Python 2

5. Methods/Models for Downstream Tasks 1,188 8. Datasets 533 3. When Coding Meets Reasoning 284 2. Models 260 6. Analysis of AI-Generated Code 232 4. Code LLM for Low-Resource, Low-Level, and Domain-Specific Languages 104 7. Human-LLM Interaction 70 News 40 9. Recommended Readings 32 5. Datasets 29 4. Datasets 20 1. Surveys 17 6. Datasets 4 Star History 2 7. User-LLM Interaction 1

8.2 Benchmarks 560 3.5 Frontend Navigation 159 Text-To-SQL 157 Vulnerability Detection 116 Others 106 3.3 Code Agents 91 2.1 Base LLMs and Pretraining Strategies 90 Code Generation 85 Code Commenting and Summarization 83 Test Generation 78 Malicious Code Detection 75 Program Repair 74 2.4 (Instruction) Fine-Tuning on Code 69 3.1 Coding for Reasoning 66 3.4 Interactive Coding 55 Security and Vulnerabilities 55 2.3 General Pretraining on Code 50 Code Translation 45 Code Review 43 Frontend Development 42 Repository-Level Coding 38 2.5 Reinforcement Learning on Code 38 Code Similarity and Embedding (Clone Detection, Code Search) 35 Correctness 33 5.2 Benchmarks 30 Requirement Engineering 28 Program Proof 26 Log Analysis 25 AI-Generated Code Detection 25 Automated Machine Learning 24 Compiler Optimization 23 Binary Analysis and Decompilation 23 Code Refactoring and Migration 23 Code RAG 23 Issue Resolution 20 4.2 Benchmarks 20 Efficiency 19 3.2 Code Simulation 17 Software Configuration 16 Code QA & Reasoning 16 Robustness 15 Oracle Generation 15 Code Ranking 14 2.2 Existing LLM Adapted to Code 13 Fuzz Testing 12 Hallucination 12 Interpretability 11 API Usage 10 Software Modeling 10 Commit Message Generation 8 Bias 7 Mutation Testing 7 Privacy 7 8.1 Pretraining 6 Type Prediction 4 6.2 Benchmarks 4 Contamination 3

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