Python 2

5. Methods/Models for Downstream Tasks 958 8. Datasets 397 3. When Coding Meets Reasoning 230 2. Models 204 6. Analysis of AI-Generated Code 188 4. Code LLM for Low-Resource, Low-Level, and Domain-Specific Languages 75 7. Human-LLM Interaction 65 4. Datasets 37 News 35 9. Recommended Readings 32 5. Datasets 29 1. Surveys 15 6. Datasets 4 Star History 2 7. User-LLM Interaction 1

8.2 Benchmarks 425 3.5 Frontend Navigation 127 Text-To-SQL 119 Vulnerability Detection 101 Others 98 Malicious Code Detection 75 2.1 Base LLMs and Pretraining Strategies 74 Test Generation 70 Code Generation 69 Program Repair 59 Code Commenting and Summarization 59 3.1 Coding for Reasoning 58 3.3 Code Agents 57 2.4 (Instruction) Fine-Tuning on Code 53 3.4 Interactive Coding 49 Security and Vulnerabilities 43 2.3 General Pretraining on Code 40 Code Translation 39 4.2 Benchmarks 37 Code Review 35 Frontend Development 34 Repository-Level Coding 33 Correctness 32 5.2 Benchmarks 30 Code Similarity and Embedding (Clone Detection, Code Search) 29 Requirement Engineering 28 2.5 Reinforcement Learning on Code 24 Log Analysis 24 Program Proof 22 Binary Analysis and Decompilation 22 AI-Generated Code Detection 17 Compiler Optimization 17 Efficiency 16 Oracle Generation 15 Code RAG 15 3.2 Code Simulation 14 Code Refactoring and Migration 14 2.2 Existing LLM Adapted to Code 13 Software Configuration 13 Automated Machine Learning 13 Code Ranking 12 Fuzz Testing 12 Software Modeling 10 Robustness 9 Interpretability 9 Hallucination 9 API Usage 8 Mutation Testing 7 Bias 7 Privacy 6 Commit Message Generation 5 8.1 Pretraining 5 6.2 Benchmarks 4 Type Prediction 4 Code QA & Reasoning 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