{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T16:00:30Z","timestamp":1785340830096,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":46,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3794763.3794828","type":"proceedings-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:18:58Z","timestamp":1785338338000},"page":"415-427","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated Test Suite Enhancement Using Large Language Models with Few-shot Prompting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0067-1477","authenticated-orcid":false,"given":"Alex","family":"Chudic","sequence":"first","affiliation":[{"name":"US Booking Services Ltd. (freetobook), Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4578-1747","authenticated-orcid":false,"given":"G\u00fcl","family":"Calikli","sequence":"additional","affiliation":[{"name":"School of Computing Science, University of Glasgow, Glasgow, Scotland Uk"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,29]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n. d.]. GPT-4 Technical Report."},{"key":"e_1_3_3_2_3_2","unstructured":"[n. d.]. Pynguin\u2014PYthoN General UnIt test geNerator \u2014 pynguin 0.41.0.dev documentation. https:\/\/pynguin.readthedocs.io\/en\/latest\/ Accessed: 2025-01-27."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/2950290.2950324"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Saranya Alagarsamy Chakkrit Tantithamthavorn and Aldeida Aleti. 2024. A3Test: Assertion-Augmented Automated Test case generation. Inf. Softw. Technol. 176 C (Dec. 2024) 15\u00a0pages. 10.1016\/j.infsof.2024.107565","DOI":"10.1016\/j.infsof.2024.107565"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663839"},{"key":"e_1_3_3_2_7_2","unstructured":"Nadia Alshahwan Mark Harman Inna Harper Alexandru Marginean Shubho Sengupta and Eddy Wang. 2024. Assured LLM-Based Software Engineering. http:\/\/arxiv.org\/abs\/2402.04380 arXiv:https:\/\/arXiv.org\/abs\/2402.04380 [cs]."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Anonymous Anonymous. 2025. Automated Test Suite Enhancement Using Large Language Models With Few-shot Prompting. 10.5281\/zenodo.15561007","DOI":"10.5281\/zenodo.15561007"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.2012.6405253"},{"key":"e_1_3_3_2_10_2","series-title":"(NIPS \u201920)","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Brown Tom\u00a0B.","year":"2020","unstructured":"Tom\u00a0B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel\u00a0M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS \u201920). Curran Associates Inc., Red Hook, NY, USA, Article 159, 25\u00a0pages."},{"key":"e_1_3_3_2_11_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique\u00a0Ponde de Oliveira\u00a0Pinto 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\u00a0Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William\u00a0Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew\u00a0N. 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. (2021). arxiv:https:\/\/arXiv.org\/abs\/2107.03374\u00a0[cs.LG]"},{"key":"e_1_3_3_2_12_2","unstructured":"Xueying Du Mingwei Liu Kaixin Wang Hanlin Wang Junwei Liu Yixuan Chen Jiayi Feng Chaofeng Sha Xin Peng and Yiling Lou. 2023. ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation. arxiv:https:\/\/arXiv.org\/abs\/2308.01861\u00a0[cs.CL]"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Jean-Baptiste D\u00f6derlein Mathieu Acher Djamel\u00a0Eddine Khelladi and Benoit Combemale. 2023. Piloting Copilot and Codex: Hot Temperature Cold Prompts or Black Magic?https:\/\/dx.doi.org\/10.2139\/ssrn.4496380","DOI":"10.2139\/ssrn.4496380"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-FoSE59343.2023.00008"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/2025113.2025179"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Mark Harman S.\u00a0Afshin Mansouri and Yuanyuan Zhang. 2012. Search-based software engineering: Trends techniques and applications. ACM Comput. Surv. 45 1 (Dec. 2012) 11:1\u201311:61. 10.1145\/2379776.2379787","DOI":"10.1145\/2379776.2379787"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Mark Harman and Phil McMinn. 2010. A Theoretical and Empirical Study of Search-Based Testing: Local Global and Hybrid Search. IEEE Transactions on Software Engineering 36 2 (March 2010) 226\u2013247. 10.1109\/TSE.2009.71Conference Name: IEEE Transactions on Software Engineering.","DOI":"10.1109\/TSE.2009.71"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/2568225.2568271"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00085"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0943"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00205"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00178"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Shuyin Ouyang Jie\u00a0M. Zhang Mark Harman and Meng Wang. 2025. An Empirical Study of the Non-Determinism of ChatGPT in Code Generation. ACM Trans. Softw. Eng. Methodol. 34 2 Article 42 (Jan. 2025) 28\u00a0pages. 10.1145\/3697010","DOI":"10.1145\/3697010"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"Wendk\u00fbuni Ou\u00e9draogo Kader Kabor\u00e9 Haoye Tian Yewei Song Anil Koyuncu Jacques Klein David Lo and Tegawend\u00e9 Bissyand\u00e9. 2024. Large-scale Independent and Comprehensive study of the power of LLMs for test case generation. 10.48550\/arXiv.2407.00225","DOI":"10.48550\/arXiv.2407.00225"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/1297846.1297902"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2007.37"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME46990.2020.00056"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416622"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Max Sch\u00e4fer Sarah Nadi Aryaz Eghbali and Frank Tip. 2024. An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation. IEEE Transactions on Software Engineering 50 1 (2024) 85\u2013105. 10.1109\/TSE.2023.3334955","DOI":"10.1109\/TSE.2023.3334955"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3661167.3661216"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","unstructured":"Mohammed\u00a0Latif Siddiq Simantika Dristi Joy Saha and Joanna C.\u00a0S. Santos. 2024. The Fault in our Stars: Quality Assessment of Code Generation Benchmarks. 10.48550\/arXiv.2404.10155arXiv:https:\/\/arXiv.org\/abs\/2404.10155.","DOI":"10.48550\/arXiv.2404.10155"},{"key":"e_1_3_3_2_33_2","unstructured":"SonarSource SA. 2025. SonarQube Cloud. https:\/\/sonarcloud.io."},{"key":"e_1_3_3_2_34_2","unstructured":"SonarSource SA. 2025. SonarScanner CLI. https:\/\/github.com\/SonarSource\/sonar-scanner-cli. Version 5.x."},{"key":"e_1_3_3_2_35_2","unstructured":"SonarSource SA. 2025. Squale rating of SonarQube. https:\/\/docs.sonarsource.com\/sonarqube-server\/9.9\/user-guide\/metric-definitions."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","unstructured":"Michele Tufano Dawn Drain Alexey Svyatkovskiy Shao Deng and Neel Sundaresan. 2020. Unit Test Case Generation with Transformers. 10.48550\/arXiv.2009.05617","DOI":"10.48550\/arXiv.2009.05617"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2015.59"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","unstructured":"Junjie Wang Yuchao Huang Chunyang Chen Zhe Liu Song Wang and Qing Wang. 2024. Software Testing With Large Language Models: Survey Landscape and Vision. IEEE Trans. Softw. Eng. 50 4 (April 2024) 911\u2013936. 10.1109\/TSE.2024.3368208","DOI":"10.1109\/TSE.2024.3368208"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"e_1_3_3_2_41_2","series-title":"(PLoP \u201923)","volume-title":"Proceedings of the 30th Conference on Pattern Languages of Programs","author":"White Jules","year":"2023","unstructured":"Jules White, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, and Douglas\u00a0C. Schmidt. 2023. A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT. In Proceedings of the 30th Conference on Pattern Languages of Programs (Monticello, IL, USA) (PLoP \u201923). The Hillside Group, USA, Article 5, 31\u00a0pages."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-55642-5_4"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2013.6693084"},{"key":"e_1_3_3_2_44_2","unstructured":"Zhuokui Xie Yinghao Chen Chen Zhi Shuiguang Deng and Jianwei Yin. 2023. ChatUniTest: a ChatGPT-based automated unit test generation tool. arxiv:https:\/\/arXiv.org\/abs\/2305.04764\u00a0[cs.SE]"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3695529"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","unstructured":"Zhiqiang Yuan Mingwei Liu Shiji Ding Kaixin Wang Yixuan Chen Xin Peng and Yiling Lou. 2024. Evaluating and Improving ChatGPT for Unit Test Generation. Proc. ACM Softw. Eng. 1 FSE Article 76 (July 2024) 24\u00a0pages. 10.1145\/3660783","DOI":"10.1145\/3660783"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","unstructured":"Peng Zhang Yang Wang Xutong Liu Zeyu Lu Yibiao Yang Yanhui Li Lin Chen Ziyuan Wang Chang-Ai Sun Xiao Yu and Yuming Zhou. 2024. Assessing Effectiveness of Test Suites: What Do We Know and What Should We Do? ACM Transactions on Software Engineering and Methodology 33 4 (May 2024) 1\u201332. 10.1145\/3635713","DOI":"10.1145\/3635713"}],"event":{"name":"ICPC '26: 34th IEEE\/ACM International Conference on Program Comprehension","location":"Rio de Janeiro , Brazil","acronym":"ICPC '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2026 34th IEEE\/ACM International Conference on Program Comprehension"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3794763.3794828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:19:24Z","timestamp":1785338364000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3794763.3794828"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":46,"alternative-id":["10.1145\/3794763.3794828","10.1145\/3794763"],"URL":"https:\/\/doi.org\/10.1145\/3794763.3794828","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}