{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T02:36:05Z","timestamp":1784342165324,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761035","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T23:59:18Z","timestamp":1762559958000},"page":"4368-4378","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1738-8335","authenticated-orcid":false,"given":"Yicong","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0368-6866","authenticated-orcid":false,"given":"Shisong","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6870-5922","authenticated-orcid":false,"given":"Jiacheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2355-288X","authenticated-orcid":false,"given":"Zhixu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China and School of Smart Governance, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","first-page":"76930","article-title":"Many-shot in-context learning","volume":"37","author":"Agarwal Rishabh","year":"2024","unstructured":"Rishabh Agarwal, Avi Singh, Lei Zhang, Bernd Bohnet, Luis Rosias, Stephanie Chan, Biao Zhang, Ankesh Anand, Zaheer Abbas, Azade Nova, et al. 2024. Many-shot in-context learning. Advances in Neural Information Processing Systems 37 (2024), 76930--76966.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","volume-title":"What learning algorithm is in-context learning? investigations with linear models. arXiv preprint arXiv:2211.15661","author":"Aky\u00fcrek Ekin","year":"2022","unstructured":"Ekin Aky\u00fcrek, Dale Schuurmans, Jacob Andreas, Tengyu Ma, and Denny Zhou. 2022. What learning algorithm is in-context learning? investigations with linear models. arXiv preprint arXiv:2211.15661 (2022)."},{"key":"e_1_3_2_1_4_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_5_1","volume-title":"Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, et al.","author":"Burns Collin","year":"2023","unstructured":"Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, et al. 2023. Weak-to-strong generalization: Eliciting strong capabilities with weak supervision. arXiv preprint arXiv:2312.09390 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2020.3020502"},{"key":"e_1_3_2_1_7_1","volume-title":"Jun Shern Chan, Samuel R Bowman, Kyunghyun Cho, and Ethan Perez.","author":"Chen Angelica","year":"2023","unstructured":"Angelica Chen, J\u00e9r\u00e9my Scheurer, Tomasz Korbak, Jon Ander Campos, Jun Shern Chan, Samuel R Bowman, Kyunghyun Cho, and Ethan Perez. 2023. Improving code generation by training with natural language feedback. arXiv preprint arXiv:2303.16749 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216","author":"Chen Jianlv","year":"2024","unstructured":"Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_10_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. 2023. Teaching large language models to self-debug. arXiv preprint arXiv:2304.05128 (2023)."},{"key":"e_1_3_2_1_11_1","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research 24, 240 (2023), 1--113.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_12_1","volume-title":"Incoder: A generative model for code infilling and synthesis. arXiv preprint arXiv:2204.05999","author":"Fried Daniel","year":"2022","unstructured":"Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen-tau Yih, Luke Zettlemoyer, and Mike Lewis. 2022. Incoder: A generative model for code infilling and synthesis. arXiv preprint arXiv:2204.05999 (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"Coda: An end-to-end neural program decompiler. Advances in Neural Information Processing Systems 32","author":"Fu Cheng","year":"2019","unstructured":"Cheng Fu, Huili Chen, Haolan Liu, Xinyun Chen, Yuandong Tian, Farinaz Koushanfar, and Jishen Zhao. 2019. Coda: An end-to-end neural program decompiler. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_14_1","volume-title":"OASIS: Order-Augmented Strategy for Improved Code Search. arXiv preprint arXiv:2503.08161","author":"Gao Zuchen","year":"2025","unstructured":"Zuchen Gao, Zizheng Zhan, Xianming Li, Erxin Yu, Haotian Zhang, Bin Chen, Yuqun Zhang, and Jing Li. 2025. OASIS: Order-Augmented Strategy for Improved Code Search. arXiv preprint arXiv:2503.08161 (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330559"},{"key":"e_1_3_2_1_16_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_17_1","first-page":"17685","article-title":"Synthesize, execute and debug: Learning to repair for neural program synthesis","volume":"33","author":"Gupta Kavi","year":"2020","unstructured":"Kavi Gupta, Peter Ebert Christensen, Xinyun Chen, and Dawn Song. 2020. Synthesize, execute and debug: Learning to repair for neural program synthesis. Advances in Neural Information Processing Systems 33 (2020), 17685--17695.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","unstructured":"Dan Hendrycks Steven Basart Saurav Kadavath Mantas Mazeika Akul Arora Ethan Guo Collin Burns Samir Puranik Horace He Dawn Song et al. 2021. Measuring coding challenge competence with apps. arXiv preprint arXiv:2105.09938 (2021)."},{"key":"e_1_3_2_1_19_1","unstructured":"Yaojie Hu Xingjian Shi Qiang Zhou and Lee Pike. 2022. Fix bugs with transformer through a neural-symbolic edit grammar. arXiv preprint arXiv:2204.06643 (2022)"},{"key":"e_1_3_2_1_20_1","volume-title":"A survey on automated program repair techniques. arXiv preprint arXiv:2303.18184","author":"Huang Kai","year":"2023","unstructured":"Kai Huang, Zhengzi Xu, Su Yang, Hongyu Sun, Xuejun Li, Zheng Yan, and Yuqing Zhang. 2023. A survey on automated program repair techniques. arXiv preprint arXiv:2303.18184 (2023)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3213846.3213871"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00107"},{"key":"e_1_3_2_1_23_1","first-page":"21314","article-title":"Coderl: Mastering code generation through pretrained models and deep reinforcement learning","volume":"35","author":"Le Hung","year":"2022","unstructured":"Hung Le, Yue Wang, Akhilesh Deepak Gotmare, Silvio Savarese, and Steven Chu Hong Hoi. 2022. Coderl: Mastering code generation through pretrained models and deep reinforcement learning. Advances in Neural Information Processing Systems 35 (2022), 21314--21328.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","volume-title":"Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al.","author":"Li Raymond","year":"2023","unstructured":"Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al. 2023. Starcoder: may the source be with you! arXiv preprint arXiv:2305.06161 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"Agustin Dal Lago, et al","author":"Li Yujia","year":"2022","unstructured":"Yujia Li, David Choi, Junyoung Chung, Nate Kushman, Julian Schrittwieser, R\u00e9mi Leblond, Tom Eccles, James Keeling, Felix Gimeno, Agustin Dal Lago, et al. 2022. Competition-level code generation with alphacode. Science 378, 6624 (2022), 1092--1097."},{"key":"e_1_3_2_1_26_1","unstructured":"Aixin Liu Bei Feng Bin Wang Bingxuan Wang Bo Liu Chenggang Zhao Chengqi Dengr Chong Ruan Damai Dai Daya Guo et al. 2024. Deepseek-v2: A strong economical and efficient mixture-of-experts language model. arXiv preprint arXiv:2405.04434 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 583--592","author":"Fei","unstructured":"Fei Liu et al. 2020. Learning to summarize from human feedback. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 583--592."},{"key":"e_1_3_2_1_28_1","volume-title":"An empirical study of catastrophic forgetting in large language models during continual fine-tuning. arXiv preprint arXiv:2308.08747","author":"Luo Yun","year":"2023","unstructured":"Yun Luo, Zhen Yang, Fandong Meng, Yafu Li, Jie Zhou, and Yue Zhang. 2023. An empirical study of catastrophic forgetting in large language models during continual fine-tuning. arXiv preprint arXiv:2308.08747 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"AuPair: Golden Example Pairs for Code Repair. arXiv preprint arXiv:2502.18487","author":"Mavalankar Aditi","year":"2025","unstructured":"Aditi Mavalankar, Hassan Mansoor, Zita Marinho, Masha Samsikova, and Tom Schaul. 2025. AuPair: Golden Example Pairs for Code Repair. arXiv preprint arXiv:2502.18487 (2025)."},{"key":"e_1_3_2_1_30_1","volume-title":"Chenglong Wang, Jianfeng Gao, and Armando Solar-Lezama.","author":"Olausson Theo X","year":"2023","unstructured":"Theo X Olausson, Jeevana Priya Inala, Chenglong Wang, Jianfeng Gao, and Armando Solar-Lezama. 2023. Is self-repair a silver bullet for code generation? arXiv preprint arXiv:2306.09896 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3608132"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.432"},{"key":"e_1_3_2_1_33_1","volume-title":"Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al.","author":"Roziere Baptiste","year":"2023","unstructured":"Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al. 2023. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"From code to correctness: Closing the last mile of code generation with hierarchical debugging. arXiv preprint arXiv:2410.01215","author":"Shi Yuling","year":"2024","unstructured":"Yuling Shi, Songsong Wang, Chengcheng Wan, and Xiaodong Gu. 2024. From code to correctness: Closing the last mile of code generation with hierarchical debugging. arXiv preprint arXiv:2410.01215 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Reflexion: Language agents with verbal reinforcement learning","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Federico Cassano, Beck Labash, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning, 2023. URL https:\/\/arxiv.org\/abs\/2303.11366 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Cassidy Hardin, Surya Bhupatiraju, L\u00e9onard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ram\u00e9, et al.","author":"Team Gemma","year":"2024","unstructured":"Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, L\u00e9onard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ram\u00e9, et al. 2024. Gemma 2: Improving open language models at a practical size. arXiv preprint arXiv:2408.00118 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"International Conference on Machine Learning. PMLR, 35151--35174","author":"Oswald Johannes Von","year":"2023","unstructured":"Johannes Von Oswald, Eyvind Niklasson, Ettore Randazzo, Jo\u00e3o Sacramento, Alexander Mordvintsev, Andrey Zhmoginov, and Max Vladymyrov. 2023. Transformers learn in-context by gradient descent. In International Conference on Machine Learning. PMLR, 35151--35174."},{"key":"e_1_3_2_1_38_1","volume-title":"Aakanksha Chowdhery, and Denny Zhou.","author":"Wang Xuezhi","year":"2022","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)."},{"key":"e_1_3_2_1_39_1","volume-title":"Self-instruct: Aligning language models with self-generated instructions. arXiv preprint arXiv:2212.10560","author":"Wang Yizhong","year":"2022","unstructured":"Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2022. Self-instruct: Aligning language models with self-generated instructions. arXiv preprint arXiv:2212.10560 (2022)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556893"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680359"},{"key":"e_1_3_2_1_42_1","volume-title":"Self-edit: Fault-aware code editor","author":"Zhang Kechi","year":"2023","unstructured":"Kechi Zhang, Zhuo Li, Jia Li, Ge Li, and Zhi Jin. 2023. Self-edit: Fault-aware code editor for code generation. arXiv preprint arXiv:2305.04087 (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3631974","article-title":"A survey of learning-based automated program repair","volume":"33","author":"Zhang Quanjun","year":"2023","unstructured":"Quanjun Zhang, Chunrong Fang, Yuxiang Ma, Weisong Sun, and Zhenyu Chen. 2023. A survey of learning-based automated program repair. ACM Transactions on Software Engineering and Methodology 33, 2 (2023), 1--69.","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"e_1_3_2_1_44_1","volume-title":"Debug like a human: A large language model debugger via verifying runtime execution step-by-step. arXiv preprint arXiv:2402.16906","author":"Zhong Li","year":"2024","unstructured":"Li Zhong, Zilong Wang, and Jingbo Shang. 2024. Debug like a human: A large language model debugger via verifying runtime execution step-by-step. arXiv preprint arXiv:2402.16906 (2024)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3545258.3545268"},{"key":"e_1_3_2_1_46_1","unstructured":"Qihao Zhu Daya Guo Zhihong Shao Dejian Yang Peiyi Wang Runxin Xu Y Wu Yukun Li Huazuo Gao Shirong Ma et al. 2024. Deepseek-coder-v2: Breaking the barrier of closed-source models in code intelligence. arXiv preprint arXiv:2406.11931 (2024)."}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:26:47Z","timestamp":1765499207000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761035"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":46,"alternative-id":["10.1145\/3746252.3761035","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761035","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}