{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T20:34:44Z","timestamp":1791491684014,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":48,"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\/3770855.3817526","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"9427-9438","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["MigrationBench: Repository-Level Code Migration Benchmark from Java 8"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7368-4974","authenticated-orcid":false,"given":"Linbo","family":"Liu","sequence":"first","affiliation":[{"name":"AWS AI, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4960-0018","authenticated-orcid":false,"given":"Xinle","family":"Liu","sequence":"additional","affiliation":[{"name":"AWS AI, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6770-0880","authenticated-orcid":false,"given":"Qiang","family":"Zhou","sequence":"additional","affiliation":[{"name":"AWS AI, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3438-0918","authenticated-orcid":false,"given":"Lin","family":"Chen","sequence":"additional","affiliation":[{"name":"AWS AI, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5290-8179","authenticated-orcid":false,"given":"Yihan","family":"Liu","sequence":"additional","affiliation":[{"name":"AWS AI, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6194-7930","authenticated-orcid":false,"given":"Hoan","family":"Nguyen","sequence":"additional","affiliation":[{"name":"AWS AI, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9103-0114","authenticated-orcid":false,"given":"Behrooz Omidvar","family":"Tehrani","sequence":"additional","affiliation":[{"name":"AWS AI, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8076-3545","authenticated-orcid":false,"given":"Xi","family":"Shen","sequence":"additional","affiliation":[{"name":"AWS AI, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7020-1604","authenticated-orcid":false,"given":"Jun","family":"Huan","sequence":"additional","affiliation":[{"name":"AWS AI, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2393-854X","authenticated-orcid":false,"given":"Omer","family":"Tripp","sequence":"additional","affiliation":[{"name":"AWS AI, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4566-8767","authenticated-orcid":false,"given":"Anoop","family":"Deoras","sequence":"additional","affiliation":[{"name":"AWS AI, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"System card: Claude sonnet 4.5","year":"2025","unstructured":"Anthropic. System card: Claude sonnet 4.5, 2025. Accessed: 2026-02-02."},{"key":"e_1_3_2_2_2_1","volume-title":"Zijian Wang, Xiaopeng Li, Yuchen Tian, Ming Tan, Wasi Uddin Ahmad, Shiqi Wang, Qing Sun, Mingyue Shang, et al. Multi-lingual evaluation of code generation models. arXiv preprint arXiv:2210.14868","author":"Athiwaratkun Ben","year":"2022","unstructured":"Ben Athiwaratkun, Sanjay Krishna Gouda, Zijian Wang, Xiaopeng Li, Yuchen Tian, Ming Tan, Wasi Uddin Ahmad, Shiqi Wang, Qing Sun, Mingyue Shang, et al. Multi-lingual evaluation of code generation models. arXiv preprint arXiv:2210.14868, 2022."},{"key":"e_1_3_2_2_3_1","volume-title":"Program synthesis with large language models. arXiv preprint arXiv:2108.07732","author":"Austin Jacob","year":"2021","unstructured":"Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, et al. Program synthesis with large language models. arXiv preprint arXiv:2108.07732, 2021."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643757"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1142\/9789812389718_0005"},{"key":"e_1_3_2_2_6_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde de Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman Alex Ray Raul Puri Gretchen Krueger Michael Petrov Heidy Khlaaf Girish Sastry Pamela Mishkin Brooke Chan Scott Gray Nick Ryder Mikhail Pavlov Alethea Power Lukasz Kaiser Mohammad Bavarian Clemens Winter Philippe Tillet Felipe Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew N. Carr Jan Leike Josh Achiam Vedant Misra Evan Morikawa Alec Radford Matthew Knight Miles Brundage Mira Murati Katie Mayer Peter Welinder Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever and Wojciech Zaremba. Evaluating large language models trained on code 2021."},{"key":"e_1_3_2_2_7_1","volume-title":"Teaching large language models to self-debug. arXiv preprint arXiv:2304.05128","author":"Chen Xinyun","year":"2023","unstructured":"Xinyun Chen, Maxwell Lin, Nathanael Sch\u00e4rli, and Denny Zhou. Teaching large language models to self-debug. arXiv preprint arXiv:2304.05128, 2023."},{"key":"e_1_3_2_2_8_1","volume-title":"Chatunitest: A framework for llm-based test generation","author":"Chen Yinghao","year":"2024","unstructured":"Yinghao Chen, Zehao Hu, Chen Zhi, Junxiao Han, Shuiguang Deng, and Jianwei Yin. Chatunitest: A framework for llm-based test generation, 2024."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.140"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671452"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533229"},{"key":"e_1_3_2_2_12_1","volume-title":"Measuring coding challenge competence with apps. arXiv preprint arXiv:2105.09938","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song, et al. Measuring coding challenge competence with apps. arXiv preprint arXiv:2105.09938, 2021."},{"key":"e_1_3_2_2_13_1","volume-title":"Zijuan Lin, Liyang Zhou, et al. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352","author":"Hong Sirui","year":"2023","unstructured":"Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, et al. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352, 2023."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3660773"},{"key":"e_1_3_2_2_15_1","volume-title":"Agentcoder: Multi-agent-based code generation with iterative testing and optimisation. arXiv preprint arXiv:2312.13010","author":"Huang Dong","year":"2023","unstructured":"Dong Huang, Qingwen Bu, Jie M Zhang, Michael Luck, and Heming Cui. Agentcoder: Multi-agent-based code generation with iterative testing and optimisation. arXiv preprint arXiv:2312.13010, 2023."},{"key":"e_1_3_2_2_16_1","volume-title":"Rangeet Pan, Saurabh Sinha, and Reyhaneh Jabbarvand. Repository-level compositional code translation and validation","author":"Ibrahimzada Ali Reza","year":"2024","unstructured":"Ali Reza Ibrahimzada, Kaiyao Ke, Mrigank Pawagi, Muhammad Salman Abid, Rangeet Pan, Saurabh Sinha, and Reyhaneh Jabbarvand. Repository-level compositional code translation and validation, 2024."},{"key":"e_1_3_2_2_17_1","volume-title":"Swe-bench: Can language models resolve real-world github issues?","author":"Jimenez Carlos E.","year":"2024","unstructured":"Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan. Swe-bench: Can language models resolve real-world github issues?, 2024."},{"key":"e_1_3_2_2_18_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Jimenez Carlos E","year":"2024","unstructured":"Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R Narasimhan. SWE-bench: Can language models resolve real-world github issues? In The Twelfth International Conference on Learning Representations, 2024."},{"key":"e_1_3_2_2_19_1","volume-title":"Search-r1: Training llms to reason and leverage search engines with reinforcement learning. arXiv preprint arXiv:2503.09516","author":"Jin Bowen","year":"2025","unstructured":"Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan Arik, Dong Wang, Hamed Zamani, and Jiawei Han. Search-r1: Training llms to reason and leverage search engines with reinforcement learning. arXiv preprint arXiv:2503.09516, 2025."},{"key":"e_1_3_2_2_20_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361, 2020."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1925805.1925817"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/359511.359522"},{"key":"e_1_3_2_2_23_1","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Lingam Vijay","year":"2025","unstructured":"Vijay Lingam, Sujay Sanghavi, Sayan Ghosh, Linbo Liu, Jun Huan, Anoop Deoras, Gaurav Gupta, and Behrooz Omidvar-Tehrani. Enhancing language model agents using diversity of thoughts. The Thirteenth International Conference on Learning Representations, 2025."},{"key":"e_1_3_2_2_24_1","volume-title":"Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437","author":"Liu Aixin","year":"2024","unstructured":"Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, et al. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437, 2024."},{"key":"e_1_3_2_2_25_1","first-page":"36","article-title":"Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation","author":"Liu Jiawei","year":"2024","unstructured":"Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang, and Lingming Zhang. Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_26_1","volume-title":"Large language model-based agents for software engineering: A survey. arXiv preprint arXiv:2409.02977","author":"Liu Junwei","year":"2024","unstructured":"Junwei Liu, Kaixin Wang, Yixuan Chen, Xin Peng, Zhenpeng Chen, Lingming Zhang, and Yiling Lou. Large language model-based agents for software engineering: A survey. arXiv preprint arXiv:2409.02977, 2024."},{"key":"e_1_3_2_2_27_1","volume-title":"NeurIPS 2025 Fourth Workshop on Deep Learning for Code","author":"May Victor","year":"2025","unstructured":"Victor May, Diganta Misra, Yanqi Luo, Anjali Sridhar, Justine Gehring, and Silvio Soares Ribeiro Junior. Freshbrew: A benchmark for evaluating AI agents on java code migration. In NeurIPS 2025 Fourth Workshop on Deep Learning for Code, 2025."},{"key":"e_1_3_2_2_28_1","volume-title":"How is google using ai for internal code migrations? arXiv preprint arXiv:2501.06972","author":"Nikolov Stoyan","year":"2025","unstructured":"Stoyan Nikolov, Daniele Codecasa, Anna Sjovall, Maxim Tabachnyk, Satish Chandra, Siddharth Taneja, and Celal Ziftci. How is google using ai for internal code migrations? arXiv preprint arXiv:2501.06972, 2025."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650896"},{"key":"e_1_3_2_2_30_1","volume-title":"Woo Jung Kim, Anoop Deoras, Giovanni Zappella, and Laurent Callot. Swe-polybench: A multi-language benchmark for repository level evaluation of coding agents","author":"Rashid Muhammad Shihab","year":"2025","unstructured":"Muhammad Shihab Rashid, Christian Bock, Yuan Zhuang, Alexander Buchholz, Tim Esler, Simon Valentin, Luca Franceschi, Martin Wistuba, Prabhu Teja Sivaprasad, Woo Jung Kim, Anoop Deoras, Giovanni Zappella, and Laurent Callot. Swe-polybench: A multi-language benchmark for repository level evaluation of coding agents, 2025."},{"key":"e_1_3_2_2_31_1","article-title":"An empirical evaluation of using large language models for automated unit test generation","author":"Sch\u00e4fer Max","year":"2023","unstructured":"Max Sch\u00e4fer, Sarah Nadi, Aryaz Eghbali, and Frank Tip. An empirical evaluation of using large language models for automated unit test generation. IEEE Transactions on Software Engineering, 2023.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_2_2_32_1","volume-title":"Syzygy: Dual code-test c to (safe) rust translation using llms and dynamic analysis","author":"Shetty Manish","year":"2024","unstructured":"Manish Shetty, Naman Jain, Adwait Godbole, Sanjit A. Seshia, and Koushik Sen. Syzygy: Dual code-test c to (safe) rust translation using llms and dynamic analysis, 2024."},{"key":"e_1_3_2_2_33_1","first-page":"36","article-title":"Language agents with verbal reinforcement learning","author":"Shinn Noah","year":"2024","unstructured":"Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_34_1","volume-title":"Software development life cycle perspective: A survey of benchmarks for code large language models and agents","author":"Wang Kaixin","year":"2025","unstructured":"Kaixin Wang, Tianlin Li, Xiaoyu Zhang, Chong Wang, Weisong Sun, Yang Liu, and Bin Shi. Software development life cycle perspective: A survey of benchmarks for code large language models and agents, 2025."},{"key":"e_1_3_2_2_35_1","volume-title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","author":"Wang Xingyao","year":"2024","unstructured":"Xingyao Wang, Boxuan Li, Yufan Song, Frank F. Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H. Tran, Fuqiang Li, Ren Ma, Mingzhang Zheng, Bill Qian, Yanjun Shao, Niklas Muennighoff, Yizhe Zhang, Binyuan Hui, Junyang Lin, Robert Brennan, Hao Peng, Heng Ji, and Graham Neubig. OpenHands: An Open Platform for AI Software Developers as Generalist Agents, 2024."},{"key":"e_1_3_2_2_36_1","volume-title":"Repotransbench: A real-world benchmark for repository-level code translation","author":"Wang Yanli","year":"2024","unstructured":"Yanli Wang, Yanlin Wang, Suiquan Wang, Daya Guo, Jiachi Chen, John Grundy, Xilin Liu, Yuchi Ma, Mingzhi Mao, Hongyu Zhang, and Zibin Zheng. Repotransbench: A real-world benchmark for repository-level code translation, 2024."},{"key":"e_1_3_2_2_37_1","volume-title":"Emergent abilities of large language models. arXiv preprint arXiv:2206.07682","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, et al. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682, 2022."},{"key":"e_1_3_2_2_38_1","volume-title":"Agentless: Demystifying llm-based software engineering agents. arXiv preprint arXiv:2407.01489","author":"Xia Chunqiu Steven","year":"2024","unstructured":"Chunqiu Steven Xia, Yinlin Deng, Soren Dunn, and Lingming Zhang. Agentless: Demystifying llm-based software engineering agents. arXiv preprint arXiv:2407.01489, 2024."},{"key":"e_1_3_2_2_39_1","volume-title":"Live-swe-agent: Can software engineering agents self-evolve on the fly? arXiv preprint arXiv:2511.13646","author":"Xia Chunqiu Steven","year":"2025","unstructured":"Chunqiu Steven Xia, Zhe Wang, Yan Yang, Yuxiang Wei, and Lingming Zhang. Live-swe-agent: Can software engineering agents self-evolve on the fly? arXiv preprint arXiv:2511.13646, 2025."},{"key":"e_1_3_2_2_40_1","volume-title":"Qwen3 technical report. arXiv preprint arXiv:2505.09388","author":"Yang An","year":"2025","unstructured":"An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. Qwen3 technical report. arXiv preprint arXiv:2505.09388, 2025."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1601"},{"key":"e_1_3_2_2_42_1","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 R Narasimhan, and Yuan Cao. React: Synergizing reasoning and acting in language models. In The eleventh international conference on learning representations, 2022."},{"key":"e_1_3_2_2_43_1","volume-title":"Debunc: mitigating hallucinations in large language model agent communication with uncertainty estimations. arXiv preprint arXiv:2407.06426","author":"Yoffe Luke","year":"2024","unstructured":"Luke Yoffe, Alfonso Amayuelas, and William Yang Wang. Debunc: mitigating hallucinations in large language model agent communication with uncertainty estimations. arXiv preprint arXiv:2407.06426, 2024."},{"key":"e_1_3_2_2_44_1","volume-title":"Swe-bench-java: A github issue resolving benchmark for java","author":"Zan Daoguang","year":"2024","unstructured":"Daoguang Zan, Zhirong Huang, Ailun Yu, Shaoxin Lin, Yifan Shi, Wei Liu, Dong Chen, Zongshuai Qi, Hao Yu, Lei Yu, Dezhi Ran, Muhan Zeng, Bo Shen, Pan Bian, Guangtai Liang, Bei Guan, Pengjie Huang, Tao Xie, Yongji Wang, and Qianxiang Wang. Swe-bench-java: A github issue resolving benchmark for java, 2024."},{"key":"e_1_3_2_2_45_1","volume-title":"Glm-5: from vibe coding to agentic engineering. arXiv preprint arXiv:2602.15763","author":"Zeng Aohan","year":"2026","unstructured":"Aohan Zeng, Xin Lv, Zhenyu Hou, Zhengxiao Du, Qinkai Zheng, Bin Chen, Da Yin, Chendi Ge, Chenghua Huang, Chengxing Xie, et al. Glm-5: from vibe coding to agentic engineering. arXiv preprint arXiv:2602.15763, 2026."},{"key":"e_1_3_2_2_46_1","volume-title":"validated code translation of entire projects using large language models","author":"Zhang Hanliang","year":"2024","unstructured":"Hanliang Zhang, Cristina David, Meng Wang, Brandon Paulsen, and Daniel Kroening. Scalable, validated code translation of entire projects using large language models, 2024."},{"key":"e_1_3_2_2_47_1","volume-title":"Codeagent: Enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges. arXiv preprint arXiv:2401.07339","author":"Zhang Kechi","year":"2024","unstructured":"Kechi Zhang, Jia Li, Ge Li, Xianjie Shi, and Zhi Jin. Codeagent: Enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges. arXiv preprint arXiv:2401.07339, 2024."},{"key":"e_1_3_2_2_48_1","volume-title":"et al. Agent-as-a-judge: Evaluate agents with agents. arXiv preprint arXiv:2410.10934","author":"Zhuge Mingchen","year":"2024","unstructured":"Mingchen Zhuge, Changsheng Zhao, Dylan Ashley, Wenyi Wang, Dmitrii Khizbullin, Yunyang Xiong, Zechun Liu, Ernie Chang, Raghuraman Krishnamoorthi, Yuandong Tian, et al. Agent-as-a-judge: Evaluate agents with agents. arXiv preprint arXiv:2410.10934, 2024."}],"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":"2026-08-07T01:25:58Z","timestamp":1786065958000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817526"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":48,"alternative-id":["10.1145\/3770855.3817526","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817526","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"}}]}}