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 **197 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 **198 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
> 🔎 **Browse & Export**: The full paper database is searchable and exportable at **[deepsoftwareanalytics.github.io/Awesome-Issue-Resolution/admin/](https://deepsoftwareanalytics.github.io/Awesome-Issue-Resolution/admin/)** — filter by category, date, or keyword, and export results as CSV.
38
38
39
39
## 📰 News
40
40
41
41
<!-- START NEWS -->
42
-
### This Month's Papers
43
-
44
-
<!-- START_THIS_MONTH -->
45
-
**2 paper(s) — 2026-03**
42
+
### Recent Papers
46
43
44
+
<!-- START_RECENT_PAPERS -->
47
45
-**BeyondSWE**: BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? [](https://arxiv.org/abs/2603.03194)
48
46
-**SWE-Adept**: SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution [](https://arxiv.org/abs/2603.01327)
49
-
<!-- END_THIS_MONTH -->
47
+
-**Closing the Loop**: Closing the Loop: Universal Repository Representation with RPG-Encoder [](https://arxiv.org/abs/2602.02084)
48
+
-**Rust-SWE-bench**: Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents [](https://arxiv.org/abs/2602.22764)
49
+
-**Scale-SWE**: Immersion in the GitHub Universe: Scaling Coding Agents to Mastery [](https://arxiv.org/abs/2602.09892)
50
+
-**SWE Context Bench**: SWE Context Bench: A Benchmark for Context Learning in Coding [](https://arxiv.org/pdf/2602.08316)
-**SWE-Bench Mobile**: SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications? [](https://arxiv.org/abs/2602.09540)
53
+
-**SWE-Hub**: SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks [](https://arxiv.org/abs/2603.00575)
54
+
-**SWE-Master**: SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training [](https://arxiv.org/abs/2602.03411)
55
+
-**SWE-MiniSandbox**: SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents [](https://arxiv.org/abs/2602.11210v1)
56
+
-**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)
57
+
-**SWE-Universe**: SWE-Universe: Scale Real-World Verifiable Environments to Millions [](https://www.arxiv.org/abs/2602.02361)
58
+
-**SWE-World**: SWE-World: Building Software Engineering Agents in Docker-Free Environments [](https://arxiv.org/abs/2602.03419)
59
+
-**SWE-rebench V2**: SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale [](https://arxiv.org/abs/2602.23866)
60
+
<!-- END_RECENT_PAPERS -->
50
61
51
62
### Recent Updates
52
63
@@ -96,7 +107,7 @@ Based on a systematic review of **197 papers and online resources**, this survey
96
107
## 📚 Complete Paper List
97
108
98
109
99
-
> **Total: 197 works** across 14 categories
110
+
> **Total: 198 works** across 14 categories
100
111
101
112
102
113
### 📊 Evaluation Datasets
@@ -107,6 +118,7 @@ Based on a systematic review of **197 papers and online resources**, this survey
107
118
-`(2026-02)`**SWE Context Bench**: SWE Context Bench: A Benchmark for Context Learning in Coding [](https://arxiv.org/pdf/2602.08316)
-`(2026-02)`**Rust-SWE-bench**: Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents [](https://arxiv.org/abs/2602.22764)[](https://github.com/GhabiX/Rust-SWE-Bench)
121
+
-`(2026-02)`**SWE-Bench Mobile**: SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications? [](https://arxiv.org/abs/2602.09540)[](https://swebenchmobile.com/)
110
122
-`(2025-12)`**SWE-InfraBench**: SWE-InfraBench: Evaluating Language Models on Cloud Infrastructure Code [](https://openreview.net/forum?id=XX0ciUwfXa)
0 commit comments