{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T04:23:08Z","timestamp":1787372588727,"version":"build-2736575974"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T00:00:00Z","timestamp":1787356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T00:00:00Z","timestamp":1787356800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91938301"],"award-info":[{"award-number":["91938301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1007\/s10664-026-10940-1","type":"journal-article","created":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T03:25:40Z","timestamp":1787369140000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CGARF: a causality-guided framework for reliable automated program repair"],"prefix":"10.1007","volume":"32","author":[{"given":"Le","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9374-0192","authenticated-orcid":false,"given":"Shaohua","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yancheng","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yawei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianlu","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,22]]},"reference":[{"key":"10940_CR1","unstructured":"Anthropic (2025) Introducing Claude 4. https:\/\/www.anthropic.com\/news\/claude-4"},{"key":"10940_CR2","unstructured":"Antoniades A, Zhang K, Xie Y et al (2025) SWE-Search: enhancing software agents with Monte Carlo tree search and iterative refinement. In: The thirteenth international conference on learning representations (ICLR 2025)"},{"key":"10940_CR3","doi-asserted-by":"crossref","unstructured":"Bouzenia I, Devanbu P, Pradel M. RepairAgent: an autonomous, LLM-based agent for program repair. In: 2025 IEEE\/ACM 47th international conference on software engineering (ICSE). Ottawa, ON, Canada: IEEE, pp 2188\u20132200","DOI":"10.1109\/ICSE55347.2025.00157"},{"key":"10940_CR4","unstructured":"Chen D, Lin S, Zeng M et al (2024) CodeR: issue resolving with multi-agent and task graphs. arXiv"},{"key":"10940_CR5","unstructured":"Claude.ai (2024) Claude 3.5 sonnet. https:\/\/www.anthropic.com\/news\/claude-3-5-sonnet"},{"key":"10940_CR6","unstructured":"Composio (2024) Skills that evolve for your Agents. https:\/\/composio.dev\/"},{"key":"10940_CR7","unstructured":"DeepSeek-AI, Guo D, Yang D et al (2025) DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv"},{"key":"10940_CR8","unstructured":"Ehrlich R, Brown B, Juravsky J et al (2025) CodeMonkeys: scaling test-time compute for software engineering. arXiv"},{"key":"10940_CR9","unstructured":"Gautam A, Kumar K, Jha A et al (2024) SuperCoder2.0: technical report on exploring the feasibility of LLMs as autonomous programmer. arXiv"},{"key":"10940_CR10","doi-asserted-by":"crossref","unstructured":"Ghanbari A, Marcus A (2022) Patch correctness assessment in automated program repair based on the impact of patches on production and test code. In: Proceedings of the 31st ACM SIGSOFT international symposium on software testing and analysis. Virtual South Korea: ACM, pp 654\u2013665","DOI":"10.1145\/3533767.3534368"},{"key":"10940_CR11","unstructured":"Grattafiori A, Dubey A, Jauhri A et al (2024) The Llama 3 herd of models. arXiv"},{"key":"10940_CR12","unstructured":"Hui B, Yang J, Cui Z et al (2024) Qwen2.5-coder technical report. arXiv"},{"key":"10940_CR13","doi-asserted-by":"crossref","unstructured":"Jiang Z, Ren X, Yan M et al (2025) CoSIL: software issue localization via LLM-driven code repository graph searching. arXiv","DOI":"10.1109\/ASE63991.2025.00249"},{"key":"10940_CR14","unstructured":"Jimenez CE, Yang J, Wettig A et al (2024) SWE-bench: can language models resolve real-world GitHub issues?. In: The twelfth international conference on learning representations"},{"key":"10940_CR15","doi-asserted-by":"crossref","unstructured":"Jin M, Shahriar S, Tufano M et al (2023) InferFix: end-to-end program repair with LLMs. In: Proceedings of the 31st ACM joint European software engineering conference and symposium on the foundations of software engineering. San Francisco CA USA: ACM, pp 1646\u20131656","DOI":"10.1145\/3611643.3613892"},{"key":"10940_CR16","unstructured":"Langgraph (2024) Balance agent control with agency. https:\/\/www.langchain.com\/langgraph"},{"key":"10940_CR17","doi-asserted-by":"crossref","unstructured":"Le X B D, Lo D, Le Goues C (2016) Empirical study on synthesis engines for semantics-based program repair. In: 2016 IEEE international conference on software maintenance and evolution (ICSME). Raleigh, NC, USA: IEEE, pp 423\u2013427","DOI":"10.1109\/ICSME.2016.68"},{"key":"10940_CR18","doi-asserted-by":"crossref","unstructured":"Le XBD, ChuD H, Lo D et al (2017) JFIX: semantics-based repair of java programs via symbolic PathFinder. In: Proceedings of the 26th ACM SIGSOFT international symposium on software testing and analysis. Santa Barbara CA USA: ACM, pp 376\u2013379","DOI":"10.1145\/3092703.3098225"},{"issue":"1","key":"10940_CR19","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1109\/TSE.2011.104","volume":"38","author":"C Le Goues","year":"2012","unstructured":"Le Goues C, Nguyen T, Forrest S et al (2012) GenProg: a generic method for automatic software repair. IEEE Trans Softw Eng 38(1):54\u201372","journal-title":"IEEE Trans Softw Eng"},{"key":"10940_CR20","doi-asserted-by":"crossref","unstructured":"Le-Cong T, Luong DM, Le XBD et al (2023) Invalidator: automated patch correctness assessment via semantic and syntactic reasoning. IEEE Trans Softw Eng 1\u201320","DOI":"10.1109\/TSE.2023.3255177"},{"key":"10940_CR21","doi-asserted-by":"publisher","first-page":"51167","DOI":"10.1109\/ACCESS.2022.3164780","volume":"10","author":"D Li","year":"2022","unstructured":"Li D, Wong WE, Jian M et al (2022a) Improving search-based automatic program repair with neural machine translation. IEEE Access 10:51167\u201351175","journal-title":"IEEE Access"},{"key":"10940_CR22","doi-asserted-by":"crossref","unstructured":"Li Y, Wang S, Nguyen TN (2020) DLFix: context-based code transformation learning for automated program repair. In: Proceedings of the ACM\/IEEE 42nd international conference on software engineering. Seoul South Korea: ACM, pp 602\u2013614","DOI":"10.1145\/3377811.3380345"},{"key":"10940_CR23","doi-asserted-by":"crossref","unstructured":"Li Y, Wang S, Nguyen TN (2022b) DEAR: a novel deep learning-based approach for automated program repair. In: Proceedings of the 44th international conference on software engineering. Pittsburgh Pennsylvania: ACM, pp 511\u2013523","DOI":"10.1145\/3510003.3510177"},{"key":"10940_CR24","doi-asserted-by":"publisher","DOI":"10.1145\/3733599","author":"W Luo","year":"2025","unstructured":"Luo W, Keung J, Yang B et al (2025) When fine-tuning LLMs meets data privacy: an empirical study of federated learning in LLM-based program repair. ACM Trans Softw Eng Methodol. https:\/\/doi.org\/10.1145\/3733599","journal-title":"ACM Trans Softw Eng Methodol"},{"key":"10940_CR25","doi-asserted-by":"crossref","unstructured":"Ma Y, Cao R, Cao Y et al (2024) Lingma SWE-GPT: an open development-process-centric language model for automated software improvement. arXiv","DOI":"10.1145\/3728981"},{"key":"10940_CR26","doi-asserted-by":"crossref","unstructured":"Ma Y, Yang Q, Cao R et al (2025) Alibaba LingmaAgent: improving automated issue resolution via comprehensive repository exploration. In: Proceedings of the 33rd ACM international conference on the foundations of software engineering. Clarion hotel Trondheim Trondheim Norway: ACM, pp 238\u2013249","DOI":"10.1145\/3696630.3728549"},{"key":"10940_CR27","doi-asserted-by":"crossref","unstructured":"Mehne B, Yoshida H, Prasad MR et al (2018) Accelerating search-based program repair. In: 2018 IEEE 11th international conference on software testing, verification and validation (ICST). Vasteras: IEEE, pp 227\u2013238","DOI":"10.1109\/ICST.2018.00031"},{"key":"10940_CR28","unstructured":"Meng X, Ma Z, Gao P et al (2024) An empirical study on LLM-based agents for automated bug fixing. arXiv"},{"key":"10940_CR29","doi-asserted-by":"crossref","unstructured":"Molina F, Copia JM, Gorla A (2024) Improving patch correctness analysis via random testing and large language models. In: 2024 IEEE conference on software testing, verification and validation (ICST). Toronto, ON, Canada: IEEE, pp 317\u2013328","DOI":"10.1109\/ICST60714.2024.00036"},{"key":"10940_CR30","doi-asserted-by":"crossref","unstructured":"Nguyen HDT, Qi D, Roychoudhury A et al (2013) SemFix: Program repair via semantic analysis. In: 2013 35th international conference on software engineering (ICSE). San Francisco, CA, USA: IEEE, pp 772\u2013781","DOI":"10.1109\/ICSE.2013.6606623"},{"key":"10940_CR31","unstructured":"OpenAI (2024) Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/"},{"key":"10940_CR32","unstructured":"OpenAI (2025b) Introducing GPT-4.1 in the API. https:\/\/openai.com\/index\/gpt-4-1\/"},{"key":"10940_CR33","unstructured":"OpenAI (2025a) GPT-5 is here. https:\/\/openai.com\/gpt-5\/"},{"key":"10940_CR34","unstructured":"OpenAI, Jaech A, Kalai A et al (2024) OpenAI o1 system card. arXiv"},{"key":"10940_CR35","unstructured":"Ouyang S, Yu W, Ma K et al (2025) Repograph: enhancing AI software engineer- ing with repository-level code graph. In: The thirteenth international conference on learning representations (ICLR 2025)"},{"key":"10940_CR36","unstructured":"Pan J, Wang X, Neubig G et al (2025) Training Software Engineering Agents and Verifiers with SWE-Gym. In: Forty-second international conference on machine learning (ICML 2025)"},{"key":"10940_CR37","doi-asserted-by":"crossref","unstructured":"Parasaram N, Yan H, Yang B et al (2025) The fact selection problem in LLM-based program repair. In: 2025 IEEE\/ACM 47th international conference on software engineering (ICSE). Ottawa, ON, Canada: IEEE, pp 2574\u20132586","DOI":"10.1109\/ICSE55347.2025.00162"},{"key":"10940_CR38","doi-asserted-by":"crossref","unstructured":"Ruan H, Zhang Y, Roychoudhury A (2025) SpecRover: code Intent Extraction via LLMs. In: 2025 IEEE\/ACM 47th international conference on software engineering (ICSE). Ottawa, ON, Canada: IEEE, pp 963\u2013974","DOI":"10.1109\/ICSE55347.2025.00080"},{"issue":"OOPSLA2","key":"10940_CR39","doi-asserted-by":"publisher","first-page":"3342","DOI":"10.1145\/3763170","volume":"9","author":"D Song","year":"2025","unstructured":"Song D, Oh H (2025) Enhancing APR with PRISM: a semantic-based approach to overfitting patch detection. Proc ACM Program Lang 9(OOPSLA2):3342\u20133370","journal-title":"Proc ACM Program Lang"},{"key":"10940_CR40","unstructured":"vLLM (2024) Welcome to vLLM. https:\/\/docs.vllm.ai\/en\/stable\/"},{"key":"10940_CR41","doi-asserted-by":"crossref","unstructured":"Wang Y, Peng Z, Wang Y et al (2025a) MCTS-refined CoT: high-quality fine-tuning data for LLM-based repository issue resolution. arXiv","DOI":"10.1109\/ASE63991.2025.00154"},{"key":"10940_CR42","unstructured":"Wang X, Li B, Song Y et al (2025b) Openhands: an open platform for AI software developers as generalist agents. In: The thirteenth international conference on learning representations (ICLR 2025)"},{"key":"10940_CR43","doi-asserted-by":"crossref","unstructured":"Wei Y, Duchenne O, Copet J et al (2025) SWE-RL: advancing LLM reasoning via reinforcement learning on open software evolution. arXiv","DOI":"10.52202\/085713-2629"},{"key":"10940_CR44","doi-asserted-by":"crossref","unstructured":"Xia CS, Deng Y, Dunn S et al (2024) Agentless: demystifying LLM-based software engineering agents. arXiv","DOI":"10.1145\/3715754"},{"key":"10940_CR45","doi-asserted-by":"crossref","unstructured":"Xie C, Li B, Gao C et al (2025) SWE-fixer: training open-source LLMS for ef- fective and efficient GitHub issue resolution. In: ICLR 2025 third workshop on deep learning for code (DL4C @ ICLR 2025)","DOI":"10.18653\/v1\/2025.findings-acl.62"},{"key":"10940_CR46","doi-asserted-by":"crossref","unstructured":"Xin Q, Reiss SP (2017) Identifying test-suite-overfitted patches through test case generation. In: Proceedings of the 26th ACM SIGSOFT international symposium on software testing and analysis. Santa Barbara CA USA: ACM, pp 226\u2013236","DOI":"10.1145\/3092703.3092718"},{"key":"10940_CR47","doi-asserted-by":"crossref","unstructured":"Xiong Y, Liu X, Zeng M et al (2018) Identifying patch correctness in test-based program repair. In: Proceedings of the 40th international conference on software engineering. Gothenburg Sweden: ACM, pp 789\u2013799","DOI":"10.1145\/3180155.3180182"},{"key":"10940_CR48","doi-asserted-by":"crossref","unstructured":"Yang J, Jimenez CE, Wettig A et al (2024) SWE-agent: agent-computer interfaces enable automated software engineering. In: Globerson A, Mackey L, Belgrave D et al. Advances in neural information processing systems 37 (NeurIPS 2024). Curran Associates, Inc., pp 50528\u201350652","DOI":"10.52202\/079017-1601"},{"key":"10940_CR49","doi-asserted-by":"crossref","unstructured":"Yang J, Lieret K, Jimenez CE et al (2025a) SWE-smith: scaling data for software engineering agents. arXiv","DOI":"10.52202\/085713-3239"},{"key":"10940_CR50","unstructured":"Yang A, Li A, Yang B et al (2025b) Qwen3 technical report. arXiv"},{"issue":"8","key":"10940_CR51","doi-asserted-by":"publisher","first-page":"2920","DOI":"10.1109\/TSE.2021.3071750","volume":"48","author":"H Ye","year":"2022","unstructured":"Ye H, Gu J, Martinez M et al (2022) Automated classification of overfitting patches with statically extracted code features. IEEE Trans Softw Eng 48(8):2920\u20132938","journal-title":"IEEE Trans Softw Eng"},{"key":"10940_CR52","doi-asserted-by":"crossref","unstructured":"Yu Z, Wen M, Guo X et al (2024) Maltracker: a fine-grained NPM malware tracker copiloted by LLM-enhanced dataset. In: Proceedings of the 33rd ACM SIGSOFT international symposium on software testing and analysis. Vienna Austria: ACM, pp 1759\u20131771","DOI":"10.1145\/3650212.3680397"},{"key":"10940_CR53","unstructured":"Yu Z, Zhang H, Zhao Y et al (2025) OrcaLoca: an LLM agent framework for software issue localization. In: Forty-second international conference on machine learning. (ICML 2025)"},{"issue":"2","key":"10940_CR54","first-page":"1","volume":"33","author":"Q Zhang","year":"2024","unstructured":"Zhang Q, Fang C, Ma Y et al (2024b) A survey of learning-based automated program repair. ACM Trans Softw Eng Methodol 33(2):1\u201369","journal-title":"ACM Trans Softw Eng Methodol"},{"key":"10940_CR55","doi-asserted-by":"crossref","unstructured":"Zhang Y, Ruan H, Fan Z et al (2024a) AutoCodeRover: autonomous program improvement. In: Proceedings of the 33rd ACM SIGSOFT international symposium on software testing and analysis. Vienna Austria: ACM, pp 1592\u20131604","DOI":"10.1145\/3650212.3680384"},{"key":"10940_CR56","unstructured":"Zhou X, Xu B, Kim K et al (2023) PatchZero: zero-shot automatic patch correctness assessment. Preprint at https:\/\/arxiv.org\/abs\/2303.00202"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-026-10940-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-026-10940-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-026-10940-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T03:25:46Z","timestamp":1787369146000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-026-10940-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,22]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2027,2]]}},"alternative-id":["10940"],"URL":"https:\/\/doi.org\/10.1007\/s10664-026-10940-1","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,22]]},"assertion":[{"value":"3 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Informed consent","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Shaohua Liu reports financial support was provided by the National Natural Science Foundation of China (Grant No. 91938301) and the Research Project on Postgraduate Education and Teaching Reform of Beijing University of Posts and Telecommunications (Grant No. 2025YY004). Other authors declare no competing interests.","order":4,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":5,"name":"Ethics","label":"Clinical Trial Number","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"27"}}