mlsanityData to 7 Oct 2026

RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion

arXiv 2403.06095 ↗First posted 10 Mar 2024cs.SE cs.AIcited by 15

Not on the map. Why?

Abstract (arXiv)

Code Large Language Models (CodeLLMs) have demonstrated impressive proficiency in code completion tasks. However, they often fall short of fully understanding the extensive context of a project repository, such as the intricacies of relevant files and class hierarchies, which can result in less precise completions. To overcome these limitations, we present tool, a multifaceted framework designed to address the complex challenges associated with repository-level code completion. Central to RepoHYPER is the em Repo-level Semantic Graph (RSG), a novel semantic graph structure that encapsulates the vast context of code repositories. Furthermore, RepoHyper leverages Expand and Refine retrieval method, including a graph expansion and a link prediction algorithm applied to the RSG, enabling the effective retrieval and prioritization of relevant code snippets. Our evaluations show that tool markedly outperforms existing techniques in repository-level code completion, showcasing enhanced accuracy across various datasets when compared to several strong baselines. Our implementation of RepoHYPER can be found at https://github.com/FSoft-AI4Code/RepoHyper.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 39 of its 55 references that are in the map. First posted on arXiv 10 Mar 2024.

Builds on

39 of 55 references.

References · 39

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  6. 2021Program Synthesis with Large Language Modelscited by 3,509
  7. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  8. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  9. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  10. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,085
  11. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  12. 2021Measuring Coding Challenge Competence With APPScited by 879
27 more
  1. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
  2. 2023StarCoder: may the source be with you!cited by 790
  3. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  4. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  5. 2021Carbon Emissions and Large Neural Network Trainingcited by 561
  6. 2020CodeBLEU: a Method for Automatic Evaluation of Code Synthesiscited by 468
  7. 2022UniXcoder: Unified Cross-Modal Pre-training for Code Representationcited by 355
  8. 2023RepoBench: Benchmarking Repository-Level Code Auto-Completion Systemscited by 346
  9. 2023CodeT5+: Open Code Large Language Models for Code Understanding and Generationcited by 327
  10. 2023CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-Xcited by 294
  11. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challengescited by 278
  12. 2019Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networkscited by 266
  13. 2020Can Graph Neural Networks Count Substructures?cited by 235
  14. 2017Learning to Represent Programs with Graphscited by 219
  15. 2023CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completioncited by 181
  16. 2023OctoPack: Instruction Tuning Code Large Language Modelscited by 178
  17. 2023CodePlan: Repository-level Coding using LLMs and Planningcited by 139
  18. 2023CodeGen2: Lessons for Training LLMs on Programming and Natural Languagescited by 124
  19. 2022Repository-Level Prompt Generation for Large Language Models of Codecited by 106
  20. 2022CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Contextcited by 64
  21. 2018Learning Conditioned Graph Structures for Interpretable Visual Question Answeringcited by 45
  22. 2023RepoFusion: Training Code Models to Understand Your Repositorycited by 40
  23. 2023CodeTF: One-stop Transformer Library for State-of-the-art Code LLMscited by 21
  24. 2023Guiding Language Models of Code with Global Context using Monitorscited by 20
  25. 2020A Toolkit for Generating Code Knowledge Graphscited by 17
  26. 2018Hierarchical Learning of Cross-Language Mappings through Distributed Vector Representations for Codecited by 5
  27. 2019TreeCaps: Tree-Structured Capsule Networks for Program Source Code Processingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 4; 2026: 6.

15 papers.

Sort:

By area:

  1. 2024M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluationcited by 21
  2. 2025Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approachescited by 20
  3. 2026In Line with Context: Repository-Level Code Generation via Context Inliningcited by 18
  4. 2024RAMBO: Enhancing RAG-based Repository-Level Method Body Completioncited by 10
  5. 2025Towards an Understanding of Context Utilization in Code Intelligencecited by 10
  6. 2026RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Modelscited by 5
  7. 2024VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoningcited by 3
  8. 2024ContextModule: Improving Code Completion via Repository-level Contextual Informationcited by 3
  9. 2026Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answeringcited by 3
  10. 2024On The Importance of Reasoning for Context Retrieval in Repository-Level Code Editingcited by 2
  11. 2025TENET: One Step Toward Test-Driven Development for Repository-Level Code Generationcited by 2
  12. 2026Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolutioncited by 1
3 more
  1. 2025Challenge on Optimization of Context Collection for Code Completioncited by 0
  2. 2026ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generationcited by 0
  3. 2026FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generationcited by 0