Neuro Symbolic Automated Program Repair: A Systematic Review of  LLM-Based and Symbolic Techniques

Ashif Anwar

Authors

Ashif Anwar Wolters Kluwer United States Inc https://orcid.org/0009-0002-1009-3864

Keywords:

Neuro-symbolic automated program repair, Large language models, Static analysis, Software bug fixing

Abstract

Automated program repair (APR) involves creating patches for software defects with minimal human intervention. Classical template-based and search-based methods are not scalable, whereas large language models (LLMs) provide good generalization but are affected by hallucinations and have weak formal guarantees. Neuro-symbolic program repair (NSPR) integrates LLMs with static analysis, SMT solving, and symbolic techniques to trade off coverage, correctness, and interpretability. We performed a systematic review of APR and NSPR systems using the PRISMA 2020 guidelines. Predefined queries in IEEE Xplore, ACM Digital Library, Scopus, Web of Science, arXiv, and Google Scholar were used to search between January 2012 and January 2026. Architectures, benchmarks, outcomes, and deployments. Two reviewers screened the records against established predetermined eligibility criteria. A total of 70 pieces of academic primary empirical research on APR/NSPR and eight (8) pieces of industrial/production deployment reports were included, and 78 papers were ultimately included in the qualitative synthesis. Our results indicate that, compared to neural or symbolic systems, NSPR systems also tend to report higher correct repair rates and lower hallucination rates. It can be deployed in CI/CD pipelines, security patches, and large-scale open-source repositories. Nevertheless, standard benchmarks and transparent assessments may still be required to perform powerful comparisons and ensure reproducibility.

Downloads

Download data is not yet available.

References

Campos, Viola, et al. “Exploring Generalizable Automated Program Repair with Large Language Models.” ArXiv.org, 3 June 2025, https://doi.org/10.48550/arxiv.2506.03283. Accessed 25 Feb. 2026.

E. Dehaerne, B. Dey, S. Halder, S. De Gendt, and W. Meert, “Code Generation Using Machine Learning: A Systematic Review,” IEEE Access, vol. 10, pp. 82434–82455, 2022, doi: 10.1109/ACCESS.2022.3196347.

I. Bouzenia, P. Devanbu, and M. Pradel, “RepairAgent: An Autonomous, LLM-Based Agent for Program Repair,” in 2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE), IEEE, Apr. 2025, pp. 2188–2200. doi: 10.1109/ICSE55347.2025.00157.

Chandra Maddila, “Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback,” ArXiv, 2025.

B. ; C. Z. ; L. F. ; L. X. B. D. ; Z. L. ; B. T. F. ; L. Y. ; T. H. Yang, “A Survey of LLM Based Automated Program Repair,” ArXiv, 2025.

B. Liang, Y. Wang, and C. Tong, “AI Reasoning in Deep Learning Era: From Symbolic AI to Neural–Symbolic AI,” Mathematics, vol. 13, no. 11, p. 1707, May 2025, doi: 10.3390/math13111707.

F. Zubair, M. Al-Hitmi, and C. Catal, “The use of large language models for program repair,” Comput. Stand. Interfaces, vol. 93, p. 103951, Apr. 2025, doi: 10.1016/j.csi.2024.103951.

Bui, Quang-Cuong, et al. “APR4Vul: An Empirical Study of Automatic Program Repair Techniques on Real-World Java Vulnerabilities.” Empirical Software Engineering, vol. 29, no. 1, 6 Dec. 2023, https://doi.org/10.1007/s10664-023-10415-7. Accessed 20 Feb. 2024.

Md. S. H. Shaon and M. S. Akter, “Modern Approaches to Software Vulnerability Detection: A Survey of Machine Learning, Deep Learning, and Large Language Models,” Electronics (Basel)., vol. 14, no. 22, p. 4449, Nov. 2025, doi: 10.3390/electronics14224449.

C. Woesle, L. Fischer-Brandies, and R. Buettner, “A Systematic Literature Review of Hallucinations in Large Language Models,” IEEE Access, vol. 13, pp. 148231–148253, 2025, doi: 10.1109/ACCESS.2025.3601206.

S. Banitaan, M. Daoud, H. Alquran, and M. Akour, “Foundation Models in Software Engineering: A Taxonomy, Systematic Review, and In-Depth Analysis of Testing Support,” Information, vol. 17, no. 1, p. 73, Jan. 2026, doi: 10.3390/info17010073.

R. Just, D. Jalali, and M. D. Ernst, “Defects4J: a database of existing faults to enable controlled testing studies for Java programs,” in Proceedings of the 2014 International Symposium on Software Testing and Analysis, New York, NY, USA: ACM, Jul. 2014, pp. 437–440. doi: 10.1145/2610384.2628055.

D. Lin, J. Koppel, A. Chen, and A. Solar-Lezama, “QuixBugs: a multi-lingual program repair benchmark set based on the quixey challenge,” in Proceedings Companion of the 2017 ACM SIGPLAN International Conference on Systems, Programming, Languages, and Applications: Software for Humanity, New York, NY, USA: ACM, Oct. 2017, pp. 55–56. doi: 10.1145/3135932.3135941.

Dikici, Sena, and Turgay Tugay Bilgin. “Advancements in Automated Program Repair: A Comprehensive Review.” Knowledge and Information Systems, 6 Mar. 2025, https://doi.org/10.1007/s10115-025-02383-9.

F. Corradini, M. Leonesi, and M. Piangerelli, “State of the Art and Future Directions of Small Language Models: A Systematic Review,” Big Data and Cognitive Computing, vol. 9, no. 7, p. 189, Jul. 2025, doi: 10.3390/bdcc9070189.

A. Faraji and N. Pombo, “AI-Driven Software Test Automation: An AI4SE-Oriented Survey of Techniques, Tools, and Challenges,” IEEE Access, vol. 13, pp. 183296–183313, 2025, doi: 10.1109/ACCESS.2025.3623944.

T. Saber and N. Tao, “Review and Mapping of Search-Based Approaches for Program Synthesis,” Information, vol. 16, no. 5, p. 401, May 2025, doi: 10.3390/info16050401.

M. Alharbi and M. Alshayeb, “Automatic Code Generation Techniques: A Systematic Literature Review,” Automated Software Engineering, vol. 33, no. 1, p. 4, May 2026, doi: 10.1007/s10515-025-00551-3.

L. B. Germano, R. R. Goldschmidt, R. C. Noya, and J. C. Duarte, “A Systematic Review on Detection, Repair, and Explanation of Vulnerabilities in Source Code Using Large Language Models,” IEEE Access, vol. 13, pp. 192263–192293, 2025, doi: 10.1109/ACCESS.2025.3631363.

B. C. , & R. W. Colelough, “Neuro-Symbolic AI in 2024: A Systematic Review,” ArXiv (Cornell University), 2025.

S. Parihar, Z. Dadachanji, P. K. Singh, R. Das, A. Karkare, and A. Bhattacharya, “Automatic Grading and Feedback using Program Repair for Introductory Programming Courses,” in Proceedings of the 2017 ACM Conference on Innovation and Technology in Computer Science Education, New York, NY, USA: ACM, Jun. 2017, pp. 92–97. doi: 10.1145/3059009.3059026.

J. C. Paiva, J. P. Leal, and Á. Figueira, “Incremental Repair Feedback on Automated Assessment of Programming Assignments,” Electronics (Basel)., vol. 14, no. 4, p. 819, Feb. 2025, doi: 10.3390/electronics14040819.

D. Choi and E. Lee, “Automated Feedback Generation for Programming Assignments Through Diversification,” in 2025 IEEE/ACM 37th International Conference on Software Engineering Education and Training (CSEE&T), IEEE, Apr. 2025, pp. 230–241. doi: 10.1109/CSEET66350.2025.00030.

Y. Yang et al., “Patch Generation in APR: A Survey from the Perspectives of Utilizing LLMs and Using APR-Specific Information,” ACM Transactions on Software Engineering and Methodology, Aug. 2025, doi: 10.1145/3764584.

C. Geethal, M. Böhme, and V.-T. Pham, “Human-in-the-Loop Automatic Program Repair,” IEEE Transactions on Software Engineering, vol. 49, no. 10, pp. 4526–4549, Oct. 2023, doi: 10.1109/TSE.2023.3305052.

K. Etemadi, N. Tarighat, S. Yadav, M. Martinez, and M. Monperrus, “Estimating the potential of program repair search spaces with commit analysis,” Journal of Systems and Software, vol. 188, p. 111263, Jun. 2022, doi: 10.1016/j.jss.2022.111263.

F. N. Meem, J. Smith, and B. Johnson, “Exploring Experiences with Automated Program Repair in Practice,” in Proceedings of the IEEE/ACM 46th International Conference on Software Engineering, New York, NY, USA: ACM, Apr. 2024, pp. 1–11. doi: 10.1145/3597503.3639182.

R. Majumdar and J.-F. Raskin, “Symbolic Model Checking in Non-Boolean Domains,” in Handbook of Model Checking, Cham: Springer International Publishing, 2018, pp. 1111–1147. doi: 10.1007/978-3-319-10575-8_31.

S. Hao, X. Shi, H. Liu, Y. Yin, and X. Chen, “Template-guided interpretable reasoning with execution feedback for LLM-based program repair,” Inf. Softw. Technol., vol. 193, p. 108058, May 2026, doi: 10.1016/j.infsof.2026.108058.

F. Li, J. Jiang, J. Sun, and H. Zhang, “Hybrid Automated Program Repair by Combining Large Language Models and Program Analysis,” ACM Transactions on Software Engineering and Methodology, vol. 34, no. 7, pp. 1–28, Sep. 2025, doi: 10.1145/3715004.

N. Jiang, K. Liu, T. Lutellier, and L. Tan, “Impact of Code Language Models on Automated Program Repair,” in 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), IEEE, May 2023, pp. 1430–1442. doi: 10.1109/ICSE48619.2023.00125.

W. Zhong, C. Li, J. Ge, and B. Luo, “Neural Program Repair : Systems, Challenges and Solutions,” in Proceedings of the 13th Asia-Pacific Symposium on Internetware, New York, NY, USA: ACM, Jun. 2022, pp. 96–106. doi: 10.1145/3545258.3545268.

C. Ni, X. Yin, X. Li, X. Xu, and Z. Yu, “Abundant Modalities Offer More Nutrients: Multi-Modal-Based Function-Level Vulnerability Detection,” ACM Transactions on Software Engineering and Methodology, vol. 35, no. 2, pp. 1–31, Feb. 2026, doi: 10.1145/3731557.

R. and P. S. and K. A. and S. S. Gupta, “DeepFix: fixing common C language errors by deep learning,” AAAI’17: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pp. 1345–1351, 2017.

T. Le-Cong, D. Nguyen, B. Le, and T. Murray, “Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing,” ACM Transactions on Software Engineering and Methodology, vol. 34, no. 7, pp. 1–44, Sep. 2025, doi: 10.1145/3716167.

A. T. C. C. D. C. Chandra, “Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback,” ArXiv, 2025.

M. M. Ruslan Idelfonso Magana Vsevolodovna, “Enhancing Large Language Models through Neuro-Symbolic Integration and Ontological Reasoning,” ArXiv, 2025.

F. L. X. Q. H. Z. J. J. Jiajun Sun, “Empirical Evaluation of Large Language Models in Automated Program Repair,” ArXiv, 2025.

Y. Chen et al., “When Large Language Models Confront Repository-Level Automatic Program Repair: How Well They Done?,” in Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings, New York, NY, USA: ACM, Apr. 2024, pp. 459–471. doi: 10.1145/3639478.3647633.

W. , J. C. , S. K. , S. M. , J. P. , T. P. , F. S. David, “User-Centric Deployment of Automated Program Repair at Bloomberg,” ArXiv, 2023.

A. Marginean et al., “SapFix: Automated End-to-End Repair at Scale,” in 2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP), IEEE, May 2019, pp. 269–278. doi: 10.1109/ICSE-SEIP.2019.00039.

H. Eladawy, C. Le Goues, and Y. Brun, “Automated Program Repair, What Is It Good For? Not Absolutely Nothing!,” in Proceedings of the IEEE/ACM 46th International Conference on Software Engineering, New York, NY, USA: ACM, Apr. 2024, pp. 1–13. doi: 10.1145/3597503.3639095.

K. Noda, Y. Nemoto, K. Hotta, H. Tanida, and S. Kikuchi, “Experience Report: How Effective is Automated Program Repair for Industrial Software?,” in 2020 IEEE 27th International Conference on Software Analysis, Evolution and Reengineering (SANER), IEEE, Feb. 2020, pp. 612–616. doi: 10.1109/SANER48275.2020.9054829.

K. Liu et al., “On the efficiency of test suite based program repair,” in Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering, New York, NY, USA: ACM, Jun. 2020, pp. 615–627. doi: 10.1145/3377811.3380338.

D. Yang, Y. Qi, and X. Mao, “An Empirical Study on the Usage of Fault Localization in Automated Program Repair,” in 2017 IEEE International Conference on Software Maintenance and Evolution (ICSME), IEEE, Sep. 2017, pp. 504–508. doi: 10.1109/ICSME.2017.37.

Q. Zhang, C. Fang, T. Zhang, B. Yu, W. Sun, and Z. Chen, “Gamma: Revisiting Template-Based Automated Program Repair Via Mask Prediction,” in 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE), IEEE, Sep. 2023, pp. 535–547. doi: 10.1109/ASE56229.2023.00063.

C. Le Goues, T. Nguyen, S. Forrest, and W. Weimer, “GenProg: A Generic Method for Automatic Software Repair,” IEEE Transactions on Software Engineering, vol. 38, no. 1, pp. 54–72, Jan. 2012, doi: 10.1109/TSE.2011.104.

F. Long and M. Rinard, “An analysis of the search spaces for generate and validate patch generation systems,” in Proceedings of the 38th International Conference on Software Engineering, New York, NY, USA: ACM, May 2016, pp. 702–713. doi: 10.1145/2884781.2884872.

D. Kim, J. Nam, J. Song, and S. Kim, “Automatic patch generation learned from human-written patches,” in 2013 35th International Conference on Software Engineering (ICSE), IEEE, May 2013, pp. 802–811. doi: 10.1109/ICSE.2013.6606626.

Y. Wang, W. Wang, S. Joty, and S. C. H. Hoi, “CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation,” in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Stroudsburg, PA, USA: Association for Computational Linguistics, 2021, pp. 8696–8708. doi: 10.18653/v1/2021.emnlp-main.685.

Y. Tang, “Large Language Models Meet Automated Program Repair: Innovations, Challenges and Solutions,” Applied and Computational Engineering, vol. 117, no. 1, pp. 22–30, Dec. 2024, doi: 10.54254/2755-2721/2024.18303.

S. Mechtaev, J. Yi, and A. Roychoudhury, “Angelix,” in Proceedings of the 38th International Conference on Software Engineering, New York, NY, USA: ACM, May 2016, pp. 691–701. doi: 10.1145/2884781.2884807.

Q. Zhu et al., “A syntax-guided edit decoder for neural program repair,” in Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, New York, NY, USA: ACM, Aug. 2021, pp. 341–353. doi: 10.1145/3468264.3468544.

M. Martinez and M. Monperrus, “ASTOR: a program repair library for Java (demo),” in Proceedings of the 25th International Symposium on Software Testing and Analysis, New York, NY, USA: ACM, Jul. 2016, pp. 441–444. doi: 10.1145/2931037.2948705.

Y. Qi, X. Mao, Y. Lei, Z. Dai, and C. Wang, “The strength of random search on automated program repair,” in Proceedings of the 36th International Conference on Software Engineering, New York, NY, USA: ACM, May 2014, pp. 254–265. doi: 10.1145/2568225.2568254.

Y. Xiong et al., “Precise Condition Synthesis for Program Repair,” in 2017 IEEE/ACM 39th International Conference on Software Engineering (ICSE), IEEE, May 2017, pp. 416–426. doi: 10.1109/ICSE.2017.45.

Z. Fan, X. Gao, M. Mirchev, A. Roychoudhury, and S. H. Tan, “Automated Repair of Programs from Large Language Models,” in 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), IEEE, May 2023, pp. 1469–1481. doi: 10.1109/ICSE48619.2023.00128.

X.-B. D. Le, D.-H. Chu, D. Lo, C. Le Goues, and W. Visser, “S3: syntax- and semantic-guided repair synthesis via programming by examples,” in Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering, New York, NY, USA: ACM, Aug. 2017, pp. 593–604. doi: 10.1145/3106237.3106309.

Q. Zhang, C. Fang, Y. Ma, W. Sun, and Z. Chen, “A Survey of Learning-based Automated Program Repair,” ACM Transactions on Software Engineering and Methodology, vol. 33, no. 2, pp. 1–69, Feb. 2024, doi: 10.1145/3631974.

Y. , Z. C. , F. L. , X. B. Boyang, “A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications,” ArXiv, 2025.

L. Chen, Y. Pei, and C. A. Furia, “Contract-based program repair without the contracts,” in 2017 32nd IEEE/ACM International Conference on Automated Software Engineering (ASE), IEEE, Oct. 2017, pp. 637–647. doi: 10.1109/ASE.2017.8115674.

Y. W. D. C. T. W. R. S. C. C. J. Rohan Mukherjee, “Neural Program Generation Modulo Static Analysis,” ArXiv, 2021.

F. Long and M. Rinard, “Staged program repair with condition synthesis,” in Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering, New York, NY, USA: ACM, Aug. 2015, pp. 166–178. doi: 10.1145/2786805.2786811.

C. Le Goues et al., “The ManyBugs and IntroClass Benchmarks for Automated Repair of C Programs,” IEEE Transactions on Software Engineering, vol. 41, no. 12, pp. 1236–1256, Dec. 2015, doi: 10.1109/TSE.2015.2454513.

L. Gazzola, D. Micucci, and L. Mariani, “Automatic Software Repair: A Survey,” IEEE Transactions on Software Engineering, vol. 45, no. 1, pp. 34–67, Jan. 2019, doi: 10.1109/TSE.2017.2755013.

C. Le Goues, M. Pradel, and A. Roychoudhury, “Automated program repair,” Commun. ACM, vol. 62, no. 12, pp. 56–65, Nov. 2019, doi: 10.1145/3318162.

M. Monperrus, “Automatic Software Repair,” ACM Comput. Surv., vol. 51, no. 1, pp. 1–24, Jan. 2019, doi: 10.1145/3105906.

M. Bohme, V.-T. Pham, and A. Roychoudhury, “Coverage-Based Greybox Fuzzing as Markov Chain,” IEEE Transactions on Software Engineering, vol. 45, no. 5, pp. 489–506, May 2019, doi: 10.1109/TSE.2017.2785841.

M. Motwani, S. Sankaranarayanan, R. Just, and Y. Brun, “Do automated program repair techniques repair hard and important bugs?,” Empir. Softw. Eng., vol. 23, no. 5, pp. 2901–2947, Oct. 2018, doi: 10.1007/s10664-017-9550-0.

M. Tufano, C. Watson, G. Bavota, M. Di Penta, M. White, and D. Poshyvanyk, “An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation,” ACM Transactions on Software Engineering and Methodology, vol. 28, no. 4, pp. 1–29, Oct. 2019, doi: 10.1145/3340544.

C. Zhang and J. Chen, “Fuzzing Methods Recommendation Based on Feature Vectors,” in 2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE), IEEE, Nov. 2021, pp. 1079–1081. doi: 10.1109/ASE51524.2021.9678630.

J. Imtiaz, M. Z. Iqbal, and M. U. khan, “An automated model-based approach to repair test suites of evolving web applications,” Journal of Systems and Software, vol. 171, p. 110841, Jan. 2021, doi: 10.1016/j.jss.2020.110841.

Z. Chen, S. J. Kommrusch, M. Tufano, L.-N. Pouchet, D. Poshyvanyk, and M. Monperrus, “SEQUENCER: Sequence-to-Sequence Learning for End-to-End Program Repair,” IEEE Transactions on Software Engineering, pp. 1–1, 2021, doi: 10.1109/TSE.2019.2940179.

Z. X. S. Y. H. S. X. L. Z. Y. Y. Z. Kai Huang, “A Survey on Automated Program Repair Techniques,” arXiv , 2023.

C. S. Xia, Y. Wei, and L. Zhang, “Automated Program Repair in the Era of Large Pre-trained Language Models,” in 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), IEEE, May 2023, pp. 1482–1494. doi: 10.1109/ICSE48619.2023.00129.

S. Hao, X. Shi, and H. Liu, “Exploring the Potential of Pre-Trained Language Models of Code for Automated Program Repair,” Electronics (Basel)., vol. 13, no. 7, p. 1200, Mar. 2024, doi: 10.3390/electronics13071200.

H. Joshi, J. Cambronero Sanchez, S. Gulwani, V. Le, G. Verbruggen, and I. Radiček, “Repair Is Nearly Generation: Multilingual Program Repair with LLMs,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 4, pp. 5131–5140, Jun. 2023, doi: 10.1609/aaai.v37i4.25642.

S. Bhatia, P. Kohli, and R. Singh, “Neuro-symbolic program corrector for introductory programming assignments,” in Proceedings of the 40th International Conference on Software Engineering, New York, NY, USA: ACM, May 2018, pp. 60–70. doi: 10.1145/3180155.3180219.