{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T21:05:47Z","timestamp":1793826347787,"version":"4.6.1"},"reference-count":70,"publisher":"Association for Computing Machinery (ACM)","issue":"FSE","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFE0202900"],"award-info":[{"award-number":["2024YFE0202900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202040"],"award-info":[{"award-number":["62202040"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ITEA projects GreenCode","award":["23016"],"award-info":[{"award-number":["23016"]}]},{"name":"GENIUS","award":["23026"],"award-info":[{"award-number":["23026"]}]},{"name":"Luxembourg National Research Fund (FNR) through the CORE project MiCE","award":["C23\/IS\/18182513"],"award-info":[{"award-number":["C23\/IS\/18182513"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>LLM-based mutation testing is a promising testing technology, but existing approaches typically rely on a fixed set of mutants as few-shot examples or none at all. This can result in generic low-quality mutants, missed context-specific mutation patterns, substantial numbers of redundant and non-compilable mutants, and limited semantic similarity to real bugs. To overcome these limitations, we introduce SMART (Semantic Mutation with Adaptive Retrieval and Tuning). SMART integrates retrieval-augmented generation (RAG) on a vectorized dataset of real-world bugs, focused code chunking, and supervised fine-tuning using mutants coupled with real-world bugs. We conducted an extensive empirical study of SMART using 1,991 real-world Java bugs from the Defects4J and ConDefects datasets, comparing SMART to the state-of-the-art LLM-based approaches, LLMut and LLMorpheus. \nThe results reveal that SMART substantially improves mutation validity, effectiveness, and efficiency (even enabling 7B-scale models to match or even surpass large models like GPT-4o). We also demonstrate that SMART significantly improves downstream software engineering applications, including test case prioritization and fault localization. More specifically, SMART improves validity (weighted average generation rate) from 42.89% to 65.6%. It raises the non-duplicate rate from 87.38% to 95.62%, and the compilable rate from 88.85% to 90.21%. In terms of effectiveness, it achieves a real bug detection rate of 92.61% (vs. 57.86% for LLMut) and improves the average Ochiai coefficient from 25.61% to 38.44%. For fault localization, SMART ranks 64 more bugs as Top-1 under MUSE and 57 more under Metallaxis.<\/jats:p>","DOI":"10.1145\/3808156","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:06:14Z","timestamp":1782839174000},"page":"3368-3391","source":"Crossref","is-referenced-by-count":3,"title":["Boosting LLMs for Mutation Generation"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7944-9182","authenticated-orcid":false,"given":"Bo","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"},{"name":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7193-0087","authenticated-orcid":false,"given":"Ming","family":"Deng","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6283-1291","authenticated-orcid":false,"given":"Mingda","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6100-8127","authenticated-orcid":false,"given":"Chengran","family":"Yang","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5143-3645","authenticated-orcid":false,"given":"Youfang","family":"Lin","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5864-4488","authenticated-orcid":false,"given":"Mark","family":"Harman","sequence":"additional","affiliation":[{"name":"University College London, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1852-2547","authenticated-orcid":false,"given":"Mike","family":"Papadakis","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Luxembourg, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0481-7264","authenticated-orcid":false,"given":"Jie M.","family":"Zhang","sequence":"additional","affiliation":[{"name":"King's College London, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et al. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] doi:10.48550\/arXiv.2303.08774 10.48550\/arXiv.2303.08774"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1062455.1062530"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00625279"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.03374"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/APSEC66846.2025.00013"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-4127-5"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2931037.2948707"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2024.107468"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/226295.226313"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643756"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSTW55395.2022.00039"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/C-M.1978.218136"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623343"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/N19-1423"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2006.92"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3660791"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et al. 2024. The Llama 3 Herd of Models. arXiv:2407.21783 [cs.AI] doi:10.48550\/arXiv.2407.21783 10.48550\/arXiv.2407.21783","DOI":"10.48550\/arXiv.2407.21783"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.1977.231145"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2019.00021"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696630.3728544"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2902362"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","unstructured":"Ali Reza Ibrahimzada Yang Chen Ryan Rong and Reyhaneh Jabbarvand. 2025. Challenging Bug Prediction and Repair Models with Synthetic Bugs. (2025) 133-144. doi:10.1109\/SCAM67354.2025.00021 10.1109\/SCAM67354.2025.00021","DOI":"10.1109\/SCAM67354.2025.00021"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAIC-PART.2008.18"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2010.62"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3239235.3240500"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2610384.2628055"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2635868.2635929"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2011.6100138"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510187"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510417"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et al. 2021. Retrieval-augmented generation for knowledge-intensive NLP tasks. arXiv:2005.11401 [cs.CL] doi:10.48550\/arXiv.2005.11401 10.48550\/arXiv.2005.11401","DOI":"10.48550\/arXiv.2005.11401"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE.2015.7381798"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","unstructured":"Yu-Seung Ma Jeff Offutt and Yong-Rae Kwon. 2006. MuJava: a mutation system for Java. (2006) 827-830. doi:10.1145\/ 1134285.1134425 10.1145\/1134285.1134425","DOI":"10.1145\/1134285.1134425"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2014.28"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2001420.2001461"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2023.3277564"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/bs.adcom.2018.03.015"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1002\/stvr.1509"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3107634"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.1999.792604"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/32.962562"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.12950"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1002\/stvr.1695"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3725528"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556949"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680395"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2025.3562025"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2019.00046"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3805038"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","unstructured":"Bo Wang Ming Deng Mingda Chen Chengran Yang Youfang Lin Mark Harman Mike Papadakis and M. Jie Zhang. 2025. The Artifact of TyMut. doi:10.5281\/zenodo.19509595 10.5281\/zenodo.19509595","DOI":"10.5281\/zenodo.19509595"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678827"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1002\/stvr.1905"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3092703.3092714"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3771933"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","unstructured":"Guoqing Wang Chengran Yang Xiaoxuan Zhou Zeyu Sun Bo Wang David Lo and Dan Hao. 2026. TestDecision: Sequential Test Suite Generation via Greedy Optimization and Reinforcement Learning. arXiv:2604.01799 [cs.SE] doi:10.48550\/arXiv.2604.01799 10.48550\/arXiv.2604.01799","DOI":"10.48550\/arXiv.2604.01799"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.68"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3695501"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3209590"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663815"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00012"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3359969"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv:2505.09388 [cs.CL] doi:10.48550\/arXiv.2505.09388 10.48550\/arXiv.2505.09388","DOI":"10.48550\/arXiv.2505.09388"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1002\/stvr.430"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2025.3573751"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3695491"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","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:2406.11931 [cs.SE] doi:10.48550\/arXiv.2406.11931 10.48550\/arXiv.2406.11931","DOI":"10.48550\/arXiv.2406.11931"},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2892102"}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3808156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:20:37Z","timestamp":1782843637000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3808156"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":70,"journal-issue":{"issue":"FSE","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3808156"],"URL":"https:\/\/doi.org\/10.1145\/3808156","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}