mlsanityData to 7 Oct 2026

RAG for code

109 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: code, generation, code generation, completion, code completion

Key facts. RAG for code: 109 papers on arXiv since 2020 (data through 7 Oct 2026). 30 of its 109 mapped papers (28%) cite “Retrieval Augmented Code Generation and Summarization” (2021, arXiv 2108.11601). 24 of its 109 mapped papers (22%) cite “ReACC: A Retrieval-Augmented Code Completion Framework” (2022, arXiv 2203.07722).

What’s new

Nothing new since 17 Sep. Latest: 10 Sep 2026.

Foundations

Most cited by papers here

  1. Retrieval Augmented Code Generation and Summarization2021cited by 30 here
  2. ReACC: A Retrieval-Augmented Code Completion Framework2022cited by 24 here
  3. Repoformer: Selective Retrieval for Repository-Level Code Completion2024cited by 14 here
  4. CodeRAG-Bench: Can Retrieval Augment Code Generation?2024cited by 11 here
  5. RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair2023cited by 10 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 14 here
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 57 here
  3. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 4 here
  4. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 5 here
  5. 2023In-Context Retrieval-Augmented Language Modelscited by 7 here
  6. 2023Active Retrieval Augmented Generationcited by 5 here
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 8 here
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 11 here
  9. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 6 here
  10. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 5 here
  11. 2025Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approachescited by 4 here
13 more it builds on, not in this chain
  1. 2020Retrieval-Augmented Generation for Code Summarization via Hybrid GNNcited by 8 here
  2. 2021Retrieval Augmented Code Generation and Summarizationcited by 30 here
  3. 2022ReACC: A Retrieval-Augmented Code Completion Frameworkcited by 24 here
  4. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 5 here
  5. 2023RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repaircited by 10 here
  6. 2024EVOR: Evolving Retrieval for Code Generationcited by 9 here
  7. 2024Repoformer: Selective Retrieval for Repository-Level Code Completioncited by 14 here
  8. 2024FT2Ra: A Fine-Tuning-Inspired Approach to Retrieval-Augmented Code Completioncited by 6 here
  9. 2024Prompt-based Code Completion via Multi-Retrieval Augmented Generationcited by 4 here
  10. 2024GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Modelcited by 9 here
  11. 2024CodeRAG-Bench: Can Retrieval Augment Code Generation?cited by 11 here
  12. 2025An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunitiescited by 6 here
  13. 2025What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyondcited by 4 here

The 24 most cited of 144.

Browse

30 of 109, ranked 6–35

  1. 6EVOR: Evolving Retrieval for Code Generation20249
  2. 7GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model20249
  3. 8Retrieval-Augmented Generation for Code Summarization via Hybrid GNN20208
  4. 9An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities20256
  5. 10FT2Ra: A Fine-Tuning-Inspired Approach to Retrieval-Augmented Code Completion20246
  6. 11What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond20254
  7. 12Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches20254
  8. 13Prompt-based Code Completion via Multi-Retrieval Augmented Generation20244
  9. 14RTLRepoCoder: Repository-Level RTL Code Completion through the Combination of Fine-Tuning and Retrieval Augmentation20253
  10. 15cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree20253
All 30
  1. 16Impact-driven Context Filtering For Cross-file Code Completion20253
  2. 17CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion20253
  3. 18Improving Retrieval-Augmented Code Comment Generation by Retrieving for Generation20243
  4. 19Building A Coding Assistant via the Retrieval-Augmented Language Model20243
  5. 20Retrieval-Augmented Code Generation for Universal Information Extraction20233
  6. 21When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?20252
  7. 22GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generation20252
  8. 23Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency Aware20252
  9. 24ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation20252
  10. 25Enhancing Code Translation in Language Models with Few-Shot Learning via Retrieval-Augmented Generation20242
  11. 26Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation20242
  12. 27RACE: Retrieval-Augmented Commit Message Generation20222
  13. 28Learning from Execution: Self-Evolving Memory for Private-Library Code Generation20261
  14. 29Beyond "What to Retrieve": Uncertainty in Retrieval-Augmented Code Generation20261
  15. 30CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs20251
  16. 31ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement20251
  17. 32RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry20251
  18. 33Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generation20251
  19. 34Retrieval-Augmented Code Review Comment Generation20251
  20. 35SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization20251