|
12 | 12 | [](https://huggingface.co/papers/2601.11655) |
13 | 13 | [](https://deepsoftwareanalytics.github.io/Awesome-Issue-Resolution/tables/) |
14 | 14 | [](https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution/graphs/contributors) |
15 | | - |
| 15 | + |
16 | 16 |
|
17 | 17 | [**📖 Documentation Website**](https://deepsoftwareanalytics.github.io/Awesome-Issue-Resolution/) | [**📄 Full Paper**](https://deepsoftwareanalytics.github.io/Awesome-Issue-Resolution/paper/) | [**📋 Tables & Resources**](https://deepsoftwareanalytics.github.io/Awesome-Issue-Resolution/tables/) |
18 | 18 |
|
|
30 | 30 |
|
31 | 31 | ## 📖 Abstract |
32 | 32 |
|
33 | | -Based on a systematic review of **203 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. |
| 33 | +Based on a systematic review of **204 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. |
34 | 34 |
|
35 | 35 | ## 📰 News |
36 | 36 |
|
37 | 37 | <!-- START NEWS --> |
38 | | -> If you would like your work to be included in this repository, please cite [](https://deepsoftwareanalytics.github.io/Awesome-Issue-Resolution/cite/) our survey. We monitor citations and will update the repository promptly. |
| 38 | +> We continuously update the paper list in real time. If your work is unintentionally missing, please let us know by opening an issue. You are also welcome to cite [](https://deepsoftwareanalytics.github.io/Awesome-Issue-Resolution/cite/) our survey to support this project. |
39 | 39 |
|
40 | 40 | ### Recent Papers |
41 | 41 |
|
42 | 42 | <!-- START_RECENT_PAPERS --> |
43 | 43 | - **BeyondSWE**: BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? [](https://arxiv.org/abs/2603.03194) [](https://github.com/AweAI-Team/BeyondSWE) [](https://huggingface.co/datasets/AweAI-Team/BeyondSWE) [](https://aweai-team.github.io/BeyondSWE/) |
| 44 | +- **RepoRepair**: RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair [](https://arxiv.org/abs/2603.01048) [](https://github.com/ZhongQiangDev/RepoRepair) |
44 | 45 | - **SWE-Adept**: SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution [](https://arxiv.org/abs/2603.01327) |
45 | 46 | - **SWE-Atlas**: SWE-Atlas [](https://labs.scale.com/leaderboard/sweatlas-qna) |
46 | 47 | - **SWE-CI**: SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration [](https://arxiv.org/abs/2603.03823) [](https://github.com/SKYLENAGE-AI/SWE-CI) [](https://huggingface.co/datasets/skylenage/SWE-CI) |
47 | 48 | - **SWE-Skills-Bench**: SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering? [](https://arxiv.org/abs/2603.15401) [](https://github.com/GeniusHTX/SWE-Skills-Bench) |
48 | 49 | - **OpenSWE**: daVinci-Env: Open SWE Environment Synthesis at Scale [](https://arxiv.org/abs/2603.13023) [](https://github.com/GAIR-NLP/OpenSWE) [](https://huggingface.co/datasets/GAIR/OpenSWE) |
49 | | -- **Closing the Loop**: Closing the Loop: Universal Repository Representation with RPG-Encoder [](https://arxiv.org/abs/2602.02084) [](https://github.com/microsoft/RPG-ZeroRepo) [](https://ayanami2003.github.io/RPG-Encoder/) |
50 | 50 | - **DockSmith**: DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder [](https://arxiv.org/abs/2602.00592) [](https://huggingface.co/collections/8sj7df9k8m5x8/docksmith) |
51 | | -- **Scale-SWE**: Immersion in the GitHub Universe: Scaling Coding Agents to Mastery [](https://arxiv.org/abs/2602.09892) [](https://github.com/AweAI-Team/ScaleSWE) [](https://huggingface.co/collections/AweAI-Team/scale-swe) |
52 | 51 | - **SWE Context Bench**: SWE Context Bench: A Benchmark for Context Learning in Coding [](https://arxiv.org/pdf/2602.08316) |
53 | | -- **SWE-ABS**: SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark [](https://arxiv.org/abs/2603.00520) |
54 | | -- **SWE-Hub**: SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks [](https://arxiv.org/abs/2603.00575) |
55 | 52 | - **SWE-Master**: SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training [](https://arxiv.org/abs/2602.03411) [](https://github.com/RUCAIBox/SWE-Master) |
56 | | -- **SWE-MiniSandbox**: SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents [](https://arxiv.org/abs/2602.11210v1) [](http://github.com/lblankl/SWE-MiniSandbox) |
57 | | -- **SWE-Protégé**: SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents [](https://arxiv.org/abs/2602.22124) |
58 | | -- **SWE-Universe**: SWE-Universe: Scale Real-World Verifiable Environments to Millions [](https://www.arxiv.org/abs/2602.02361) |
59 | 53 | - **SWE-World**: SWE-World: Building Software Engineering Agents in Docker-Free Environments [](https://arxiv.org/abs/2602.03419) [](https://github.com/RUCAIBox/SWE-World) |
60 | | -- **SWE-rebench V2**: SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale [](https://arxiv.org/abs/2602.23866) |
61 | 54 | <!-- END_RECENT_PAPERS --> |
62 | 55 |
|
63 | 56 | ### Recent Updates |
@@ -109,7 +102,7 @@ Based on a systematic review of **203 papers and online resources**, this survey |
109 | 102 | ## 📚 Complete Paper List |
110 | 103 |
|
111 | 104 |
|
112 | | -> **Total: 203 works** across 14 categories |
| 105 | +> **Total: 204 works** across 14 categories |
113 | 106 |
|
114 | 107 |
|
115 | 108 | ### 📊 Evaluation Datasets |
@@ -213,6 +206,7 @@ Based on a systematic review of **203 papers and online resources**, this survey |
213 | 206 | *Methods leveraging external tools* |
214 | 207 |
|
215 | 208 | - `(2026-03)` **SWE-Adept**: SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution [](https://arxiv.org/abs/2603.01327) |
| 209 | +- `(2026-03)` **RepoRepair**: RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair [](https://arxiv.org/abs/2603.01048) [](https://github.com/ZhongQiangDev/RepoRepair) |
216 | 210 | - `(2026-02)` **Closing the Loop**: Closing the Loop: Universal Repository Representation with RPG-Encoder [](https://arxiv.org/abs/2602.02084) [](https://ayanami2003.github.io/RPG-Encoder/) [](https://github.com/microsoft/RPG-ZeroRepo) |
217 | 211 | - `(2026-01)` **SWE-Tester**: SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories [](https://arxiv.org/abs/2601.13713) |
218 | 212 | - `(2025-12)` **GraphLocator**: GraphLocator: Graph-guided Causal Reasoning for Issue Localization [](https://arxiv.org/abs/2512.22469) |
@@ -563,23 +557,23 @@ pip install flask flask-cors sqlalchemy pyyaml requests |
563 | 557 |
|
564 | 558 | # Full update + start admin server |
565 | 559 | # (refreshes news, re-renders README/docs, builds static site, then serves) |
566 | | -python start.py |
| 560 | +python app.py |
567 | 561 |
|
568 | 562 | # Or force re-import from YAML/CSV first |
569 | | -python start.py --init |
| 563 | +python app.py --init |
570 | 564 | ``` |
571 | 565 |
|
572 | 566 | Open **http://localhost:5000/admin** to manage papers, datasets, and methods. |
573 | 567 |
|
574 | 568 | | Command | Description | |
575 | 569 | |---------|-------------| |
576 | | -| `python start.py` | Full update (news + render + build) then start server | |
577 | | -| `python start.py --init` | Re-import from YAML/CSV, then full update + start | |
578 | | -| `python start.py --no-update` | Start server without running update steps | |
579 | | -| `python start.py --port 8080` | Use a custom port | |
580 | | -| `python start.py --news` | Refresh Recent Papers section only and exit | |
581 | | -| `python start.py --render` | Re-render README/docs from DB only and exit | |
582 | | -| `python start.py --build` | Build static site (mkdocs) only and exit | |
| 570 | +| `python app.py` | Full update (news + render + build) then start server | |
| 571 | +| `python app.py --init` | Re-import from YAML/CSV, then full update + start | |
| 572 | +| `python app.py --no-update` | Start server without running update steps | |
| 573 | +| `python app.py --port 8080` | Use a custom port | |
| 574 | +| `python app.py --news` | Refresh Recent Papers section only and exit | |
| 575 | +| `python app.py --render` | Re-render README/docs from DB only and exit | |
| 576 | +| `python app.py --build` | Build static site (mkdocs) only and exit | |
583 | 577 |
|
584 | 578 | --- |
585 | 579 | <!-- END USAGE --> |
|
0 commit comments