{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:53Z","timestamp":1786120853714,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":13,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"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":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818237","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:43Z","timestamp":1786036543000},"page":"13421-13422","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["KDD Workshop on Evaluation and Trustworthiness of Agentic AI"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1135-5240","authenticated-orcid":false,"given":"Yuan","family":"Ling","sequence":"first","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0240-681X","authenticated-orcid":false,"given":"Shujing","family":"Dong","sequence":"additional","affiliation":[{"name":"Amazon, Irvine, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7595-6945","authenticated-orcid":false,"given":"Yarong","family":"Feng","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5665-7752","authenticated-orcid":false,"given":"Sadid A.","family":"Hasan","sequence":"additional","affiliation":[{"name":"Microsoft, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2753-1437","authenticated-orcid":false,"given":"George","family":"Karypis","sequence":"additional","affiliation":[{"name":"University of Minnesota, Minneapolis, MN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2839-3662","authenticated-orcid":false,"given":"Chandan","family":"Reddy","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Workshop on Computer Use Agents. ICML 2025 Workshop (Organizers). https:\/\/icml.cc\/virtual\/2025\/workshop\/39960","author":"Barber David","year":"2025","unstructured":"David Barber, Doina Precup, Andrei Nica, Roberta Raileanu, Harshil Shah, Boyuan Zheng, and Shuyan Zhou. 2025. Workshop on Computer Use Agents. ICML 2025 Workshop (Organizers). https:\/\/icml.cc\/virtual\/2025\/workshop\/39960."},{"key":"e_1_3_2_1_2_1","volume-title":"Workshop on Collaborative and Federated Agentic Workflows (CFAgentic). ICML 2025 Workshop (Organizers). https:\/\/cfagentic.github.io\/.","author":"Erben Alexander","year":"2025","unstructured":"Alexander Erben, Gauri Joshi, Nicholas Lane, Huan Sun, Shiqiang Wang, and Herbert Woisetschlaeger. 2025. Workshop on Collaborative and Federated Agentic Workflows (CFAgentic). ICML 2025 Workshop (Organizers). https:\/\/cfagentic.github.io\/."},{"key":"e_1_3_2_1_3_1","volume-title":"Gartner Predicts Over 40 Percent of Agentic AI Projects Will Be Canceled by End of","year":"2027","unstructured":"Gartner. 2025. Gartner Predicts Over 40 Percent of Agentic AI Projects Will Be Canceled by End of 2027. https:\/\/www.gartner.com\/en\/newsroom\/press-releases\/2025-06-25-gartner-predicts-over-40-percent-of-agentic-ai-projects-will-be-canceled-by-end-of-2027. Accessed: 2026-02-01."},{"key":"e_1_3_2_1_4_1","unstructured":"Jiawei Gu Xuhui Jiang Zhichao Shi Hexiang Tan Xuehao Zhai Chengjin Xu Wei Li Yinghan Shen Shengjie Ma Honghao Liu et al. 2024. A survey on llm-as-a-judge. The Innovation (2024)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"e_1_3_2_1_6_1","volume-title":"NeurIPS 2025 Workshop (Organizers). https:\/\/sites.google.com\/view\/llm-eval-workshop\/.","author":"Isik Berivan","year":"2025","unstructured":"Berivan Isik, Beyza Ermis, Diyi Yang, Marius Hobbhahn, Nithya Attaluri, Rishi Bommasani, and Yangjun Ruan. 2025. LLM-eval@NeurIPS: Benchmarks, Emergent Abilities, and Scaling. NeurIPS 2025 Workshop (Organizers). https:\/\/sites.google.com\/view\/llm-eval-workshop\/."},{"key":"e_1_3_2_1_7_1","volume-title":"Hallucinations: A Survey of Taxonomy, Methods, and Directions. arXiv preprint arXiv:2509.18970","author":"Lin Xixun","year":"2025","unstructured":"Xixun Lin, Yucheng Ning, Jingwen Zhang, Yan Dong, Yilong Liu, Yongxuan Wu, Xiaohua Qi, Nan Sun, Yanmin Shang, Kun Wang, et al., 2025. LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions. arXiv preprint arXiv:2509.18970 (2025)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737854"},{"key":"e_1_3_2_1_9_1","volume-title":"KDD workshop on Evaluation and Trustworthiness of Generative AI Models. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 6729-6730","author":"Ling Yuan","year":"2024","unstructured":"Yuan Ling, Shujing Dong, Yarong Feng, Zongyi Liu, George Karypis, and Chandan K Reddy. 2024. KDD workshop on Evaluation and Trustworthiness of Generative AI Models. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 6729-6730."},{"key":"e_1_3_2_1_10_1","volume-title":"Lana Saadeddin, and Mykel J. Kochenderfer.","author":"Meimandi Kiana Jafari","year":"2025","unstructured":"Kiana Jafari Meimandi, Gabriela Ar\u00e1nguiz-Dias, Grace Ra Kim, Lana Saadeddin, and Mykel J. Kochenderfer. 2025. The Measurement Imbalance in Agentic AI Evaluation Undermines Industry Productivity Claims. arXiv preprint arXiv:2506.02064 (2025)."},{"key":"e_1_3_2_1_11_1","volume-title":"V6, 1","author":"Shukla Manish","year":"2026","unstructured":"Manish Shukla. 2026. Adaptive monitoring and real-world evaluation of agentic AI systems. AI and Ethics, V6, 1 (2026), 129."},{"key":"e_1_3_2_1_12_1","volume-title":"Survey on Evaluation of LLM-based Agents. arXiv preprint arXiv:2503.16416","author":"Yehudai Asaf","year":"2025","unstructured":"Asaf Yehudai, Lilach Eden, Alan Li, Guy Uziel, Yilun Zhao, Roy Bar-Haim, Arman Cohan, and Michal Shmueli-Scheuer. 2025. Survey on Evaluation of LLM-based Agents. arXiv preprint arXiv:2503.16416 (2025). ACL Findings."},{"key":"e_1_3_2_1_13_1","volume-title":"A Survey on Trustworthy LLM Agents: Threats and Countermeasures. arXiv preprint arXiv:2503.09648","author":"Yu Miao","year":"2025","unstructured":"Miao Yu, Fanci Meng, Xinyun Zhou, Shilong Wang, Junyuan Mao, Linsey Pang, Tianlong Chen, Kun Wang, Xinfeng Li, Yongfeng Zhang, Bo An, and Qingsong Wen. 2025. A Survey on Trustworthy LLM Agents: Threats and Countermeasures. arXiv preprint arXiv:2503.09648 (2025)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:11:24Z","timestamp":1786065084000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818237"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":13,"alternative-id":["10.1145\/3770855.3818237","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818237","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}