{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T11:01:24Z","timestamp":1785495684946,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"NSERC Discovery Grant","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]},{"name":"University of Manitoba Startup Grant","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3793302.3793619","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:42:54Z","timestamp":1785494574000},"page":"1009-1013","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["How Do Agentic AI Systems Address Performance Optimizations? A BERTopic-Based Analysis of Pull Requests"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1220-560X","authenticated-orcid":false,"given":"Md Nahidul Islam","family":"Opu","sequence":"first","affiliation":[{"name":"Computer Science, University of Manitoba, Winnipeg, Manitoba, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5546-1816","authenticated-orcid":false,"given":"Shahidul","family":"Islam","sequence":"additional","affiliation":[{"name":"Computer Science, University of Manitoba, Winnipeg, Manitoba, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1420-105X","authenticated-orcid":false,"given":"Muhammad","family":"Asaduzzaman","sequence":"additional","affiliation":[{"name":"Computer Science, University of Windsor, Windsor, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2301-6104","authenticated-orcid":false,"given":"Shaiful","family":"Chowdhury","sequence":"additional","affiliation":[{"name":"Computer Science, University of Manitoba, Winnipeg, Manitoba, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Altaf\u00a0Allah Abbassi Leuson Mario\u00a0Pedro Da\u00a0Silva Amin Nikanjam and Foutse Khomh. 2025. A Taxonomy of Inefficiencies in LLM-Generated Python Code. Institute of Electrical and Electronics Engineers.","DOI":"10.1109\/ICSME64153.2025.00043"},{"key":"e_1_3_3_2_3_2","unstructured":"Sandhini Agarwal Lama Ahmad Jason Ai Sam Altman Andy Applebaum Edwin Arbus Rahul\u00a0K Arora Yu Bai Bowen Baker Haiming Bao et\u00a0al. 2025. gpt-oss-120b & gpt-oss-20b model card. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.10925 (2025)."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Simonetta Balsamo Antinisca Di\u00a0Marco Paola Inverardi and Marta Simeoni. 2004. Model-based performance prediction in software development: A survey. IEEE Transactions on Software Engineering 30 5 (2004) 295\u2013310.","DOI":"10.1109\/TSE.2004.9"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2019.00052"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Abdul\u00a0Ali Bangash Hareem Sahar Abram Hindle and Karim Ali. 2020. On the Time-Based Conclusion Stability of Cross-Project Defect Prediction Models. Empirical Softw. Engg. 25 6 (2020).","DOI":"10.1007\/s10664-020-09878-9"},{"key":"e_1_3_3_2_7_2","unstructured":"Mark Chen. 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":"crossref","unstructured":"Shaiful Chowdhury Stephanie Borle Stephen Romansky and Abram Hindle. 2019. GreenScaler: training software energy models with automatic test generation. Empirical software engineering 24 4 (2019) 1649\u20131692.","DOI":"10.1007\/s10664-018-9640-7"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Jacob Cohen. 1960. A coefficient of agreement for nominal scales. Educational and psychological measurement 20 1 (1960) 37\u201346.","DOI":"10.1177\/001316446002000104"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3661167.3661221"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Giuseppe Crupi Rosalia Tufano Alejandro Velasco Antonio Mastropaolo Denys Poshyvanyk and Gabriele Bavota. 2025. On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization. IEEE Transactions on Software Engineering (2025).","DOI":"10.1109\/TSE.2025.3586082"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2016.49"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Patrick Diehl Noujoud Nader Maxim Moraru and Steven\u00a0R Brandt. 2025. LLM benchmarking with LLaMA2: evaluating code development performance across multiple programming languages. Journal of Machine Learning for Modeling and Computing 6 3 (2025).","DOI":"10.1615\/JMachLearnModelComput.2025058957"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Roman Egger and Joanne Yu. 2022. A topic modeling comparison between lda nmf top2vec and bertopic to demystify twitter posts. Frontiers in sociology 7 (2022) 886498.","DOI":"10.3389\/fsoc.2022.886498"},{"key":"e_1_3_3_2_15_2","unstructured":"Omar El-Gayar Mohammad Al-Ramahi Abdullah Wahbeh Tareq Nasralah and Ahmed Elnoshokaty. 2024. A comparative analysis of the interpretability of lda and llm for topic modeling: The case of healthcare apps. (2024)."},{"key":"e_1_3_3_2_16_2","first-page":"376","volume-title":"International Symposium on Artificial Intelligence and Robotics","author":"Gan Lin","year":"2023","unstructured":"Lin Gan, Tao Yang, Yifan Huang, Boxiong Yang, Yami\u00a0Yanwen Luo, Lui Wing\u00a0Cheung Richard, and Dabo Guo. 2023. Experimental comparison of three topic modeling methods with LDA, Top2Vec and BERTopic. In International Symposium on Artificial Intelligence and Robotics. Springer, 376\u2013391."},{"key":"e_1_3_3_2_17_2","unstructured":"Maarten Grootendorst. 2022. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.05794 (2022)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Kilem\u00a0Li Gwet. 2008. Computing inter-rater reliability and its variance in the presence of high agreement. Brit. J. Math. Statist. Psych. 61 1 (2008) 29\u201348.","DOI":"10.1348\/000711006X126600"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/2568225.2568271"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Wannes Janssens Matthias Bogaert and Dirk Van\u00a0den Poel. 2025. A Comparative Analysis of Topic Reduction Techniques for BERTopic. IEEE Access 13 (2025).","DOI":"10.1109\/ACCESS.2025.3638956"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Guoliang Jin Linhai Song Xiaoming Shi Joel Scherpelz and Shan Lu. 2012. Understanding and detecting real-world performance bugs. ACM SIGPLAN Notices 47 6 (2012) 77\u201388.","DOI":"10.1145\/2345156.2254075"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Sathvik Joel Jie Wu and Fatemeh Fard. 2024. A survey on llm-based code generation for low-resource and domain-specific programming languages. ACM Transactions on Software Engineering and Methodology (2024).","DOI":"10.1145\/3770084"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/2597073.2597074"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Takeshi Kojima Shixiang\u00a0Shane Gu Machel Reid Yutaka Matsuo and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems 35 (2022) 22199\u201322213.","DOI":"10.52202\/068431-1613"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.16919272"},{"key":"e_1_3_3_2_26_2","unstructured":"Hao Li Haoxiang Zhang and Ahmed\u00a0E. Hassan. 2025. The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping Software Engineering. arxiv:https:\/\/arXiv.org\/abs\/2507.15003\u00a0[cs.SE]"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE62328.2024.00030"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Leland McInnes John Healy and Steve Astels. 2017. hdbscan: Hierarchical density based clustering. The Journal of Open Source Software 2 11 (mar 2017).","DOI":"10.21105\/joss.00205"},{"key":"e_1_3_3_2_29_2","unstructured":"Leland McInnes John Healy and James Melville. 2018. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1802.03426 (2018)."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2013.6624035"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/Forge66646.2025.00008"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/2684822.2685324"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Peter\u00a0J Rousseeuw. 1987. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of computational and applied mathematics 20 (1987) 53\u201365.","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884829"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/AITest66680.2025.00020"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Gias Uddin Fatima Sabir Yann-Ga\u00ebl Gu\u00e9h\u00e9neuc Omar Alam and Foutse Khomh. 2021. An empirical study of IoT topics in IoT developer discussions on Stack Overflow. Empirical Software Engineering 26 6 (2021) 121.","DOI":"10.1007\/s10664-021-10021-5"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/AIIM64537.2024.10934280"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","unstructured":"Miku Watanabe Hao Li Yutaro Kashiwa Brittany Reid Hajimu Iida and Ahmed\u00a0E. Hassan. 2025. On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub. 10.48550\/ARXIV.2509.14745","DOI":"10.48550\/ARXIV.2509.14745"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","unstructured":"Lirong Yi Gregory Gay and Philipp Leitner. 2025. An Experimental Study of Real-Life LLM-Proposed Performance Improvements. 10.48550\/ARXIV.2510.15494","DOI":"10.48550\/ARXIV.2510.15494"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/1985441.1985457"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2012.6224281"},{"key":"e_1_3_3_2_42_2","unstructured":"Quanjun Zhang Chunrong Fang Yang Xie Yaxin Zhang Yun Yang Weisong Sun Shengcheng Yu and Zhenyu Chen. 2023. A survey on large language models for software engineering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.15223 (2023)."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","unstructured":"Yutong Zhao Lu Xiao and Sunny Wong. 2024. A Platform-Agnostic Framework for Automatically Identifying Performance Issue Reports With Heuristic Linguistic Patterns. IEEE Transactions on Software Engineering 50 7 (July 2024) 1704\u20131725. 10.1109\/TSE.2024.3390623","DOI":"10.1109\/TSE.2024.3390623"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Zibin Zheng Kaiwen Ning Qingyuan Zhong Jiachi Chen Wenqing Chen Lianghong Guo Weicheng Wang and Yanlin Wang. 2025. Towards an understanding of large language models in software engineering tasks. Empirical Software Engineering 30 2 (2025) 50.","DOI":"10.1007\/s10664-024-10602-0"}],"event":{"name":"MSR '26: 23rd International Conference on Mining Software Repositories","location":"Rio de Janeiro Brazil","acronym":"MSR '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 23rd International Conference on Mining Software Repositories"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793302.3793619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:49:20Z","timestamp":1785494960000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793302.3793619"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":43,"alternative-id":["10.1145\/3793302.3793619","10.1145\/3793302"],"URL":"https:\/\/doi.org\/10.1145\/3793302.3793619","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}