Python 2

5. Methods/Models for Downstream Tasks 986 8. Datasets 417 3. When Coding Meets Reasoning 235 2. Models 208 6. Analysis of AI-Generated Code 192 4. Code LLM for Low-Resource, Low-Level, and Domain-Specific Languages 81 7. Human-LLM Interaction 66 4. Datasets 37 News 35 9. Recommended Readings 32 5. Datasets 29 1. Surveys 16 6. Datasets 4 Star History 2 7. User-LLM Interaction 1

8.2 Benchmarks 444 3.5 Frontend Navigation 133 Text-To-SQL 120 Vulnerability Detection 103 Others 99 Malicious Code Detection 76 2.1 Base LLMs and Pretraining Strategies 75 Code Generation 72 Test Generation 70 Code Commenting and Summarization 66 3.3 Code Agents 61 Program Repair 60 3.1 Coding for Reasoning 58 2.4 (Instruction) Fine-Tuning on Code 55 3.4 Interactive Coding 50 Security and Vulnerabilities 44 2.3 General Pretraining on Code 41 Code Translation 40 4.2 Benchmarks 37 Frontend Development 35 Code Review 35 Repository-Level Coding 34 Correctness 32 5.2 Benchmarks 30 Code Similarity and Embedding (Clone Detection, Code Search) 30 Requirement Engineering 28 Log Analysis 24 2.5 Reinforcement Learning on Code 24 Binary Analysis and Decompilation 22 Program Proof 22 Compiler Optimization 17 AI-Generated Code Detection 17 Code Refactoring and Migration 17 Efficiency 16 Automated Machine Learning 16 Oracle Generation 15 Code RAG 15 3.2 Code Simulation 14 2.2 Existing LLM Adapted to Code 13 Software Configuration 13 Code Ranking 12 Fuzz Testing 12 Robustness 10 Software Modeling 10 Hallucination 10 Interpretability 9 API Usage 8 Privacy 7 Mutation Testing 7 Bias 7 8.1 Pretraining 6 Code QA & Reasoning 6 Commit Message Generation 5 6.2 Benchmarks 4 Type Prediction 4

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