiangyu Liu Asuman Ozdaglar and Kaiqing Zhang. 2025. Do LLM Agents Have Regret? A Case Study in Online Learning and Games. doi:10.48550\/arXiv.2403.16843","DOI":"10.48550\/arXiv.2403.16843"},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","unstructured":"Zehua Pei Hui-Ling Zhen Ying Zhang Zhiyuan Yang Xing Li Xianzhi Yu Mingxuan Yuan and Bei Yu. 2025. Behavioral Fingerprinting of Large Language Models. doi:10.48550\/arXiv.2509.04504","DOI":"10.48550\/arXiv.2509.04504"},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","unstructured":"Elija Perrier and Michael Timothy Bennett. 2025. Agent Identity Evals: Measuring Agentic Identity. doi:10.48550\/arXiv.2507.17257","DOI":"10.48550\/arXiv.2507.17257"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.10420"},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-011-9277-z"},{"key":"e_1_3_2_1_107_1","volume-title":"Plutarch's Lives","unstructured":"Plutarch. 1914. Life of Theseus. In Plutarch's Lives. Loeb Classical Library, Vol. 1. Harvard University Press, Cambridge, MA."},{"key":"e_1_3_2_1_108_1","unstructured":"Wenjie Qu Xuandong Zhao Jiaheng Zhang and Dawn Song. 2026. Self-Sovereign Agent. arXiv:2604.08551 https:\/\/arxiv.org\/abs\/2604.08551"},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888904000116"},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2507.14263"},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2601.04170"},{"key":"e_1_3_2_1_112_1","doi-asserted-by":"publisher","unstructured":"Siyue Ren Wanli Fu Xinkun Zou Chen Shen Yi Cai Chen Chu Zhen Wang and Shuyue Hu. 2025. Reputation as a Solution to Cooperation Collapse in LLM-based MASs. doi:10.48550\/arXiv.2505.05029","DOI":"10.48550\/arXiv.2505.05029"},{"key":"e_1_3_2_1_113_1","doi-asserted-by":"publisher","DOI":"10.1145\/355112.355122"},{"key":"e_1_3_2_1_114_1","doi-asserted-by":"publisher","unstructured":"Paul Resnick and Richard Zeckhauser. 2002. Trust among strangers in Internet transactions: Empirical analysis of eBay's reputation system. Emerald 127\u2013157. doi:10.1016\/S0278-0984(02)11030-3","DOI":"10.1016\/S0278-0984(02)11030-3"},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10683-006-4309-2"},{"key":"e_1_3_2_1_116_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.14981"},{"key":"e_1_3_2_1_117_1","first-page":"3758","article-title":"Algorithmic labor and information asymmetries: A case study of Uber's drivers","volume":"10","author":"Rosenblat Alex","year":"2016","unstructured":"Alex Rosenblat and Luke Stark. 2016. Algorithmic labor and information asymmetries: A case study of Uber's drivers. International Journal of Communication 10 (2016), 3758\u20133784. https:\/\/ijoc.org\/index.php\/ijoc\/article\/view\/4892","journal-title":"International Journal of Communication"},{"key":"e_1_3_2_1_118_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-004-0041-5"},{"key":"e_1_3_2_1_119_1","first-page":"383","article-title":"Multiple Personality Disorder and Criminal Responsibility","volume":"25","author":"Saks Elyn","year":"1991","unstructured":"Elyn R.Saks. 1991. Multiple Personality Disorder and Criminal Responsibility. UC Davis Law Review 25, 2(1991), 383\u2013460.","journal-title":"UC Davis Law Review"},{"key":"e_1_3_2_1_120_1","volume-title":"Behnke","author":"Saks Elyn R.","year":"1997","unstructured":"Elyn R. Saks and Stephen H. Behnke. 1997. Jekyll on Trial: Multiple Personality Disorder and Criminal Law. New York University Press."},{"key":"e_1_3_2_1_121_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06647-8"},{"key":"e_1_3_2_1_122_1","unstructured":"Natalie Shapira Chris Wendler Avery Yen Gabriele Sarti Koyena Pal Olivia Floody Adam Belfki Alex Loftus Aditya Ratan Jannali Nikhil Prakash Jasmine Cui Giordano Rogers Jannik Brinkmann Can Rager Amir Zur Michael Ripa Aruna Sankaranarayanan David Atkinson Rohit Gandikota Jaden Fiotto-Kaufman EunJeong Hwang Hadas Orgad P Sam Sahil Negev Taglicht Tomer Shabtay Atai Ambus Nitay Alon Shiri Oron Ayelet Gordon-Tapiero Yotam Kaplan Vered Shwartz Tamar Rott Shaham Christoph Riedl Reuth Mirsky Maarten Sap David Manheim Tomer Ullman and David Bau. 2026. Agents of Chaos. arXiv:2602.20021 https:\/\/arxiv.org\/abs\/2602.20021"},{"key":"e_1_3_2_1_123_1","volume-title":"Proceedings of the 12th International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=tvhaxkMKAn ICLR 2024 Poster.","author":"Sharma Mrinank","year":"2024","unstructured":"Mrinank Sharma, Meg Tong, Tomasz Korbak, David Duvenaud, Amanda Askell, Samuel R. Bowman, Newton Cheng, Esin Durmus, Zac Hatfield-Dodds, Scott R. Johnston, Shauna Kravec, Timothy Maxwell, Sam McCandlish, Kamal Ndousse, Oliver Rausch, Nicholas Schiefer, Da Yan, Miranda Zhang, and Ethan Perez. 2024. Towards Understanding Sycophancy in Language Models. In Proceedings of the 12th International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=tvhaxkMKAn ICLR 2024 Poster."},{"key":"e_1_3_2_1_124_1","doi-asserted-by":"publisher","DOI":"10.1145\/3735633"},{"key":"e_1_3_2_1_125_1","first-page":"277","article-title":"Criminal Law and Multiple Personality Disorder: The Vexing Problems of Personhood and Responsibility","volume":"10","author":"Sinnott-Armstrong Walter","year":"2000","unstructured":"Walter Sinnott-Armstrong and Stephen Behnke. 2000. Criminal Law and Multiple Personality Disorder: The Vexing Problems of Personhood and Responsibility. Southern California Interdisciplinary Law Journal 10 (2000), 277\u2013296. https:\/\/scholarship.law.duke.edu\/faculty_scholarship\/1054\/","journal-title":"Southern California Interdisciplinary Law Journal"},{"key":"e_1_3_2_1_126_1","first-page":"3","article-title":"The Multiple Personality and the Law","volume":"12","author":"Slovenko Ralph","year":"1993","unstructured":"Ralph Slovenko. 1993. The Multiple Personality and the Law. Medicine and Law 12, 3-4 (1993), 303\u2013340. https:\/\/pubmed.ncbi.nlm.nih.gov\/8189960\/","journal-title":"Medicine and Law"},{"key":"e_1_3_2_1_127_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.09674"},{"key":"e_1_3_2_1_128_1","doi-asserted-by":"publisher","unstructured":"Leon Staufer Kevin Feng Kevin Wei Luke Bailey Yawen Duan Mick Yang A. Pinar Ozisik Stephen Casper and Noam Kolt. 2026. The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems. doi:10.48550\/ARXIV.2602.17753","DOI":"10.48550\/ARXIV.2602.17753"},{"key":"e_1_3_2_1_129_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1234-981X(199707)5:3<305::AID-EURO184>3.0.CO;2-4"},{"key":"e_1_3_2_1_130_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-006-5952-x"},{"key":"e_1_3_2_1_131_1","doi-asserted-by":"publisher","DOI":"10.1002\/cb.1667"},{"key":"e_1_3_2_1_132_1","doi-asserted-by":"publisher","unstructured":"Nenad Toma\u0161ev Matija Franklin Julian Jacobs S\u00e9bastien Krier and Simon Osindero. 2025. Distributional AGI Safety. doi:10.48550\/ARXIV.2512.16856","DOI":"10.48550\/ARXIV.2512.16856"},{"key":"e_1_3_2_1_133_1","doi-asserted-by":"publisher","unstructured":"Nenad Toma\u0161ev Matija Franklin and Simon Osindero. 2026. Intelligent AI Delegation. doi:10.48550\/ARXIV.2602.11865","DOI":"10.48550\/ARXIV.2602.11865"},{"key":"e_1_3_2_1_134_1","volume-title":"25th USENIX Security Symposium (USENIX Security 16)","author":"Tram\u00e8r Florian","year":"2016","unstructured":"Florian Tram\u00e8r, Fan Zhang, Ari Juels, Michael K. Reiter, and Thomas Ristenpart. 2016. Stealing Machine Learning Models via Prediction APIs. In 25th USENIX Security Symposium (USENIX Security 16). USENIX Association, Austin, TX, 601\u2013618. https:\/\/www.usenix.org\/conference\/usenixsecurity16\/technical-sessions\/presentation\/tramer"},{"key":"e_1_3_2_1_135_1","doi-asserted-by":"publisher","DOI":"10.1086\/406755"},{"key":"e_1_3_2_1_136_1","first-page":"117","article-title":"Machines Without Principals: Liability Rules and Artificial Intelligence","volume":"89","author":"Vladeck David C.","year":"2014","unstructured":"David C. Vladeck. 2014. Machines Without Principals: Liability Rules and Artificial Intelligence. Washington Law Review 89, 1 (2014), 117\u2013150. https:\/\/digitalcommons.law.uw.edu\/wlr\/vol89\/iss1\/5\/","journal-title":"Washington Law Review"},{"key":"e_1_3_2_1_137_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533088"},{"key":"e_1_3_2_1_138_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4105763"},{"key":"e_1_3_2_1_139_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning (ICML). https:\/\/openreview.net\/forum?id=KXsUCgn9Ks ICML 2024 Poster.","author":"Wolf Yotam","year":"2024","unstructured":"Yotam Wolf, Noam Wies, Yoav Levine, and Amnon Shashua. 2024. Fundamental Limitations of Alignment in Large Language Models. In Proceedings of the 41st International Conference on Machine Learning (ICML). https:\/\/openreview.net\/forum?id=KXsUCgn9Ks ICML 2024 Poster."},{"key":"e_1_3_2_1_140_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2507.21206"},{"key":"e_1_3_2_1_141_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11002-020-09546-4"}],"event":{"name":"FAccT '26: The 2026 ACM Conference on Fairness, Accountability, and Transparency","location":"Montreal QC Canada","acronym":"FAccT '26","sponsor":["ACM\/SIG"]},"container-title":["Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805689.3806748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:17:52Z","timestamp":1782757072000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805689.3806748"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":141,"alternative-id":["10.1145\/3805689.3806748","10.1145\/3805689"],"URL":"https:\/\/doi.org\/10.1145\/3805689.3806748","relation":{},"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"2026-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}