{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T04:08:14Z","timestamp":1779422894729,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":41,"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\/3786335.3813147","type":"proceedings-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:16:22Z","timestamp":1779419782000},"page":"483-496","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Trace-Level Analysis of Information Contamination in Multi-Agent Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9337-9832","authenticated-orcid":false,"given":"Anna","family":"Mazhar","sequence":"first","affiliation":[{"name":"Cornell University, Ithaca, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4571-666X","authenticated-orcid":false,"given":"Huzaifa","family":"Suri","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2529-4036","authenticated-orcid":false,"given":"Sainyam","family":"Galhotra","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,26]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Moloud Abdar Farhad Pourpanah Sadiq Hussain Dana Rezazadegan Li Liu Mohammad Ghavamzadeh Paul Fieguth Xiaochun Cao Abbas Khosravi U.\u00a0Rajendra Acharya Vladimir Makarenkov and Saeid Nahavandi. 2021. A review of uncertainty quantification in deep learning: Techniques applications and challenges. Information Fusion (2021).","DOI":"10.1016\/j.inffus.2021.05.008"},{"key":"e_1_3_3_1_3_2","unstructured":"Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry Quoc Le and Charles Sutton. 2021. Program Synthesis with Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2108.07732"},{"key":"e_1_3_3_1_4_2","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\u00a0El Showk Stanislav Fort Tamera Lanham Timothy Telleen-Lawton Tom Conerly Tom Henighan Tristan Hume Samuel\u00a0R. Bowman Zac Hatfield-Dodds Ben Mann Dario Amodei Nicholas Joseph Sam McCandlish Tom Brown and Jared Kaplan. 2022. Constitutional AI: Harmlessness from AI Feedback. arxiv:https:\/\/arXiv.org\/abs\/2212.08073"},{"key":"e_1_3_3_1_5_2","unstructured":"Mert Cemri Melissa\u00a0Z. Pan Shuyi Yang Lakshya\u00a0A. Agrawal Bhavya Chopra Rishabh Tiwari Kurt Keutzer Aditya Parameswaran Dan Klein Kannan Ramchandran Matei Zaharia Joseph\u00a0E. Gonzalez and Ion Stoica. 2025. Why Do Multi-Agent LLM Systems Fail? arxiv:https:\/\/arXiv.org\/abs\/2503.13657"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Jiawei Chen Hongyu Lin Xianpei Han and Le Sun. 2024. Benchmarking Large Language Models in Retrieval-Augmented Generation. Proceedings of the AAAI Conference on Artificial Intelligence (2024).","DOI":"10.1609\/aaai.v38i16.29728"},{"key":"e_1_3_3_1_7_2","volume-title":"Advances in Neural Information Processing Systems","author":"Deng Xiang","year":"2023","unstructured":"Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Sam Stevens, Boshi Wang, Huan Sun, and Yu Su. 2023. Mind2Web: Towards a Generalist Agent for the Web. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_1_8_2","unstructured":"Adam Fourney Gagan Bansal Hussein Mozannar Cheng Tan Eduardo Salinas Erkang Zhu Friederike Niedtner Grace Proebsting Griffin Bassman Jack Gerrits Jacob Alber Peter Chang Ricky Loynd Robert West Victor Dibia Ahmed Awadallah Ece Kamar Rafah Hosn and Saleema Amershi. 2024. Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks. arxiv:https:\/\/arXiv.org\/abs\/2411.04468"},{"key":"e_1_3_3_1_9_2","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Gao Luyu","year":"2023","unstructured":"Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. PAL: Program-aided Language Models. In Proceedings of the 40th International Conference on Machine Learning."},{"key":"e_1_3_3_1_10_2","unstructured":"Guardrails AI. [n. d.]. Guardrails AI Documentation. https:\/\/guardrailsai.com\/guardrails\/docs."},{"key":"e_1_3_3_1_11_2","unstructured":"Guardrails AI Inc.2024. Guardrails AI: Adding Guardrails to Large Language Models. https:\/\/github.com\/guardrails-ai\/guardrails"},{"key":"e_1_3_3_1_12_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Hong Sirui","year":"2024","unstructured":"Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, 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. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_1_13_2","unstructured":"Carlos\u00a0E. Jimenez John Yang Alexander Wettig Shunyu Yao Kexin Pei Ofir Press and Karthik Narasimhan. 2024. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? arxiv:https:\/\/arXiv.org\/abs\/2310.06770"},{"key":"e_1_3_3_1_14_2","unstructured":"Jo\u00e3o Moura. 2024. CrewAI: Framework for orchestrating role-playing autonomous AI agents. https:\/\/github.com\/crewAIInc\/crewAI."},{"key":"e_1_3_3_1_15_2","unstructured":"Omar Khattab Arnav Singhvi Paridhi Maheshwari Zhiyuan Zhang Keshav Santhanam Sri Vardhamanan Saiful Haq Ashutosh Sharma Thomas\u00a0T. Joshi Hanna Moazam Heather Miller Matei Zaharia and Christopher Potts. 2023. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines. arxiv:https:\/\/arXiv.org\/abs\/2310.03714"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Yubin Kim Ken Gu Chanwoo Park Chunjong Park Samuel Schmidgall A.\u00a0Ali Heydari Yao Yan Zhihan Zhang Yuchen Zhuang Mark Malhotra Paul\u00a0Pu Liang Hae\u00a0Won Park Yuzhe Yang Xuhai Xu Yilun Du Shwetak Patel Tim Althoff Daniel McDuff and Xin Liu. 2025. Towards a Science of Scaling Agent Systems. arxiv:https:\/\/arXiv.org\/abs\/2512.08296","DOI":"10.21203\/rs.3.rs-8414536\/v1"},{"key":"e_1_3_3_1_17_2","unstructured":"Lorenz Kuhn Yarin Gal and Sebastian Farquhar. 2023. Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation. arxiv:https:\/\/arXiv.org\/abs\/2302.09664"},{"key":"e_1_3_3_1_18_2","unstructured":"LangChain. [n. d.]. LangSmith. https:\/\/www.langchain.com\/langsmith."},{"key":"e_1_3_3_1_19_2","unstructured":"LangChain. 2024. LangGraph: Building stateful multi-actor applications with LLMs. https:\/\/github.com\/langchain-ai\/langgraph."},{"key":"e_1_3_3_1_20_2","volume-title":"Advances in Neural Information Processing Systems","author":"Li Guohao","year":"2023","unstructured":"Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_1_21_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"},{"key":"e_1_3_3_1_22_2","volume-title":"Advances in Neural Information Processing Systems","author":"Ma Chang","year":"2024","unstructured":"Chang Ma, Junlei Zhang, Zhihao Zhu, Cheng Yang, Yujiu Yang, Yaohui Jin, Zhenzhong Lan, Lingpeng Kong, and Junxian He. 2024. AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_1_23_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Mialon Gr\u00e9goire","year":"2024","unstructured":"Gr\u00e9goire Mialon, Cl\u00e9mentine Fourrier, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2024. GAIA: a benchmark for General AI Assistants. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.5555\/1251460.1251461"},{"key":"e_1_3_3_1_25_2","unstructured":"Bhargavi Paranjape Scott Lundberg Sameer Singh Hannaneh Hajishirzi Luke Zettlemoyer and Marco\u00a0Tulio Ribeiro. 2023. ART: Automatic multi-step reasoning and tool-use for large language models. arxiv:https:\/\/arXiv.org\/abs\/2303.09014"},{"key":"e_1_3_3_1_26_2","unstructured":"Aaron Parisi Yao Zhao and Noah Fiedel. 2022. TALM: Tool Augmented Language Models. arxiv:https:\/\/arXiv.org\/abs\/2205.12255"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.810"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.40"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.442"},{"key":"e_1_3_3_1_30_2","volume-title":"Advances in Neural Information Processing Systems","author":"Schick Timo","year":"2023","unstructured":"Timo Schick, Jane Dwivedi-Yu, Roberto Dessi, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language Models Can Teach Themselves to Use Tools. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_1_31_2","volume-title":"Advances in Neural Information Processing Systems","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: language agents with verbal reinforcement learning. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_1_32_2","unstructured":"Linxin Song Jiale Liu Jieyu Zhang Shaokun Zhang Ao Luo Shijian Wang Qingyun Wu and Chi Wang. 2025. Adaptive In-conversation Team Building for Language Model Agents. arxiv:https:\/\/arXiv.org\/abs\/2405.19425"},{"key":"e_1_3_3_1_33_2","unstructured":"Junlin Wang Jue Wang Ben Athiwaratkun Ce Zhang and James Zou. 2024. Mixture-of-Agents Enhances Large Language Model Capabilities. arxiv:https:\/\/arXiv.org\/abs\/2406.04692"},{"key":"e_1_3_3_1_34_2","volume-title":"Advances in Neural Information Processing Systems","author":"Wei Alexander","year":"2023","unstructured":"Alexander Wei, Nika Haghtalab, and Jacob Steinhardt. 2023. Jailbroken: How Does LLM Safety Training Fail?. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_1_35_2","volume-title":"First Conference on Language Modeling","author":"Wu Qingyun","year":"2024","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. 2024. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversations. In First Conference on Language Modeling."},{"key":"e_1_3_3_1_36_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik\u00a0R Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.670"},{"key":"e_1_3_3_1_38_2","unstructured":"Shaokun Zhang Ming Yin Jieyu Zhang Jiale Liu Zhiguang Han Jingyang Zhang Beibin Li Chi Wang Huazheng Wang Yiran Chen and Qingyun Wu. 2025. Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems. arxiv:https:\/\/arXiv.org\/abs\/2505.00212"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Haiyan Zhao Hanjie Chen Fan Yang Ninghao Liu Huiqi Deng Hengyi Cai Shuaiqiang Wang Dawei Yin and Mengnan Du. 2024. Explainability for Large Language Models: A Survey. ACM Trans. Intell. Syst. Technol. (2024).","DOI":"10.1145\/3639372"},{"key":"e_1_3_3_1_40_2","unstructured":"Shuyan Zhou Frank\u00a0F. Xu Hao Zhu Xuhui Zhou Robert Lo Abishek Sridhar Xianyi Cheng Tianyue Ou Yonatan Bisk Daniel Fried Uri Alon and Graham Neubig. 2024. WebArena: A Realistic Web Environment for Building Autonomous Agents. arxiv:https:\/\/arXiv.org\/abs\/2307.13854"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3689217.3690621"},{"key":"e_1_3_3_1_42_2","volume-title":"Socially Responsible Language Modelling Research","author":"Zhu Sicheng","year":"2023","unstructured":"Sicheng Zhu, Ruiyi Zhang, Bang An, Gang Wu, Joe Barrow, Zichao Wang, Furong Huang, Ani Nenkova, and Tong Sun. 2023. AutoDAN: Automatic and Interpretable Adversarial Attacks on Large Language Models. In Socially Responsible Language Modelling Research."}],"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":"2026-05-22T03:33:31Z","timestamp":1779420811000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786335.3813147"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,26]]},"references-count":41,"alternative-id":["10.1145\/3786335.3813147","10.1145\/3786335"],"URL":"https:\/\/doi.org\/10.1145\/3786335.3813147","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"}}]}}