{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:50:27Z","timestamp":1764996627716,"version":"build-2065373602"},"reference-count":62,"publisher":"Association for Computing Machinery (ACM)","issue":"OOPSLA2","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402214,62232014"],"award-info":[{"award-number":["62402214,62232014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20241194"],"award-info":[{"award-number":["BK20241194"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025T180420"],"award-info":[{"award-number":["2025T180420"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZB20250386"],"award-info":[{"award-number":["GZB20250386"]}]},{"name":"Hong Kong Polytechnic University Fund","award":["P0051205,P0051074"],"award-info":[{"award-number":["P0051205,P0051074"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Program. Lang."],"published-print":{"date-parts":[[2025,10,9]]},"abstract":"<jats:p>Large-language models (LLMs) have been leveraged to enhance the capability of automated program repair techniques in recent research.  \nWhile existing LLM-based program repair techniques compared favorably to other techniques based on heuristics, constraint-solving, and learning in producing high-quality patches,  \nthey mainly target bugs that can be corrected by changing a single faulty method,  \nwhich greatly limits the effectiveness of such techniques in repairing bugs that demand patches spanning across multiple methods.  \nIn this work, we propose the PReMM technique to effectively propose patches changing multiple methods.  \nPReMM builds on three core component techniques:  \nthe faulty method clustering technique to partition the faulty methods into clusters based on the dependence relationship among them,  \nenabling a divide-and-conquer strategy for the repairing task;  \nthe fault context extraction technique to gather extra information about the fault context which can be utilized to better guide the diagnosis of the fault and the generation of correct patches;  \nthe dual-agent-based patch generation technique that employs two LLM-based agents with different roles to analyze the fault more precisely and generate patches of higher-quality.  \nWe have implemented the PReMM technique into a tool with the same name and applied the tool to repair real-world bugs from datasets Defects4J V1.2 and V2.0.  \nPReMM produced correct patches for 307 bugs in total.  \nCompared with ThinkRepair, the state-of-the-art LLM-based program repair technique,  \nPReMM correctly repaired 102 more bugs, achieving an improvement of 49.8%.<\/jats:p>","DOI":"10.1145\/3763097","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T08:51:31Z","timestamp":1759999891000},"page":"1316-1344","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["PReMM: LLM-Based Program Repair for Multi-method Bugs via Divide and Conquer"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4163-8994","authenticated-orcid":false,"given":"Linna","family":"Xie","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3849-3416","authenticated-orcid":false,"given":"Zhong","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6065-6958","authenticated-orcid":false,"given":"Yu","family":"Pei","sequence":"additional","affiliation":[{"name":"Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6737-9953","authenticated-orcid":false,"given":"Zhongzhen","family":"Wen","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0145-615X","authenticated-orcid":false,"given":"Kui","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0104-2731","authenticated-orcid":false,"given":"Tian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3090-9568","authenticated-orcid":false,"given":"Xuandong","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"2025. Interpret Odds Ratio - R Method. https:\/\/easystats.github.io\/effectsize\/reference\/interpret_oddsratio.html Accessed: 2025-07."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3495883"},{"key":"e_1_2_1_5_1","unstructured":"chatgptendpoint. 2023. Introducing ChatGPT and Whisper APIs. https:\/\/openai.com\/blog\/introducing-chatgpt-and-whisper-apis"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1080\/03610911003650383"},{"key":"e_1_2_1_7_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. 2021. Evaluating Large Language Models Trained on Code. arxiv:2107.03374. arxiv:2107.03374"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295184"},{"key":"e_1_2_1_9_1","volume-title":"Statistical Power Analysis for the Behavioral Sciences","author":"Cohen J.","unstructured":"J. Cohen. 2013. Statistical Power Analysis for the Behavioral Sciences. Taylor & Francis. isbn:978-1-134-74277-6"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2593735.2593740"},{"key":"e_1_2_1_11_1","unstructured":"Dawn Drain Colin B. Clement Guillermo Serrato and Neel Sundaresan. 2021. DeepDebug: Fixing Python Bugs Using Stack Traces Backtranslation and Code Skeletons. arxiv:2105.09352. arxiv:2105.09352"},{"key":"e_1_2_1_12_1","volume-title":"Luke Zettlemoyer, and Mike Lewis.","author":"Fried Daniel","year":"2023","unstructured":"Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen tau Yih, Luke Zettlemoyer, and Mike Lewis. 2023. InCoder: A Generative Model for Code Infilling and Synthesis. arxiv:2204.05999. arxiv:2204.05999"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330559"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/506315.506316"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3264600"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00111"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00107"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2610384.2628055"},{"key":"e_1_2_1_19_1","volume-title":"Patch Generation with Language Models: Feasibility and Scaling Behavior. In Deep Learning for Code Workshop. https:\/\/openreview.net\/forum?id=rHlzJh_b1-5","author":"Kolak Sophia D","year":"2022","unstructured":"Sophia D Kolak, Ruben Martins, Claire Le Goues, and Vincent Josua Hellendoorn. 2022. Patch Generation with Language Models: Feasibility and Scaling Behavior. In Deep Learning for Code Workshop. https:\/\/openreview.net\/forum?id=rHlzJh_b1-5"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3106309"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2016.76"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2011.104"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2011.104"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-NIER66352.2025.00024"},{"key":"e_1_2_1_25_1","unstructured":"R. Li L. B. Allal Y. Zi N. Muennighoff D. Kocetkov C. Mou M. Marone C. Akiki J. Li J. Chim Q. Liu E. Zheltonozhskii T. Y. Zhuo T. Wang O. Dehaene M. Davaadorj J. Lamy-Poirier J. Monteiro O. Shliazhko N. Gontier N. Meade A. Randy M-H. Yee L. K. Umapathi J. Zhu B. Lipkin M. Oblokulov Z. Wang R. Murthy J. Stillerman S. S. Patel D. Abulkhanov M. Zocca M. Dey Z. Zhang N. Fahmy U. Bhattacharyya S. Gunasekar W. Yu S. Singh S. Luccioni P. Villegas M. Kunakov F. Zhdanov M. Romero T. Lee N. Timor J. Ding C. Schlesinger H. Schoelkopf J. Ebert T. Dao M. Mishra A. Gu J. Robinson C. J. Anderson B. Dolan-Gavitt D. Contractor S. Reddy D. Fried D. Bahdanau Y. Jernite C. M. Ferrandis S. Hughes T. Wolf A. Guha L. von Werra and H. de Vries. [n.d.]. StarCoder: May the Source be With You!. Transactions on machine learning research https:\/\/par.nsf.gov\/biblio\/10483982"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380345"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377812.3390896"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510177"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680381"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","unstructured":"LinnaX7. 2025. LinnaX7\/PReMM: PReMM: LLM-Based Program Repair for Multi-Method Bugs via Divide and Conquer. https:\/\/doi.org\/10.5281\/zenodo.16927561 10.5281\/zenodo.16927561","DOI":"10.5281\/zenodo.16927561"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2019.8667970"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330577"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2786805.2786811"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3395363.3397369"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2931037.2948705"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02295996"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884807"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00127"},{"key":"e_1_2_1_41_1","volume-title":"https:\/\/rank.opencompass.org.cn\/home","author":"Rank OpenCompass","year":"2024","unstructured":"OpenCompass. 2024. OpenCompass Rank. (2024). https:\/\/rank.opencompass.org.cn\/home"},{"key":"e_1_2_1_42_1","first-page":"9781713871088","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems (NIPS \u201922)","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. In Proceedings of the 36th International Conference on Neural Information Processing Systems (NIPS \u201922). Curran Associates Inc., Red Hook, NY, USA. Article 2011, 15 pages. isbn:9781713871088"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524459.3527351"},{"key":"e_1_2_1_44_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2411.13323"},{"key":"e_1_2_1_46_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arxiv:1707.06347. arxiv:1707.06347"},{"key":"e_1_2_1_47_1","unstructured":"John Schulman Barret Zoph Jacob Hilton Christina Kim Jacob Menick Jiayi Weng Juan Felipe Ceron Uribe Liam Fedus Luke Metz Michael Pokorny Rapha Gontijo Lopes Shengjia Zhao Arun Vijayvergiya Eric Sigler Adam Perelman Chelsea Voss Mike Heaton Joel Parish Dave Cummings Rajeev Nayak Valerie Balcom David Schnurr Tomer Kaftan Chris Hallacy Nicholas Turley Noah Deutsch Vik Goel Jonathan Ward Aris Konstantinidis Wojciech Zaremba Long Ouyang Leonard Bogdonoff Joshua Gross David Medina Sarah Yoo Teddy Lee Ryan Lowe Dan Mossing Joost Huizinga Roger Jiang Carroll Wainwright Diogo Almeida Steph Lin Marvin Zhang Kai Xiao Katarina Slama Steven Bills Alex Gray Jan Leike Jakub Pachocki Phil Tillet Shantanu Jain Greg Brockman and Nick Ryder. 2022. ChatGPT: Optimizing Language Models for Dialogue. https:\/\/openai.com\/blog\/chatgpt\/"},{"key":"e_1_2_1_48_1","volume-title":"GitBug-Java: A Reproducible Benchmark of Recent Java Bugs. In 2024 IEEE\/ACM 21st International Conference on Mining Software Repositories (MSR). 118\u2013122","author":"Silva Andr\u00e9","year":"2024","unstructured":"Andr\u00e9 Silva, Nuno Saavedra, and Martin Monperrus. 2024. GitBug-Java: A Reproducible Benchmark of Recent Java Bugs. In 2024 IEEE\/ACM 21st International Conference on Mining Software Repositories (MSR). 118\u2013122."},{"key":"e_1_2_1_49_1","unstructured":"Qwen Team. 2024. Qwen2.5: A Party of Foundation Models. https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616271"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180233"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00129"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549101"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680323"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556893"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556926"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510222"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680359"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00063"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468544"},{"key":"e_1_2_1_62_1","unstructured":"Daniel M. Ziegler Nisan Stiennon Jeffrey Wu Tom B. Brown Alec Radford Dario Amodei Paul Christiano and Geoffrey Irving. 2020. Fine-Tuning Language Models from Human Preferences. arxiv:1909.08593. arxiv:1909.08593"}],"container-title":["Proceedings of the ACM on Programming Languages"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3763097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:40:55Z","timestamp":1760031655000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3763097"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":62,"journal-issue":{"issue":"OOPSLA2","published-print":{"date-parts":[[2025,10,9]]}},"alternative-id":["10.1145\/3763097"],"URL":"https:\/\/doi.org\/10.1145\/3763097","relation":{},"ISSN":["2475-1421"],"issn-type":[{"value":"2475-1421","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,9]]},"assertion":[{"value":"2025-03-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-12","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}