{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T20:44:29Z","timestamp":1792701869838,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"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":[[2026,7,5]]},"DOI":"10.1145\/3805760.3814924","type":"proceedings-article","created":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T08:46:13Z","timestamp":1783241173000},"page":"332-339","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["SWE-Bench+: Enhanced LLM Coding Benchmark"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1937-3733","authenticated-orcid":false,"given":"Haoran","family":"Xue","sequence":"first","affiliation":[{"name":"York University, Department of Electrical Engineering and Computer Science, North York, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8856-9685","authenticated-orcid":false,"given":"Reem","family":"Aleithan","sequence":"additional","affiliation":[{"name":"York University, Department of Electrical Engineering and Computer Science, North York, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4357-5719","authenticated-orcid":false,"given":"Nafid","family":"Enan","sequence":"additional","affiliation":[{"name":"York University, Department of Electrical Engineering and Computer Science, North York, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1376-095X","authenticated-orcid":false,"given":"Gias","family":"Uddin","sequence":"additional","affiliation":[{"name":"York University, Department of Electrical Engineering and Computer Science, North York, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0617-2877","authenticated-orcid":false,"given":"Song","family":"Wang","sequence":"additional","affiliation":[{"name":"York University, Department of Electrical Engineering and Computer Science, North York, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Kamel Alrashedy and Ahmed Binjahlan. 2024. Language Models are Better Bug Detector Through Code-Pair Classification. arXiv:2311.07957 [cs.SE] https: \/\/arxiv.org\/abs\/2311.07957"},{"key":"e_1_3_2_1_2_1","unstructured":"Antonis Antoniades Albert \u00d6rwall Kexun Zhang Yuxi Xie Anirudh Goyal and William Wang. 2025. SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement. arXiv:2410.20285 [cs.AI] https: \/\/arxiv.org\/abs\/2410.20285"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10371-6"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2406.01304"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.03374"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00022"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109291"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.02014"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025.00038"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.716"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639219"},{"key":"e_1_3_2_1_12_1","volume-title":"Jimenez et al","author":"Carlos","year":"2024","unstructured":"Carlos E. Jimenez et al. 2024. SWE-bench: Can Language Models Resolve Real- World GitHub Issues? arXiv:2310.06770 [cs.CL] https:\/\/arxiv.org\/abs\/2310.06770"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dibe.2024"},{"key":"e_1_3_2_1_14_1","volume-title":"Software Engineering: An Example from ChatGPT and Automated Program Repair. arXiv:2310.08879 [cs.SE] https:\/\/arxiv.org\/abs\/2310.08879","author":"Quanjun Zhang","year":"2024","unstructured":"Quanjun Zhang et al. 2024. A Critical Review of Large Language Model on Software Engineering: An Example from ChatGPT and Automated Program Repair. arXiv:2310.08879 [cs.SE] https:\/\/arxiv.org\/abs\/2310.08879"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3747588"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715765"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.01114"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1837"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650203.3663334"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","unstructured":"Shanchao Liang Spandan Garg and Roshanak Moghaddam. 2025. The SWE- Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason. doi:10. 48550\/arXiv.2506.12286 10.48550\/arXiv.2506.12286","DOI":"10.48550\/arXiv.2506.12286"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/AITest62860.2024.00019"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715727"},{"key":"e_1_3_2_1_23_1","volume-title":"Quantifying contamination in evaluating code generation capabilities of language models. arXiv preprint arXiv:2403.04811","author":"Riddell Martin","year":"2024","unstructured":"Martin Riddell, Ansong Ni, and Arman Cohan. 2024. Quantifying contamination in evaluating code generation capabilities of language models. arXiv preprint arXiv:2403.04811 (2024)."},{"key":"e_1_3_2_1_24_1","unstructured":"Ricardo La Rosa Corey Hulse and Bangdi Liu. 2024. Can Github issues be solved with Tree Of Thoughts? arXiv:2405.13057 [cs.SE] https:\/\/arxiv.org\/abs\/2405. 13057"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643769"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2013.11"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549145"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","unstructured":"Jiho Shin Reem Aleithan Hadi Hemmati and Song Wang. 2024. Retrieval- Augmented Test Generation: How Far Are We? doi:10.48550\/arXiv.2409.12682 10.48550\/arXiv.2409.12682","DOI":"10.48550\/arXiv.2409.12682"},{"key":"e_1_3_2_1_29_1","unstructured":"5 Team and Aohan Zeng et al. 2025. GLM-4.5: Agentic Reasoning and Coding (ARC) Foundation Models. arXiv:2508.06471 [cs.CL] https:\/\/arxiv.org\/abs\/2508. 06471"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2507.23370"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2406.19314"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715754"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.301"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680328"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1601"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623316"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 42nd International Conference on Machine Learning","author":"Yu Zhongming","year":"2025","unstructured":"Zhongming et al. Yu. 2025. OrcaLoca: an LLM agent framework for software issue localization. In Proceedings of the 42nd International Conference on Machine Learning (Vancouver, Canada) (ICML'25). JMLR.org, Article 2939, 21 pages."},{"key":"e_1_3_2_1_40_1","unstructured":"Daoguang Zan Zhirong Huang and Ailun Yu et al. 2024. SWE-bench-java: A GitHub Issue Resolving Benchmark for Java. arXiv:2408.14354 [cs.SE] https: \/\/arxiv.org\/abs\/2408.14354"},{"key":"e_1_3_2_1_41_1","unstructured":"Kexun Zhang Weiran Yao and Zuxin Liu et al. 2024. Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents. arXiv:2408.07060 [cs.SE] https:\/\/arxiv.org\/abs\/2408.07060"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680384"}],"event":{"name":"AIware '26: 3rd ACM International Conference on AI-Powered Software","location":"Montreal QC Canada","acronym":"AIware '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 3rd ACM International Conference on AI-Powered Software"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805760.3814924","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T08:47:57Z","timestamp":1783241277000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805760.3814924"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":42,"alternative-id":["10.1145\/3805760.3814924","10.1145\/3805760"],"URL":"https:\/\/doi.org\/10.1145\/3805760.3814924","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}