|
25 | 25 |
|
26 | 26 | Based on a systematic review of **176 papers and online resources**, this survey establishes a holistic theoretical framework for Issue Resolution in software engineering. We examine how **Large Language Models (LLMs)** are transforming the automation of GitHub issue resolution. Beyond the theoretical analysis, we have curated a comprehensive collection of datasets and model training resources, which are continuously synchronized with our GitHub repository and project documentation website. |
27 | 27 |
|
| 28 | +<!-- START EXPLORE --> |
28 | 29 | **🔍 Explore This Survey:** |
29 | 30 |
|
30 | | -- 📊 **[Data](#-complete-paper-list)**: Evaluation and training datasets, data collection and synthesis methods |
31 | | -- 🛠️ **[Methods](#-complete-paper-list)**: Training-free (agent/workflow) and training-based (SFT/RL) approaches |
32 | | -- 🔍 **[Analysis](#-complete-paper-list)**: Insights into both data characteristics and method performance |
| 31 | +- 📊 **[Data](#-data)**: Evaluation and training datasets, data collection and synthesis methods |
| 32 | + - [📊 Evaluation Datasets](#-evaluation-datasets) |
| 33 | + - [🎯 Training Datasets](#-training-datasets) |
| 34 | + - [📥 Data Collection Methods](#-data-collection) |
| 35 | + - [🔬 Data Synthesis Methods](#-data-synthesis) |
| 36 | +- 🛠️ **[Methods](#%EF%B8%8F-methods)**: Training-free (agent/workflow) and training-based (SFT/RL) approaches |
| 37 | + - **Training-free Methods** |
| 38 | + - [🤖 Single-Agent Systems](#-single-agent-systems) |
| 39 | + - [👥 Multi-Agent Systems](#-multi-agent-systems) |
| 40 | + - [🔄 Workflow-Based Methods](#-workflow-based-methods) |
| 41 | + - [🛠️ Tool-Augmented Methods](#%EF%B8%8F-tool-augmented-methods) |
| 42 | + - [🧠 Memory-Enhanced Methods](#-memory-enhanced-methods) |
| 43 | + - [⚡ Inference-Time Scaling](#-inference-time-scaling) |
| 44 | + - **Training-based Methods** |
| 45 | + - [📚 Supervised Fine-Tuning (SFT)](#-supervised-fine-tuning-sft) |
| 46 | + - [🎮 Reinforcement Learning (RL)](#-reinforcement-learning-rl) |
| 47 | +- 🔍 **[Analysis](#-analysis)**: Insights into both data characteristics and method performance |
| 48 | + - [📈 Data Analysis](#-data-analysis) |
| 49 | + - [🔍 Methods Analysis](#-methods-analysis) |
33 | 50 | - 📋 **[Tables & Resources](https://deepsoftwareanalytics.github.io/Awesome-Issue-Resolution/tables/)**: Comprehensive statistical tables and resources |
34 | 51 | - 📄 **[Full Paper](https://deepsoftwareanalytics.github.io/Awesome-Issue-Resolution/paper/)**: Read the complete survey paper |
35 | 52 | - 🤝 **[Contributing](#-contributing)**: How to contribute to this project |
| 53 | +<!-- END EXPLORE --> |
36 | 54 |
|
37 | 55 | **🎙️ Interactive Exploration:** |
38 | 56 |
|
|
0 commit comments