Python 2

5. Methods/Models for Downstream Tasks 1,114 8. Datasets 493 3. When Coding Meets Reasoning 264 2. Models 246 6. Analysis of AI-Generated Code 222 4. Code LLM for Low-Resource, Low-Level, and Domain-Specific Languages 95 7. Human-LLM Interaction 68 4. Datasets 37 News 34 9. Recommended Readings 32 5. Datasets 29 1. Surveys 16 6. Datasets 4 Star History 2 7. User-LLM Interaction 1

8.2 Benchmarks 520 3.5 Frontend Navigation 150 Text-To-SQL 138 Vulnerability Detection 113 Others 103 2.1 Base LLMs and Pretraining Strategies 87 Code Commenting and Summarization 81 Code Generation 79 3.3 Code Agents 77 Malicious Code Detection 76 Test Generation 76 Program Repair 71 2.4 (Instruction) Fine-Tuning on Code 67 3.1 Coding for Reasoning 64 3.4 Interactive Coding 54 Security and Vulnerabilities 52 2.3 General Pretraining on Code 46 Code Translation 44 Code Review 40 Frontend Development 37 4.2 Benchmarks 37 Repository-Level Coding 36 Code Similarity and Embedding (Clone Detection, Code Search) 33 2.5 Reinforcement Learning on Code 33 Correctness 32 5.2 Benchmarks 30 Requirement Engineering 28 Program Proof 24 Log Analysis 24 Binary Analysis and Decompilation 23 AI-Generated Code Detection 23 Compiler Optimization 21 Automated Machine Learning 21 Code RAG 20 Code Refactoring and Migration 19 Efficiency 18 Issue Resolution 16 Robustness 15 Oracle Generation 15 3.2 Code Simulation 14 Code Ranking 14 Software Configuration 14 2.2 Existing LLM Adapted to Code 13 Fuzz Testing 12 Hallucination 11 Code QA & Reasoning 11 API Usage 10 Software Modeling 10 Interpretability 10 Commit Message Generation 7 Bias 7 Mutation Testing 7 Privacy 7 8.1 Pretraining 6 6.2 Benchmarks 4 Type Prediction 4 Contamination 3

user-friendly 1 multi-task-learning 1 multi-task-fine-tuning 1 multi-model-support 1 customizable 1 tool-learning 1 rag 1 multi-agent 1 memory-management 1 llm 1 kg 1 ekg 1 agent 1