{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T19:56:31Z","timestamp":1790625391439,"version":"4.1.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62376013"],"award-info":[{"award-number":["62376013"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3694367","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T19:46:13Z","timestamp":1779133573000},"page":"12024-12041","source":"Crossref","is-referenced-by-count":1,"title":["Evolving Diverse Red-Team Language Models in Multi-Round Multi-Agent Games"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7963-3024","authenticated-orcid":false,"given":"Chengdong","family":"Ma","sequence":"first","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8795-8365","authenticated-orcid":false,"given":"Ziran","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7170-277X","authenticated-orcid":false,"given":"Hai","family":"Ci","sequence":"additional","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minquan","family":"Gao","sequence":"additional","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1890-660X","authenticated-orcid":false,"given":"Xuehai","family":"Pan","sequence":"additional","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8132-5613","authenticated-orcid":false,"given":"Yaodong","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Introducing chatGPT","author":"Schulman","year":"2022"},{"key":"ref2","article-title":"Meet claude","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00359-2"},{"key":"ref5","first-page":"2633","article-title":"Extracting training data from large language models","volume-title":"Proc. 30th USENIX Secur. Symp.","author":"Carlini"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.235"},{"key":"ref8","article-title":"Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned","author":"Ganguli","year":"2022"},{"key":"ref9","article-title":"Recursively summarizing books with human feedback","author":"Wu","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1461"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.225"},{"key":"ref12","article-title":"GPTFUZZER: Red teaming large language models with auto-generated jailbreak prompts","author":"Yu","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00639"},{"key":"ref14","article-title":"Universal and transferable adversarial attacks on aligned language models","author":"Zou","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.175"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6400"},{"key":"ref17","article-title":"Curiosity-driven red-teaming for large language models","author":"Hong","year":"2024"},{"key":"ref18","article-title":"Explore, establish, exploit: Red teaming language models from scratch","author":"Casper","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.4337\/9781781950777.00022"},{"key":"ref20","first-page":"1","article-title":"Can LLMs generate random numbers? Evaluating LLM sampling in controlled domains","volume-title":"Proc. ICML 2023 Workshop: Sampling Optim. Discrete Space","author":"Hopkins"},{"key":"ref21","article-title":"ODIN: Disentangled reward mitigates hacking in RLHF","author":"Chen","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21307"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref24","first-page":"17443","article-title":"Real world games look like spinning tops","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Czarnecki"},{"key":"ref25","first-page":"4193","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lanctot"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jet.2005.12.010"},{"key":"ref27","first-page":"3008","article-title":"Learning to summarize with human feedback","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Stiennon"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00639"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.442"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.696"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1262"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682430"},{"key":"ref33","article-title":"Constitutional AI: Harmlessness from AI feedback","author":"Bai","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0115"},{"key":"ref35","article-title":"Neural text generation with unlikelihood training","author":"Welleck","year":"2019"},{"key":"ref36","article-title":"Negative training for neural dialogue response generation","author":"He","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.428"},{"key":"ref38","volume-title":"The Theory of Extensive Form Games","author":"Ritzberger","year":"2016"},{"key":"ref39","volume-title":"Introduction to Tensor Calculus and Continuum Mechanics","volume":"52","author":"Heinbockel","year":"2001"},{"key":"ref40","first-page":"793","article-title":"Deep counterfactual regret minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Brown"},{"key":"ref41","first-page":"536","article-title":"Planning in the presence of cost functions controlled by an adversary","volume-title":"Proc. 20th Int. Conf. Mach. Learn.","author":"McMahan"},{"key":"ref42","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811654"},{"key":"ref44","first-page":"8514","article-title":"Modelling behavioural diversity for learning in open-ended games","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Perez-Nieves"},{"key":"ref45","first-page":"941","article-title":"Towards unifying behavioral and response diversity for open-ended learning in zero-sum games","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref46","first-page":"18050","article-title":"Effective diversity in population based reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Parker-Holder"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0751"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2005.08.005"},{"key":"ref49","article-title":"Stanford alpaca: An instruction-following LLaMA model","author":"Taori","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1072"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1967.10482901"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3660147"},{"key":"ref53","first-page":"1","article-title":"Understanding the effects of RLHF on LLM generalisation and diversity","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Kirk"},{"key":"ref54","first-page":"6555","article-title":"Improving neural language modeling via adversarial training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref55","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-51630-6_6"},{"issue":"11","key":"ref58","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11523653.pdf?arnumber=11523653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T19:07:33Z","timestamp":1790622453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11523653\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":57,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3694367","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}