You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Based on a systematic review of **186 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.
35
+
Based on a systematic review of **188 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.
36
36
37
37
<!-- START EXPLORE -->
38
38
**🔍 Explore This Survey:**
@@ -67,7 +67,7 @@ Based on a systematic review of **186 papers and online resources**, this survey
67
67
## 📚 Complete Paper List
68
68
69
69
70
-
> **Total: 186 works** across 14 categories
70
+
> **Total: 188 works** across 14 categories
71
71
72
72
73
73
### 📊 Evaluation Datasets
@@ -296,6 +296,7 @@ Based on a systematic review of **186 papers and online resources**, this survey
-**SWE-Master**: SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training (2026) [](https://arxiv.org/abs/2602.03411)[](https://github.com/RUCAIBox/SWE-Master)
298
298
-**SWE-Protégé**: SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents (2026) [](https://arxiv.org/abs/2602.22124)
299
+
-**SWE-MiniSandbox**: SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents (2026) [](https://arxiv.org/abs/2602.11210v1)[](http://github.com/lblankl/SWE-MiniSandbox)
299
300
300
301
### ⚡ Inference-Time Scaling
301
302
@@ -318,6 +319,7 @@ Based on a systematic review of **186 papers and online resources**, this survey
318
319
-**RepoForge**: RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale (2025) [](https://arxiv.org/abs/2508.01550)
319
320
-**Multi-Docker-Eval**: Multi-Docker-Eval: A `Shovel of the Gold Rush' Benchmark on Automatic Environment Building for Software Engineering (2025) [](https://arxiv.org/abs/2512.06915)
320
321
-**DockSmith**: DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder (2026) [](https://arxiv.org/abs/2602.00592)[](https://huggingface.co/collections/8sj7df9k8m5x8/docksmith)
322
+
-**MEnvAgent**: MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering (2026) [](https://arxiv.org/abs/2601.22859)[](https://github.com/ernie-research/MEnvAgent)
Copy file name to clipboardExpand all lines: docs/about.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,7 +2,7 @@
2
2
3
3
## About This Project
4
4
5
-
Based on a systematic review of 186 papers and online resources, this project establishes a holistic theoretical framework for Issue Resolution in software engineering. This website is designed to facilitate efficient literature retrieval and exploration.
5
+
Based on a systematic review of 188 papers and online resources, this project establishes a holistic theoretical framework for Issue Resolution in software engineering. This website is designed to facilitate efficient literature retrieval and exploration.
Based on a systematic review of 186 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](https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution) and project documentation website.
60
+
Based on a systematic review of 188 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](https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution) and project documentation website.
61
61
62
62
**🔍 Explore This Survey:**
63
63
@@ -142,6 +142,7 @@ This section covers the datasets used for evaluation and training, as well as me
142
142
***RepoForge**: RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale (2025) [](https://arxiv.org/abs/2508.01550){: target="_blank" }
143
143
***Multi-Docker-Eval**: Multi-Docker-Eval: A `Shovel of the Gold Rush' Benchmark on Automatic Environment Building for Software Engineering (2025) [](https://arxiv.org/abs/2512.06915){: target="_blank" }
144
144
***DockSmith**: DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder (2026) [](https://arxiv.org/abs/2602.00592){: target="_blank" } [](https://huggingface.co/collections/8sj7df9k8m5x8/docksmith){: target="_blank" }
145
+
***MEnvAgent**: MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering (2026) [](https://arxiv.org/abs/2601.22859){: target="_blank" } [](https://github.com/ernie-research/MEnvAgent){: target="_blank" }
145
146
<!-- END PAPERS:data_collection -->
146
147
147
148
### Data Synthesis
@@ -350,6 +351,7 @@ This section covers both training-free and training-based methods for issue reso
***SWE-Master**: SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training (2026) [](https://arxiv.org/abs/2602.03411){: target="_blank" } [](https://github.com/RUCAIBox/SWE-Master){: target="_blank" }
352
353
***SWE-Protégé**: SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents (2026) [](https://arxiv.org/abs/2602.22124){: target="_blank" }
354
+
***SWE-MiniSandbox**: SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents (2026) [](https://arxiv.org/abs/2602.11210v1){: target="_blank" } [](http://github.com/lblankl/SWE-MiniSandbox){: target="_blank" }
<h2id="about-this-project">About This Project<aclass="headerlink" href="#about-this-project" title="Permanent link">¶</a></h2>
707
-
<p>Based on a systematic review of 186 papers and online resources, this project establishes a holistic theoretical framework for Issue Resolution in software engineering. This website is designed to facilitate efficient literature retrieval and exploration.</p>
707
+
<p>Based on a systematic review of 188 papers and online resources, this project establishes a holistic theoretical framework for Issue Resolution in software engineering. This website is designed to facilitate efficient literature retrieval and exploration.</p>
<p>Based on a systematic review of 186 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 <ahref="https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution">GitHub repository</a> and project documentation website. </p>
1052
+
<p>Based on a systematic review of 188 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 <ahref="https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution">GitHub repository</a> and project documentation website. </p>
1053
1053
<p><strong>🔍 Explore This Survey:</strong></p>
1054
1054
<ul>
1055
1055
<li>📊 <strong><ahref="#data">Data</a></strong>: Evaluation and training datasets, data collection and synthesis methods</li>
<li><strong>RepoForge</strong>: RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale (2025) <ahref="https://arxiv.org/abs/2508.01550" target="_blank"><imgalt="arXiv" src="https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white" /></a></li>
1130
1130
<li><strong>Multi-Docker-Eval</strong>: Multi-Docker-Eval: A `Shovel of the Gold Rush' Benchmark on Automatic Environment Building for Software Engineering (2025) <ahref="https://arxiv.org/abs/2512.06915" target="_blank"><imgalt="arXiv" src="https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white" /></a></li>
1131
1131
<li><strong>DockSmith</strong>: DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder (2026) <ahref="https://arxiv.org/abs/2602.00592" target="_blank"><imgalt="arXiv" src="https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white" /></a><ahref="https://huggingface.co/collections/8sj7df9k8m5x8/docksmith" target="_blank"><imgalt="HuggingFace" src="https://img.shields.io/badge/HuggingFace-dataset-ff7e21?logo=huggingface&logoColor=white" /></a></li>
1132
+
<li><strong>MEnvAgent</strong>: MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering (2026) <ahref="https://arxiv.org/abs/2601.22859" target="_blank"><imgalt="arXiv" src="https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white" /></a><ahref="https://github.com/ernie-research/MEnvAgent" target="_blank"><imgalt="GitHub" src="https://img.shields.io/badge/GitHub-repo-24292F?logo=github&logoColor=white" /></a></li>
<li><strong>SWE-Master</strong>: SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training (2026) <ahref="https://arxiv.org/abs/2602.03411" target="_blank"><imgalt="arXiv" src="https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white" /></a><ahref="https://github.com/RUCAIBox/SWE-Master" target="_blank"><imgalt="GitHub" src="https://img.shields.io/badge/GitHub-repo-24292F?logo=github&logoColor=white" /></a></li>
1343
1344
<li><strong>SWE-Protégé</strong>: SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents (2026) <ahref="https://arxiv.org/abs/2602.22124" target="_blank"><imgalt="arXiv" src="https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white" /></a></li>
1345
+
<li><strong>SWE-MiniSandbox</strong>: SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents (2026) <ahref="https://arxiv.org/abs/2602.11210v1" target="_blank"><imgalt="arXiv" src="https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white" /></a><ahref="http://github.com/lblankl/SWE-MiniSandbox" target="_blank"><imgalt="GitHub" src="https://img.shields.io/badge/GitHub-repo-24292F?logo=github&logoColor=white" /></a></li>
0 commit comments