{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T07:17:37Z","timestamp":1783408657591,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:00:00Z","timestamp":1775952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"NSF","award":["CNS-244271"],"award-info":[{"award-number":["CNS-244271"]}]},{"name":"Open Philanthropy","award":["No award number"],"award-info":[{"award-number":["No award number"]}]},{"name":"OpenAI","award":["No award number"],"award-info":[{"award-number":["No award number"]}]},{"name":"Google DeepMind","award":["No award number"],"award-info":[{"award-number":["No award number"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3786181.3788703","type":"proceedings-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:28:24Z","timestamp":1783405704000},"page":"159-166","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World Repositories"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6274-0085","authenticated-orcid":false,"given":"Chihao","family":"Shen","sequence":"first","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6250-1437","authenticated-orcid":false,"given":"Connor","family":"Dilgren","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7515-5387","authenticated-orcid":false,"given":"Purva","family":"Chiniya","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1147-9701","authenticated-orcid":false,"given":"Luke","family":"Griffith","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1918-782X","authenticated-orcid":false,"given":"Yu","family":"Ding","sequence":"additional","affiliation":[{"name":"Google DeepMind, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2019-5955","authenticated-orcid":false,"given":"Yizheng","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,6]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Anthropic. 2025. Claude Code. https:\/\/www.claude.com\/product\/claude-code"},{"key":"e_1_3_3_2_3_2","unstructured":"Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry Quoc Le et\u00a0al. 2021. Program Synthesis with Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.07732 (2021)."},{"key":"e_1_3_3_2_4_2","unstructured":"Manish Bhatt Sahana Chennabasappa Cyrus Nikolaidis Shengye Wan Ivan Evtimov Dominik Gabi Daniel Song Faizan Ahmad Cornelius Aschermann Lorenzo Fontana et\u00a0al. 2023. Purple llama cyberseceval: A secure coding benchmark for language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.04724 (2023)."},{"key":"e_1_3_3_2_5_2","unstructured":"Egor Bogomolov Aleksandra Eliseeva Timur Galimzyanov Evgeniy Glukhov Anton Shapkin Maria Tigina Yaroslav Golubev Alexander Kovrigin Arie van Deursen Maliheh Izadi et\u00a0al. 2024. Long Code Arena: a Set of Benchmarks for Long-Context Code Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.11612 (2024)."},{"key":"e_1_3_3_2_6_2","unstructured":"Business of Apps. 2025. Microsoft Copilot Revenue and Usage Statistics (2025). https:\/\/www.businessofapps.com\/data\/microsoft-copilot-statistics\/."},{"key":"e_1_3_3_2_7_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde de\u00a0Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman et\u00a0al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2107.03374 (2021)."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3607199.3607242"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025.00038"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2023"},{"key":"e_1_3_3_2_11_2","unstructured":"Eirini Kalliamvakou GitHub Blog. 2022. Research: quantifying GitHub Copilot\u2019s impact on developer productivity and happiness. https:\/\/github.blog\/2022-09-07-research-quantifying-github-copilots-impact-on-developer-productivity-and-happiness\/."},{"key":"e_1_3_3_2_12_2","unstructured":"Yanjun Fu Ethan Baker Yu Ding and Yizheng Chen. 2024. Constrained Decoding for Secure Code Generation. arXiv:https:\/\/arXiv.org\/abs\/2405.00218 (2024)."},{"key":"e_1_3_3_2_13_2","unstructured":"Paul Gauthier. 2023. Aider: AI-assisted coding in your terminal with GPT. https:\/\/aider.chat\/. Accessed: 2025-05-15."},{"key":"e_1_3_3_2_14_2","unstructured":"Alex Gu Baptiste Rozi\u00e8re Hugh Leather Armando Solar-Lezama Gabriel Synnaeve and Sida\u00a0I Wang. 2024. Cruxeval: A benchmark for code reasoning understanding and execution. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.03065 (2024)."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML59370.2024.00040"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3623175"},{"key":"e_1_3_3_2_17_2","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"He Jingxuan","year":"2024","unstructured":"Jingxuan He, Mark Vero, Gabriela Krasnopolska, and Martin Vechev. 2024. Instruction Tuning for Secure Code Generation. In Proceedings of the International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_2_18_2","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","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\u00a0al. 2021. Measuring Coding Challenge Competence With APPS. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_3_2_19_2","unstructured":"Ivan Homoliak Martin Pere\u0161\u00edni Ale\u0161 Smr\u010dka Kamil Malinka and Petr Hanacek. 2024. Enhancing Security of AI-Based Code Synthesis with GitHub Copilot via Cheap and Efficient Prompt-Engineering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.12671 (2024)."},{"key":"e_1_3_3_2_20_2","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence Workshop","author":"Islam Nafis\u00a0Tanveer","year":"2024","unstructured":"Nafis\u00a0Tanveer Islam and Peyman Najafirad. 2024. Code Security Vulnerability Repair Using Reinforcement Learning with Large Language Models. In Proceedings of the AAAI Conference on Artificial Intelligence Workshop."},{"key":"e_1_3_3_2_21_2","unstructured":"Naman Jain King Han Alex Gu Wen-Ding Li Fanjia Yan Tianjun Zhang Sida Wang Armando Solar-Lezama Koushik Sen and Ion Stoica. 2024. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.07974 (2024)."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680371"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Yujia Li David Choi Junyoung Chung Nate Kushman Julian Schrittwieser R\u00e9mi Leblond Tom Eccles James Keeling Felix Gimeno Agustin Dal\u00a0Lago et\u00a0al. 2022. Competition-level code generation with alphacode. Science 378 6624 (2022) 1092\u20131097.","DOI":"10.1126\/science.abq1158"},{"key":"e_1_3_3_2_24_2","unstructured":"Shanchao Liang Yiran Hu Nan Jiang and Lin Tan. 2024. Can Language Models Replace Programmers? REPOCOD Says\u2019 Not Yet\u2019. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.21647 (2024)."},{"key":"e_1_3_3_2_25_2","unstructured":"Jiawei Liu Chunqiu\u00a0Steven Xia Yuyao Wang and Lingming Zhang. 2024. 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)."},{"key":"e_1_3_3_2_26_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Liu Tianyang","year":"2024","unstructured":"Tianyang Liu, Canwen Xu, and Julian McAuley. 2024. RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_2_27_2","unstructured":"Maxim Tabachnyk and Stoyan Nikolov Google Research. 2022. ML-Enhanced Code Completion Improves Developer Productivity. https:\/\/research.google\/blog\/ml-enhanced-code-completion-improves-developer-productivity\/."},{"key":"e_1_3_3_2_28_2","unstructured":"Xiang Mei Pulkit\u00a0Singh Singaria Jordi\u00a0Del Castillo Haoran Xi Abdelouahab Benchikh Tiffany Bao Ruoyu Wang Yan Shoshitaishvili Adam Doup\u00e9 Hammond Pearce and Brendan Dolan-Gavitt. 2024. ARVO: Atlas of Reproducible Vulnerabilities for Open Source Software."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690298"},{"key":"e_1_3_3_2_30_2","volume-title":"The Thirty-Ninth Annual Conference on Neural Information Processing Systems","author":"Nie Yuzhou","year":"2025","unstructured":"Yuzhou Nie, Zhun Wang, Yu Yang, Ruizhe Jiang, Yuheng Tang, Xander Davies, Yarin Gal, Bo Li, Wenbo Guo, and Dawn Song. 2025. SecCodePLT: A Unified Benchmark for Evaluating the Security Risks and Capabilities of Code Agents. In The Thirty-Ninth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833571"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179324"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/LLM4Code66737.2025.00009"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3433210.3437528"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3549035.3561184"},{"key":"e_1_3_3_2_36_2","unstructured":"Mark Vero Niels M\u00fcndler Victor Chibotaru Veselin Raychev Maximilian Baader Nikola Jovanovi\u0107 Jingxuan He and Martin Vechev. 2025. BaxBench: Can LLMs Generate Correct and Secure Backends?arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.11844 (2025)."},{"key":"e_1_3_3_2_37_2","unstructured":"Jiexin Wang Liuwen Cao Xitong Luo Zhiping Zhou Jiayuan Xie Adam Jatowt and Yi Cai. 2023. Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.16263 (2023)."},{"key":"e_1_3_3_2_38_2","unstructured":"Xingyao Wang Boxuan Li Yufan Song Frank\u00a0F. Xu Xiangru Tang Mingchen Zhuge Jiayi Pan Yueqi Song Bowen Li Jaskirat Singh Hoang\u00a0H. 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. 2024. OpenHands: An Open Platform for AI Software Developers as Generalist Agents. arxiv:https:\/\/arXiv.org\/abs\/2407.16741\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2407.16741"},{"key":"e_1_3_3_2_39_2","unstructured":"Colin White Samuel Dooley Manley Roberts Arka Pal Ben Feuer Siddhartha Jain Ravid Shwartz-Ziv Neel Jain Khalid Saifullah Siddartha Naidu et\u00a0al. 2024. Livebench: A challenging contamination-free llm benchmark. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.19314 (2024)."},{"key":"e_1_3_3_2_40_2","unstructured":"Chunqiu\u00a0Steven Xia Yinlin Deng and Lingming Zhang. 2024. Top Leaderboard Ranking= Top Coding Proficiency Always? EvoEval: Evolving Coding Benchmarks via LLM. Proceedings of the First Conference on Language Modeling (2024)."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30185"}],"event":{"name":"LLM4Code '26: 3rd International Workshop on Large Language Models For Code","location":"Rio de Janeiro Brazil","acronym":"LLM4Code '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the 3rd International Workshop on Large Language Models For Code"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786181.3788703","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786181.3788703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:40:15Z","timestamp":1783406415000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786181.3788703"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":40,"alternative-id":["10.1145\/3786181.3788703","10.1145\/3786181"],"URL":"https:\/\/doi.org\/10.1145\/3786181.3788703","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}