Elamur Research⌕
☰
home / papers / 2025 / 检索增强生成在软件工程中的应用综述

检索增强生成在软件工程中的应用综述

Summary

This Chinese-language survey from Nanjing University maps how retrieval-augmented generation (RAG) is used across software engineering. Work that pairs retrievers with PLMs and LLMs for code tasks has grown quickly, so the field lacked an overview of methods, open problems and directions. Earlier RAG surveys mostly cover NLP tasks. The authors followed systematic-review guidelines (Petersen, Kitchenham). They queried seven databases, screened results by hand and added papers through snowballing, ending with 108 studies from 2021–2024. They first chart publication venues, programming languages and models. They then classify retrievers as sparse, dense, hybrid or graph-based, and describe how retrieved content reaches the generator, either through prompt engineering or through attention over retrieved material. Applications span development, testing and maintenance, including code generation and completion, program and vulnerability repair, test generation, Text-to-SQL and refactoring. Challenges are grouped into three stages: knowledge-base construction, retrieval and generation. The survey serves as a practical entry map for anyone building code-oriented RAG systems.

Key points

  • Corpus of studies: 98 core papers came from database search and 10 more from snowballing, for 108 in total. Yearly output rose from 2 papers in 2021 to 70 in 2024.
  • Venues: about 67% of the papers are peer-reviewed and 33% are arXiv-only. The most frequent venues are EMNLP (11), ICSE (10), ASE (6), ACL (4) and ISSTA (3).
  • Languages and models:
    • Python appears in about 31% of studies, Java in 22%, SQL in 7%, and C, C++ and JS in about 5% each.
    • Across 46 models, GPT-3.5 is used most often (38 times), followed by GPT-4 (18), Codex (12), CodeT5 (12) and GPT-4o (8).
  • Example systems:
    • Repository-level tools: RepoCoder, ReACC, RLCoder, GraphCoder, CodexGraph and RepoGraph.
    • Repair and refactoring tools: InferFix, RTLFixer (Verilog), RING, T-RAP and SBLLM.
  • Open problems:
    • Knowledge bases built from code are often noisy and narrow.
    • Retrievers and generators are optimized toward different goals.
    • Generators are limited by context windows and produce hallucinated or outdated APIs.
    • Proposed remedies include RL-tuned retrievers (e.g. PPO), context compression and post-generation verification.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages · Natural language processing

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.13328/j.cnki.jos.007567

@article{2025,
  title = {{检索增强生成在软件工程中的应用综述}},
  author = {张犬俊 and 谢杨 and 房春荣 and 虞圣呈 and 赵源 and 陈振宇},
  journal = {软件学报 (Journal of Software)},
  year = {2025},
  doi = {10.13328/j.cnki.jos.007567},
  url = {https://doi.org/10.13328/j.cnki.jos.007567}
}

References

109 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Biolchini J, Mian PG, Natali AC, Travassos GH. Systematic review in software engineering. Rio de Janeiro: System Engineering and Computer Science Department COPPE/UFRJ, 2005. find
  2. Zelkowitz MV. Perspectives in software engineering. ACM Computing Surveys (CSUR), 1978, 10(2): 197–216. [doi: 10.1145/356725.356731] — [doi:10.1145/356725.356731](https://doi.org/10.1145/356725.356731) find
  3. Yang YM, Xia X, Lo D, Grundy J. A survey on deep learning for software engineering. ACM Computing Surveys (CSUR), 2022, 54(10s): 206. [doi: 10.1145/3505243] — [doi:10.1145/3505243](https://doi.org/10.1145/3505243) find
  4. Wang JJ, Huang YC, Chen CY, Liu Z, Wang S, Wang Q. Software testing with large language models: Survey, landscape, and vision. IEEE Trans. on Software Engineering, 2024, 50(4): 911–936. [doi: 10.1109/TSE.2024.3368208] — [doi:10.1109/tse.2024.3368208](https://doi.org/10.1109/tse.2024.3368208) find
  5. Devlin J, Chang MW, Lee K, Toutanova K. BERT: Pre-training of deep bidirectional Transformers for language understanding. In: Proc. of the 2019 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Minneapolis: ACL, 2019. 4171–4186. find
  6. Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou YQ, Li W, Liu PJ. Exploring the limits of transfer learning with a unified text-to-text Transformer. Journal of Machine Learning Research, 2020, 21(1): 140. find
  7. Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I. Language models are unsupervised multitask learners. 2019. https://api.semanticscholar.org/CorpusID:160025533 ↗
  8. Feng ZY, Guo DY, Tang DY, Duan N, Feng XC, Gong M, Shou LJ, Qin B, Liu T, Jiang DX, Zhou M. CodeBERT: A pre-trained model for programming and natural languages. In: Findings of the Association for Computational Linguistics: EMNLP 2020. ACL, 2020. 1536–1547. [doi: 10.18653/v1/2020.findings-emnlp.139] find our card
  9. Wang Y, Wang WS, Joty S, Hoi SCH. CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. In: Proc. of the 2021 Conf. on Empirical Methods in Natural Language Processing. Punta Cana: ACL, 2021. 8696–8708. [doi: 10.18653/v1/2021.emnlp-main.685] find
  10. Chen M, Tworek J, Jun H, et al. Evaluating large language models trained on code. arXiv:2107.03374, 2021. find our card
  11. Zhang QJ, Fang CR, Zheng Y, Qian RX, Yu SC, Zhao Y, Zhou JY, Yang Y, Zheng T, Chen ZY. Improving retrieval-augmented deep assertion generation via joint training. IEEE Trans. on Software Engineering, 2025, 51(4): 1232–1247. [doi: 10.1109/TSE.2025.3545970] — [doi:10.1109/tse.2025.3545970](https://doi.org/10.1109/tse.2025.3545970) find
  12. Yu XR, Li C, Pan MX, Li XD. DroidCoder: Enhanced android code completion with context-enriched retrieval-augmented generation. In: Proc. of the 39th IEEE/ACM Int’l Conf. on Automated Software Engineering. Sacramento: ACM, 2024. 681–693. [doi: 10.1145/3691620.3695063] — [doi:10.1145/3691620.3695063](https://doi.org/10.1145/3691620.3695063) find
  13. Zhang QJ, Fang CR, Zheng Y, Zhang YX, Zhao Y, Huang RB, Zhou JY, Yang Y, Zheng T, Chen ZY. Improving deep assertion generation via fine-tuning retrieval-augmented pre-trained language models. ACM Trans. on Software Engineering and Methodology, 2025, 34(7): 209. [doi: 10.1145/3721128] — [doi:10.1145/3721128](https://doi.org/10.1145/3721128) find
  14. Su HJ, Jiang SY, Lai YH, Wu HY, Shi BA, Liu C, Liu Q, Yu T. EvoR: Evolving retrieval for code generation. In: Findings of the Association for Computational Linguistics: EMNLP 2024. Miami: ACL, 2024. 2538–2554. [doi: 10.18653/v1/2024.findings-emnlp.143] find
  15. Guo Q, Li XH, Xie XF, Liu SQ, Tang Z, Feng RT, Wang JJ, Ge JD, Bu L. FT2Ra: A fine-tuning-inspired approach to retrieval-augmented code completion. In: Proc. of the 33rd ACM SIGSOFT Int’l Symp. on Software Testing and Analysis. Vienna: ACM, 2024. 313–324. [doi: 10.1145/3650212.3652130] — [doi:10.1145/3650212.3652130](https://doi.org/10.1145/3650212.3652130) find
  16. Liang M, Xie XH, Zhang GH, Zheng XJ, Di P, Jiang W, Chen HW, Wang CP, Fan G. RepoGenix: Dual context-aided repository-level code completion with language models. In: Proc. of the 39th IEEE/ACM Int’l Conf. on Automated Software Engineering. Sacramento: ACM, 2024. 2466–2467. [doi: 10.1145/3691620.3695… — [doi:10.1145/3691620.3695331](https://doi.org/10.1145/3691620.3695331) find
  17. Wu SY, Xiong Y, Cui YF, Wu HL, Chen C, Yuan Y, Huang LM, Liu X, Kuo TW, Guan N, Xue CJ. Retrieval-augmented generation for natural language processing: A survey. arXiv:2407.13193, 2024. find
  18. Zhao PH, Zhang HL, Yu QH, Wang ZR, Geng YT, Fu FC, Yang L, Zhang WT, Jiang J, Cui B. Retrieval-augmented generation for AI-generated content: A survey. arXiv:2402.19473, 2024. find
  19. Gao YF, Xiong Y, Gao XY, Jia KX, Pan JL, Bi YX, Dai Y, Sun JW, Wang M, Wang HF. Retrieval-augmented generation for large language models: A survey. arXiv:2312.10997, 2023. find our card
  20. Fan WQ, Ding YJ, Ning LB, Wang SJ, Li HY, Yin DW, Chua TS, Li Q. A survey on RAG meeting LLMs: Towards retrieval-augmented large language models. In: Proc. of the 30th ACM SIGKDD Conf. on Knowledge Discovery and Data Mining. Barcelona: ACM, 2024. 6491–6501. [doi: 10.1145/3637528.3671470] find our card
  21. Zhang QJ, Fang CR, Xie Y, Zhang YX, Yang Y, Sun WS, Yu SC, Chen ZY. A survey on large language models for software engineering. arXiv:2312.15223, 2023. — [arXiv:2312.15223](https://arxiv.org/abs/2312.15223) find
  22. Petersen K, Vakkalanka S, Kuzniarz L. Guidelines for conducting systematic mapping studies in software engineering: An update. Information and Software Technology, 2015, 64: 1–18. [doi: 10.1016/j.infsof.2015.03.007] — [doi:10.1016/j.infsof.2015.03.007](https://doi.org/10.1016/j.infsof.2015.03.007) find
  23. Software Engineering Group. Guidelines for performing systematic literature reviews in software engineering. Technical Report, EBSE 2007-001. Durham: University of Durham, 2007. 1–65. find
  24. Watson C, Cooper N, Palacio DN, Moran K, Poshyvanyk D. A systematic literature review on the use of deep learning in software engineering research. ACM Trans. on Software Engineering and Methodology (TOSEM), 2022, 31(2): 32. [doi: 10.1145/3485275] — [doi:10.1145/3485275](https://doi.org/10.1145/3485275) find
  25. Li J, Zhao YF, Li YM, Li G, Jin Z. ACECODER: An effective prompting technique specialized in code generation. ACM Trans. on Software Engineering and Methodology, 2024, 33(8): 204. [doi: 10.1145/3675395] — [doi:10.1145/3675395](https://doi.org/10.1145/3675395) find
  26. Li J, Li YM, Li G, Jin Z, Hao YY, Hu X. SkCoder: A sketch-based approach for automatic code generation. In: Proc. of the 45th IEEE/ACM Int’l Conf. on Software Engineering (ICSE). Melbourne: IEEE, 2023. 2124–2135. [doi: 10.1109/ICSE48619.2023.00179] — [doi:10.1109/icse48619.2023.00179](https://doi.org/10.1109/icse48619.2023.00179) find
  27. Zhang LH, Zhang HY, Wang C, Liang P. RAG-enhanced commit message generation. arXiv:2406.05514, 2024. — [arXiv:2406.05514](https://arxiv.org/abs/2406.05514) find
  28. Wang YL, Wang YL, Guo DY, Chen JC, Zhang RK, Ma YC, Zheng ZB. RLCoder: Reinforcement learning for repository-level code completion. In: Proc. of the 47th IEEE/ACM Int’l Conf. on Software Engineering. Ottawa: IEEE, 2025. 1140–1152. [doi: 10.1109/ICSE55347.2025.00014] — [doi:10.1109/icse55347.2025.00014](https://doi.org/10.1109/icse55347.2025.00014) find
  29. Parvez R, Ahmad W, Chakraborty S, Ray B, Chang KW. Retrieval augmented code generation and summarization. In: Findings of the Association for Computational Linguistics: EMNLP 2021. Punta Cana: ACL, 2021. 2719–2734. [doi: 10.18653/v1/2021.findings-emnlp.232] find
  30. Gou QW, Dong YW, Wu YJ, Ke Q. RRGcode: Deep hierarchical search-based code generation. Journal of Systems and Software, 2024, 211: 111982. [doi: 10.1016/j.jss.2024.111982] — [doi:10.1016/j.jss.2024.111982](https://doi.org/10.1016/j.jss.2024.111982) find
  31. Nan LY, Zhao YL, Zou WJ, Ri N, Tae J, Zhang E, Cohan A, Radev D. Enhancing text-to-SQL capabilities of large language models: A study on prompt design strategies. In: Findings of the Association for Computational Linguistics: EMNLP 2023. Singapore: ACL, 2023. 14935–14956. [doi: 10.18653/v1/2023.find… find
  32. Zhao JJ, Chen X, Yang G, Shen YH. Automatic smart contract comment generation via large language models and in-context learning. Information and Software Technology, 2024, 168: 107405. [doi: 10.1016/j.infsof.2024.107405] — [doi:10.1016/j.infsof.2024.107405](https://doi.org/10.1016/j.infsof.2024.107405) find
  33. Yu C, Yang G, Chen X, Liu K, Zhou YL. BashExplainer: Retrieval-augmented bash code comment generation based on fine-tuned CodeBERT. In: Proc. of the 2022 IEEE Int’l Conf. on Software Maintenance and Evolution. Limassol: IEEE, 2022. 82–93. [doi: 10.1109/ICSME55016.2022.00016] — [doi:10.1109/icsme55016.2022.00016](https://doi.org/10.1109/icsme55016.2022.00016) find
  34. Guo DY, Ren S, Lu S, Feng ZY, Tang DY, Liu SJ, Zhou L, Duan N, Svyatkovskiy A, Fu SY, Tufano M, Deng SK, Clement CB, Drain D, Sundaresan N, Yin J, Jiang DX, Zhou M. GraphCodeBERT: Pre-training code representations with data flow. In: Proc. of the 9th Int’l Conf. on Learning Representations. OpenRevi… find our card
  35. Zhang FJ, Chen B, Zhang Y, Keung J, Liu J, Zan DG, Mao Y, Lou JG, Chen WZ. RepoCoder: Repository-level code completion through iterative retrieval and generation. In: Proc. of the 2023 Conf. on Empirical Methods in Natural Language Processing. Singapore: ACL, 2023. 2471–2484. [doi: 10.18653/v1/2023.… find
  36. Li LX, Liang B, Chen L, Zhang XF. Cross-modal retrieval-enhanced code summarization based on joint learning for retrieval and generation. Information and Software Technology, 2024, 175: 107527. [doi: 10.1016/j.infsof.2024.107527] — [doi:10.1016/j.infsof.2024.107527](https://doi.org/10.1016/j.infsof.2024.107527) find
  37. Tang Z, Ge JD, Liu SQ, Zhu TW, Xu TT, Huang LG, Luo B. Domain adaptive code completion via language models and decoupled domain databases. In: Proc. of the 38th IEEE/ACM Int’l Conf. on Automated Software Engineering. Luxembourg: IEEE, 2023. 421–433. [doi: 10.1109/ASE56229.2023.00076] — [doi:10.1109/ase56229.2023.00076](https://doi.org/10.1109/ase56229.2023.00076) find
  38. Eghbali A, Pradel M. De-Hallucinator: Iterative grounding for LLM-based code completion. arXiv:2401.01701v1, 2024. — [arXiv:2401.01701](https://arxiv.org/abs/2401.01701) find
  39. Gong LN, Zhou YR, Qiao Y, Jiang SJ, Wei MQ, Huang ZQ. Research progress of pre-trained model in software engineering. Ruan Jian Xue Bao/Journal of Software, 2025, 36(1): 1–26 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/7143.htm [doi: 10.13328/j.cnki.jos.007143] ↗ our card
  40. Gao XY, Xiong Y, Wang DZ, Guan ZH, Shi ZJ, Wang HF, Li SS. Preference-guided refactored tuning for retrieval augmented code generation. In: Proc. of the 39th IEEE/ACM Int’l Conf. on Automated Software Engineering. Sacramento: ACM, 2024. 65–77. [doi: 10.1145/3691620.3694987] — [doi:10.1145/3691620.3694987](https://doi.org/10.1145/3691620.3694987) find
  41. Wang WS, Wang Y, Joty S, Hoi SCH. RAP-Gen: Retrieval-augmented patch generation with CodeT5 for automatic program repair. In: Proc. of the 31st ACM Joint European Software Engineering Conf. and Symp. on the Foundations of Software Engineering. San Francisco: ACM, 2023. 146–158. [doi: 10.1145/3611643… — [doi:10.1145/3611643.3616256](https://doi.org/10.1145/3611643.3616256) find
  42. Lu S, Duan N, Han H, Guo DY, Hwang SW, Svyatkovskiy A. ReACC: A retrieval-augmented code completion framework. In: Proc. of the 60th Annual Meeting of the Association for Computational Linguistics. Dublin: ACL, 2022. 6227–6240. [doi: 10.18653/v1/2022.acl-long.431] find
  43. Wang Y, Le H, Gotmare A, Bui N, Li JN, Hoi S. CodeT5+: Open code large language models for code understanding and generation. In: Proc. of the 2023 Conf. on Empirical Methods in Natural Language Processing. Singapore: ACL, 2023. 1069–1088. [doi: 10.18653/v1/2023.emnlp-main.68] find
  44. Liang M, Xie XH, Zhang GH, Zheng XJ, Di P, Jiang W, Chen HW, Wang CP, Fan G. REPOFUSE: Repository-level code completion with fused dual context. arXiv:2402.14323, 2024. — [arXiv:2402.14323](https://arxiv.org/abs/2402.14323) find
  45. Liu MW, Yang TY, Lou YL, Du XY, Wang Y, Peng X. CodeGen4Libs: A two-stage approach for library-oriented code generation. In: Proc. of the 38th IEEE/ACM Int’l Conf. on Automated Software Engineering. Luxembourg: IEEE, 2023. 434–445. [doi: 10.1109/ASE56229.2023.00159] — [doi:10.1109/ase56229.2023.00159](https://doi.org/10.1109/ase56229.2023.00159) find
  46. Wang ZZ, Asai A, Yu XV, Xu FF, Xie YQ, Neubig G, Fried D. CodeRAG-Bench: Can retrieval augment code generation? In: Findings of the Association for Computational Linguistics: NAACL 2025. Albuquerque: ACL, 2024. 3199–3214. [doi: 10.18653/v1/2025. findings-naacl.176] find
  47. Shrivastava D, Kocetkov D, de Vries H, Bahdanau D, Scholak T. RepoFusion: Training code models to understand your repository. arXiv:2306.10998, 2023. — [arXiv:2306.10998](https://arxiv.org/abs/2306.10998) find
  48. Du XY, Zheng G, Wang KX, Zou Y, Wang YJ, Deng WT, Feng JY, Liu MW, Chen BH, Peng X, Ma T, Lou YL. Vul-RAG: Enhancing LLM-based vulnerability detection via knowledge-level RAG. arXiv:2406.11147, 2024. — [arXiv:2406.11147](https://arxiv.org/abs/2406.11147) find
  49. Mackay A. Test suite augmentation using language models-applying RAG to improve robustness verification. In: Proc. of the 12th European Congress on Embedded Real-time Systems (ERTS 2024). 2024. 1–11. find
  50. Ouyang SR, Yu WH, Ma KX, Xiao ZL, Zhang ZH, Jia MZ, Han JW, Zhang HM, Yu D. RepoGraph: Enhancing AI software engineering with repository-level code graph. arXiv:2410.14684, 2024. — [arXiv:2410.14684](https://arxiv.org/abs/2410.14684) find
  51. Zhang Z, Liu XY, Lin YZ, Gao X, Sun HL, Yuan Y. LLM-based unit test generation via property retrieval. arXiv:2410.13542, 2024. — [arXiv:2410.13542](https://arxiv.org/abs/2410.13542) find
  52. Bogin B, Gupta S, Clark P, Sabharwal A. Leveraging code to improve in-context learning for semantic parsing. In: Proc. of the 2024 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Mexico City: ACL, 2024. 4971–5012. [doi: 10.18653/v1/2… find
  53. Liu XY, Lan B, Hu ZY, Liu Y, Zhang ZC, Wang F, Shieh MQ, Zhou WM. CodexGraph: Bridging large language models and code repositories via code graph databases. In: Proc. of the 2025 Conf. of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologie… find
  54. Guo DY, Zhu QH, Yang DJ, Xie ZD, Dong K, Zhang WT, Chen GT, Bi X, Wu Y, Li YK, Luo FL, Xiong YF, Liang WF. DeepSeek-Coder: When the large language model meets programming—The rise of code intelligence. arXiv:2401.14196, 2024. find
  55. Chen JK, Hu X, Li ZH, Gao CY, Xia X, Lo D. Code search is all you need? Improving code suggestions with code search. In: Proc. of the 46th IEEE/ACM Int’l Conf. on Software Engineering. Lisbon: ACM, 2024. 73. [doi: 10.1145/3597503.3639085] — [doi:10.1145/3597503.3639085](https://doi.org/10.1145/3597503.3639085) find
  56. Rozière B, Gehring J, Gloeckle F, et al. Code LLaMA: Open foundation models for code. arXiv:2308.12950, 2023. find our card
  57. CodeGemma Team. CodeGemma: Open code models based on gemma. arXiv:2406.11409, 2024. find
  58. Yang ZZ, Chen SR, Gao CY, Li ZH, Li G, Lyu MRT. Deep learning based code generation methods: Literature review. Ruan Jian Xue Bao/Journal of Software, 2024, 35(2): 604–628 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6981.htm [doi: 10.13328/j.cnki.jos.006981] ↗ our card
  59. He PF, Wang SW, Chowdhury S, Chen TH. Evaluating the effectiveness and efficiency of demonstration retrievers in RAG for coding tasks. arXiv:2410.09662, 2024. — [arXiv:2410.09662](https://arxiv.org/abs/2410.09662) find
  60. Daneshvar SS, Nong Y, Yang X, Wang SW, Cai HP. VulScribeR: Exploring RAG-based vulnerability augmentation with LLMs. ACM Trans. on Software Engineering and Methodology, 2025. [doi: 10.1145/3760775] — [doi:10.1145/3760775](https://doi.org/10.1145/3760775) find
  61. Kamiya T. A RAG method for source code inquiry tailored to long-context LLMs. arXiv:2404.06082, 2024. — [arXiv:2404.06082](https://arxiv.org/abs/2404.06082) find
  62. Mansourian D, Olsson A, Sönnerhed L. A generative AI approach to native iOS and Android code translation: With and without retrieval-augmented generation (RAG). 2025. https://www.diva-portal.org/smash/record.jsf?pid=diva2%3A1879944&dswid=-5661 ↗
  63. Xu TT, Liu K, Xia X. Survey on automated vulnerability repair. Ruan Jian Xue Bao/Journal of Software, 2024, 35(1): 136–158 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6828.htm [doi: 10.13328/j.cnki.jos.006828] — [doi:10.13328/j.cnki.jos.006828](https://doi.org/10.13328/j.cnki.jos.006828) ↗
  64. Dai HP, Sun CA, Jin H, Xiao MJ. State-of-the-art survey on fuzz testing for deep learning system. Ruan Jian Xue Bao/Journal of Software, 2023, 34(11): 5008–5028 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6679.htm [doi: 10.13328/j.cnki. jos.006679] — [doi:10.13328/j.cnki](https://doi.org/10.13328/j.cnki) ↗
  65. Bui TD, Luu-Van DT, Nguyen TP, Nguyen TT, Nguyen S, Vo HD. RAMBO: Enhancing RAG-based repository-level method body completion. arXiv:2409.15204, 2024. — [arXiv:2409.15204](https://arxiv.org/abs/2409.15204) find
  66. Wu YX, He PF, Wang ZH, Wang SW, Tian Y, Chen TH. A comprehensive framework for evaluating API-oriented code generation in large language models. arXiv:2409.15228, 2024. — [arXiv:2409.15228](https://arxiv.org/abs/2409.15228) find
  67. Koziolek H, Grüner S, Hark R, Ashiwal V, Linsbauer S, Eskandani N. LLM-based and retrieval-augmented control code generation. In: Proc. of the 1st Int’l Workshop on Large Language Models for Code. Lisbon: ACM, 2024. 22–29. [doi: 10.1145/3643795.3648384] — [doi:10.1145/3643795.3648384](https://doi.org/10.1145/3643795.3648384) find
  68. Ding YRB, Wang ZJ, Ahmad W, Ramanathan MK, Nallapati R, Bhatia P, Roth D, Xiang B. CoCoMIC: Code completion by jointly modeling in-file and cross-file context. In: Proc. of the 2024 Joint Int’l Conf. on Computational Linguistics, Language Resources and Evaluation. Torino: ACL, 2024. 3433–3445. find
  69. Jin M, Shahriar S, Tufano M, Shi X, Lu S, Sundaresan N, Svyatkovskiy A. InferFix: End-to-end program repair with LLMs. In: Proc. of the 31st ACM Joint European Software Engineering Conf. and Symp. on the Foundations of Software Engineering. San Francisco: ACM, 2023. 1646–1656. [doi: 10.1145/3611643.… — [doi:10.1145/3611643.3613892](https://doi.org/10.1145/3611643.3613892) find
  70. Lu HZ, Liu ZX. Improving retrieval-augmented code comment generation by retrieving for generation. In: Proc. of the 2024 IEEE Int’l Conf. on Software Maintenance and Evolution. Flagstaff: IEEE, 2024. 350–362. [doi: 10.1109/ICSME58944.2024.00040] — [doi:10.1109/icsme58944.2024.00040](https://doi.org/10.1109/icsme58944.2024.00040) find
  71. Xu JJL, Cui Z, Zhao Y, Zhang X, He SL, He PJ. UniLog: Automatic logging via LLM and in-context learning. In: Proc. of the 46th IEEE/ACM Int’l Conf. on Software Engineering. Lisbon: IEEE, 2024. 1–12. [doi: 10.1145/3597503.3623326] — [doi:10.1145/3597503.3623326](https://doi.org/10.1145/3597503.3623326) find
  72. Shao YC, Huang YH, Shen JW, Ma L, Su T, Wan CC. Vortex under ripplet: An empirical study of RAG-enabled applications. arXiv:2407.05138v1, 2024. — [arXiv:2407.05138](https://arxiv.org/abs/2407.05138) find
  73. Guo YC, Li ZX, Jin XL, Liu YT, Zeng YT, Liu WX, Li X, Yang P, Bai L, Guo JF, Cheng XQ. Retrieval-augmented code generation for universal information extraction. In: Proc. of the 13th National CCF Conf. on Natural Language Processing and Chinese Computing. Hangzhou: Springer, 2025. 30–42. [doi: 10.10… — [doi:10.1007/978-981-97-9434-8_3](https://doi.org/10.1007/978-981-97-9434-8_3) find
  74. Yoo J, Han H, Lee Y, Kim J, Hwang SW. PERC: Plan-as-query example retrieval for underrepresented code generation. In: Proc. of the 31st Int’l Conf. on Computational Linguistics. Abu Dhabi: ACL, 2025. 7982–7997. find
  75. Liu ZH, Zeng RN, Wang DX, Peng GY, Wang JY, Liu Q, Liu PY, Wang WH. Agents4PLC: Automating closed-loop PLC code generation and verification in industrial control systems using LLM-based agents. arXiv:2410.14209, 2024. — [arXiv:2410.14209](https://arxiv.org/abs/2410.14209) find
  76. Zan DG, Chen B, Lin ZQ, Guan B, Wang YJ, Lou JG. When language model meets private library. In: Findings of the Association for Computational Linguistics: EMNLP 2022. Abu Dhabi: ACL, 2022. 277–288. [doi: 10.18653/v1/2022.findings-emnlp.21] find
  77. Zhang KC, Zhang HZ, Li G, Li J, Li Z, Jin Z. ToolCoder: Teach code generation models to use API search tools. arXiv:2305.04032, 2023. — [arXiv:2305.04032](https://arxiv.org/abs/2305.04032) find
  78. Liao DS, Pan SD, Sun XY, Ren XW, Huang Q, Xing ZC, Jin H, Li QY. A 3 -CodGen: A repository-level code generation framework for code reuse with local-aware, global-aware, and third-party-library-aware. IEEE Trans. on Software Engineering, 2024, 50(12): 3369–3384. [doi: 10.1109/TSE.2024.3486195] — [doi:10.1109/tse.2024.3486195](https://doi.org/10.1109/tse.2024.3486195) find
  79. Zhang KC, Li J, Li G, Shi XJ, Jin Z. CodeAgent: Enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges. In: Proc. of the 62nd Annual Meeting of the Association for Computational Linguistics. Bangkok: ACL, 2024. 13643–13658. [doi: 10.18653/v1/2024.acl… find
  80. Tan HZ, Luo Q, Jiang L, Zhan ZZ, Li J, Zhang HT, Zhang YQ. Prompt-based code completion via multi-retrieval augmented generation. ACM Trans. on Software Engineering and Methodology, 2025. [doi: 10.1145/3725812] — [doi:10.1145/3725812](https://doi.org/10.1145/3725812) find
  81. Liu W, Yu AL, Zan DG, Shen B, Zhang W, Zhao HY, Jin Z, Wang QX. GraphCoder: Enhancing repository-level code completion via coarse-to-fine retrieval based on code context graph. In: Proc. of the 39th IEEE/ACM Int’l Conf. on Automated Software Engineering. Sacramento: ACM, 2024. 570–581. [doi: 10.1145… — [doi:10.1145/3691620.3695054](https://doi.org/10.1145/3691620.3695054) find
  82. Zhu TW, Li Z, Pan MX, Shi CX, Zhang T, Pei Y, Li XD. Deep is better? An empirical comparison of information retrieval and deep learning approaches to code summarization. ACM Trans. on Software Engineering and Methodology, 2024, 33(3): 67. [doi: 10.1145/3631975] — [doi:10.1145/3631975](https://doi.org/10.1145/3631975) find
  83. Ahmed T, Pai KS, Devanbu P, Barr E. Automatic semantic augmentation of language model prompts (for code summarization). In: Proc. of the 46th IEEE/ACM Int’l Conf. on Software Engineering. Lisbon: ACM, 2024. 220. [doi: 10.1145/3597503.3639183] — [doi:10.1145/3597503.3639183](https://doi.org/10.1145/3597503.3639183) find
  84. Shi ES, Wang YL, Tao W, Du L, Zhang HY, Han S, Zhang DM, Sun HB. RACE: Retrieval-augmented commit message generation. In: Proc. of the 2022 Conf. on Empirical Methods in Natural Language Processing. Abu Dhabi: ACL, 2022. 5520–5530. [doi: 10.18653/v1/2022.emnlp-main.372] find
  85. Ji XY, Parameswaran A, Hulsebos M. TARGET: Benchmarking table retrieval for generative tasks. In: Proc. of the 3rd Table Representation Learning Workshop. Vancouver, 2024. 1–8. find
  86. Li HY, Zhang J, Li CP, Chen H. RESDSQL: Decoupling schema linking and skeleton parsing for text-to-SQL. In: Proc. of the 37th AAAI Conf. on Artificial Intelligence. Washington: AAAI Press, 2023. 13067–13075. [doi: 10.1609/aaai.v37i11.26535] find
  87. Zhang K, Lin XX, Wang YZ, Zhang X, Sun F, Cen JH, Tan HX, Jiang XH, Shen HW. ReFSQL: A retrieval-augmentation framework for text-to-SQL generation. In: Findings of the Association for Computational Linguistics: EMNLP 2023. Singapore: ACL, 2023. 664–673. [doi: 10.18653/v1/2023.findings-emnlp.48] find
  88. Poesia G, Polozov O, Le V, Tiwari A, Soares G, Meek C, Gulwani S. Synchromesh: Reliable code generation from pre-trained language models. In: Proc. of the 10th Int’l Conf. on Learning Representations. OpenReview.net, 2022. find
  89. Shi P, Zhang R, Bai H, Lin J. XRICL: Cross-lingual retrieval-augmented in-context learning for cross-lingual text-to-SQL semantic parsing. In: Findings of the Association for Computational Linguistics: EMNLP 2022. Abu Dhabi: ACL, 2022. 5248–5259. [doi: 10.18653/v1/2022.findings-emnlp.384] find
  90. Chang SC, Fosler-Lussier E. Selective demonstrations for cross-domain text-to-SQL. In: Findings of the Association for Computational Linguistics: EMNLP 2023. Singapore: ACL, 2023. 14174–14189. [doi: 10.18653/v1/2023.findings-emnlp.944] find
  91. Zhang XL, Wang DZR, Dou LX, Zhu QF, Che WX. MURRE: Multi-hop table retrieval with removal for open-domain text-to-SQL. In: Proc. of the 31st Int’l Conf. on Computational Linguistics. Abu Dhabi: ACL, 2025. 5789–5806. find
  92. Deng X, Ye W, Xie R, Zhang SK. Survey of source code bug detection based on deep learning. Ruan Jian Xue Bao/Journal of Software, 2023, 34(2): 625–654 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6696.htm [doi: 10.13328/j.cnki.jos.006696] — [doi:10.13328/j.cnki.jos.006696](https://doi.org/10.13328/j.cnki.jos.006696) ↗
  93. Shang Y, Zhang QJ, Fang CR, Gu SQ, Zhou JY, Chen ZY. A large-scale empirical study on fine-tuning large language models for unit testing. In: Proc. of the 2025 ACM SIGSOFT Int’l Symp. on Software Testing and Analysis (ISSTA 2025). [doi: 10.1145/3728951] find
  94. Chi JL, Wang XT, Huang YH, Yu LC, Cui D, Sun JG, Sun J. REACCEPT: Automated co-evolution of production and test code based on dynamic validation and large language models. In: Proc. of the 2025 ACM SIGSOFT Int’l Symp. on Software Testing and Analysis (ISSTA 2025). [doi: 10.1145/3728930] — [doi:10.1145/3728930](https://doi.org/10.1145/3728930) find
  95. Zhang QJ, Sun WF, Fang CR, Yu BW, Li HY, Yan M, Zhou JY, Chen ZY. Exploring automated assertion generation via large language models. ACM Trans. on Software Engineering and Methodology, 2025, 34(3): 81. [doi: 10.1145/3699598] — [doi:10.1145/3699598](https://doi.org/10.1145/3699598) find
  96. Nashid N, Sintaha M, Mesbah A. Retrieval-based prompt selection for code-related few-shot learning. In: Proc. of the 45th IEEE/ACM Int’l Conf. on Software Engineering. Melbourne: IEEE, 2023. 2450–2462. [doi: 10.1109/ICSE48619.2023.00205] — [doi:10.1109/icse48619.2023.00205](https://doi.org/10.1109/icse48619.2023.00205) find
  97. Liu Z, Chen CY, Wang JJ, Chen MZ, Wu BY, Tian ZL, Huang YK, Hu J, Wang Q. Testing the limits: Unusual text inputs generation for mobile app crash detection with large language model. In: Proc. of the 46th IEEE/ACM Int’l Conf. on Software Engineering. Lisbon: ACM, 2024. 137. [doi: 10.1145/3597503.363… — [doi:10.1145/3597503.3639118](https://doi.org/10.1145/3597503.3639118) find
  98. Jiang JJ, Chen JJ, Xiong YF. Survey of automatic program repair techniques. Ruan Jian Xue Bao/Journal of Software, 2021, 32(9): 2665–2690 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6274.htm [doi: 10.13328/j.cnki.jos.006274] — [doi:10.13328/j.cnki.jos.006274](https://doi.org/10.13328/j.cnki.jos.006274) ↗
  99. Yuan MY, Chen JS, Xing ZC, Quigley A, Luo YY, Luo TQ, Mohammadi G, Lu QH, Zhu LM. DesignRepair: Dual-stream design guideline-aware frontend repair with large language models. In: Proc. of the 47th IEEE/ACM Int’l Conf. on Software Engineering. Ottawa: IEEE, 2025. 2483–2494. [doi: 10.1109/ICSE55347.20… — [doi:10.1109/icse55347.2025.00109](https://doi.org/10.1109/icse55347.2025.00109) find
  100. Qayyum K, Hassan M, Ahmadi-Pour S, Jha CK, Drechsler R. From bugs to fixes: HDL bug identification and patching using LLMs and RAG. In: Proc. of the 2024 IEEE LLM Aided Design Workshop. San Jose: IEEE, 2024. 1–5. [doi: 10.1109/LAD62341.2024.10691874] — [doi:10.1109/lad62341.2024.10691874](https://doi.org/10.1109/lad62341.2024.10691874) find
  101. Liu CS, Cetin P, Patodia Y, Ray B, Chakraborty S, Ding YRB. Automated code editing with search-generate-modify. In: Proc. of the 46th IEEE/ACM Int’l Conf. on Software Engineering: Companion Proc. Lisbon: ACM, 2024. 398–399. [doi: 10.1145/3639478.3643124] — [doi:10.1145/3639478.3643124](https://doi.org/10.1145/3639478.3643124) find
  102. Tsai Y, Liu MJ, Ren HX. RTLFixer: Automatically fixing RTL syntax errors with large language model. In: Proc. of the 61st ACM/IEEE Design Automation Conf. San Francisco: ACM, 2024. 53. [doi: 10.1145/3649329.3657353] — [doi:10.1145/3649329.3657353](https://doi.org/10.1145/3649329.3657353) find
  103. Joshi H, Sanchez JC, Gulwani S, Le V, Verbruggen G, Radiček I. Repair is nearly generation: Multilingual program repair with LLMs. In: Proc. of the 37th AAAI Conf. on Artificial Intelligence. Washington: AAAI Press, 2023. 5131–5140. [doi: 10.1609/aaai.v37i4.25642] — [doi:10.1609/aaai.v37i4.25642](https://doi.org/10.1609/aaai.v37i4.25642) find
  104. Chan CM, Xu CP, Yuan RB, Luo HY, Xue W, Guo YK, Fu J. RQ-RAG: Learning to refine queries for retrieval augmented generation. arXiv:2404.00610, 2024. find
  105. Liu P, Lin B, Qin YH, Weng C, Chen LQ. T-RAP: A template-guided retrieval-augmented vulnerability patch generation approach. In: Proc. of the 15th Asia-Pacific Symp. on Internetware. Macao: ACM, 2024. 105–114. [doi: 10.1145/3671016.3672506] — [doi:10.1145/3671016.3672506](https://doi.org/10.1145/3671016.3672506) find
  106. Gao SZ, Gao CY, Gu WC, Lyu MR. Search-based LLMs for code optimization. In: Proc. of the 47th IEEE/ACM Int’l Conf. on Software Engineering. Ottawa: IEEE, 2025. 578–590. [doi: 10.1109/ICSE55347.2025.00021] — [doi:10.1109/icse55347.2025.00021](https://doi.org/10.1109/icse55347.2025.00021) find
  107. Guo ZR, Xia LH, Yu YH, Ao T, Huang C. LightRAG: Simple and fast retrieval-augmented generation. arXiv:2410.05779, 2024. find our card
  108. Su HJ, Jiang SY, Lai YH, Wu HY, Shi BA, Liu C, Liu Q, Yu T. ARKS: Active retrieval in knowledge soup for code generation. arXiv:2402.12317v1, 2024. — [arXiv:2402.12317](https://arxiv.org/abs/2402.12317) find
  109. Drain D, Hu CR, Wu C, Breslav M, Sundaresan N. Generating code with the help of retrieved template functions and stack overflow answers. arXiv:2104.05310, 2021. 附中文参考文献 [39] 宫丽娜, 周易人, 乔羽, 姜淑娟, 魏明强, 黄志球. 预训练模型在软件工程领域应用研究进展. 软件学报, 2025, 36(1): 1–26. http://www.jos.org.cn/1000-9825/7143.htm [doi: 10.1… ↗ our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/zhang-2025-application-retrieval-augmented/