Skip to content

Commit 8423805

Browse files
committed
docs: update papers
1 parent a1461ef commit 8423805

File tree

17 files changed

+290
-83
lines changed

17 files changed

+290
-83
lines changed

README.md

Lines changed: 21 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@
1212
[![Hugging Face](https://img.shields.io/badge/HF_Paper-2601.11655-FFD21E?style=for-the-badge&logo=huggingface&logoColor=000)](https://huggingface.co/papers/2601.11655)
1313
[![Tables](https://img.shields.io/badge/TABLES-Statistics-blue?style=for-the-badge&logo=databricks)](https://deepsoftwareanalytics.github.io/Awesome-Issue-Resolution/tables/)
1414
[![Contributors](https://img.shields.io/github/contributors/DeepSoftwareAnalytics/Awesome-Issue-Resolution?style=for-the-badge&color=green&logo=github)](https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution/graphs/contributors)
15-
![Papers Count](https://img.shields.io/badge/papers-197-green?style=for-the-badge&logo=googlescholar&logoColor=white)
15+
![Papers Count](https://img.shields.io/badge/papers-198-green?style=for-the-badge&logo=googlescholar&logoColor=white)
1616

1717
[**📖 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/)
1818

@@ -32,21 +32,32 @@
3232

3333
## 📖 Abstract
3434

35-
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.
3636

3737
> 🔎 **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.
3838
3939
## 📰 News
4040

4141
<!-- START NEWS -->
42-
### This Month's Papers
43-
44-
<!-- START_THIS_MONTH -->
45-
**2 paper(s) — 2026-03**
42+
### Recent Papers
4643

44+
<!-- START_RECENT_PAPERS -->
4745
- **BeyondSWE**: BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.03194)
4846
- **SWE-Adept**: SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.01327)
49-
<!-- END_THIS_MONTH -->
47+
- **Closing the Loop**: Closing the Loop: Universal Repository Representation with RPG-Encoder [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2602.02084)
48+
- **Rust-SWE-bench**: Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2602.22764)
49+
- **Scale-SWE**: Immersion in the GitHub Universe: Scaling Coding Agents to Mastery [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2602.09892)
50+
- **SWE Context Bench**: SWE Context Bench: A Benchmark for Context Learning in Coding [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/pdf/2602.08316)
51+
- **SWE-ABS**: SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.00520)
52+
- **SWE-Bench Mobile**: SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications? [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2602.09540)
53+
- **SWE-Hub**: SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.00575)
54+
- **SWE-Master**: SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2602.03411)
55+
- **SWE-MiniSandbox**: SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](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 [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2602.22124)
57+
- **SWE-Universe**: SWE-Universe: Scale Real-World Verifiable Environments to Millions [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://www.arxiv.org/abs/2602.02361)
58+
- **SWE-World**: SWE-World: Building Software Engineering Agents in Docker-Free Environments [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2602.03419)
59+
- **SWE-rebench V2**: SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2602.23866)
60+
<!-- END_RECENT_PAPERS -->
5061

5162
### Recent Updates
5263

@@ -96,7 +107,7 @@ Based on a systematic review of **197 papers and online resources**, this survey
96107
## 📚 Complete Paper List
97108

98109

99-
> **Total: 197 works** across 14 categories
110+
> **Total: 198 works** across 14 categories
100111
101112

102113
### 📊 Evaluation Datasets
@@ -107,6 +118,7 @@ Based on a systematic review of **197 papers and online resources**, this survey
107118
- `(2026-02)` **SWE Context Bench**: SWE Context Bench: A Benchmark for Context Learning in Coding [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/pdf/2602.08316)
108119
- `(2026-02)` **SWE-ABS**: SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.00520)
109120
- `(2026-02)` **Rust-SWE-bench**: Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2602.22764) [![GitHub](https://img.shields.io/badge/GitHub-repo-24292F?logo=github&logoColor=white)](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? [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2602.09540) [![Website](https://img.shields.io/badge/Website-paper-5B9BD5?logo=googlechrome&logoColor=white)](https://swebenchmobile.com/)
110122
- `(2025-12)` **SWE-InfraBench**: SWE-InfraBench: Evaluating Language Models on Cloud Infrastructure Code [![OpenReview](https://img.shields.io/badge/OpenReview-paper-8C1B13?logo=openreview&logoColor=white)](https://openreview.net/forum?id=XX0ciUwfXa)
111123
- `(2025-12)` **SWE-EVO**: SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2512.18470)
112124
- `(2025-11)` **SWE-Sharp-Bench**: SWE-Sharp-Bench: A Reproducible Benchmark for C# Software Engineering Tasks [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2511.02352)
@@ -556,7 +568,7 @@ Open **http://localhost:5000/admin** to manage papers, datasets, and methods.
556568
| `python start.py --init` | Re-import from YAML/CSV, then full update + start |
557569
| `python start.py --no-update` | Start server without running update steps |
558570
| `python start.py --port 8080` | Use a custom port |
559-
| `python start.py --news` | Refresh This Month's Papers only and exit |
571+
| `python start.py --news` | Refresh Recent Papers section only and exit |
560572
| `python start.py --render` | Re-render README/docs from DB only and exit |
561573
| `python start.py --build` | Build static site (mkdocs) only and exit |
562574

admin/static/js/admin.js

Lines changed: 34 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -648,7 +648,8 @@ function renderPapersTable(items) {
648648
<input type="checkbox" class="paper-checkbox" id="select-all-cb"
649649
title="Select all" ${allChecked ? 'checked' : ''}
650650
onchange="toggleSelectAll(this)">
651-
</th>`;
651+
</th>
652+
<th title="Pin to Recent Papers section">Featured</th>`;
652653

653654
sortableColumns.forEach(col => {
654655
if (col.sortable) {
@@ -669,12 +670,18 @@ function renderPapersTable(items) {
669670
const displayMonth = paper.month ? paper.month.replace('-', '.') : '';
670671
const monthValue = paper.month || '';
671672
const checked = selectedPapers.has(paper.id) ? 'checked' : '';
673+
const featuredClass = paper.featured ? 'featured-star active' : 'featured-star';
674+
const featuredTitle = paper.featured ? 'Remove from Recent Papers' : 'Pin to Recent Papers';
672675
html += `
673-
<tr data-id="${paper.id}" data-type="papers" class="${selectedPapers.has(paper.id) ? 'row-selected' : ''}">
676+
<tr data-id="${paper.id}" data-type="papers" class="${selectedPapers.has(paper.id) ? 'row-selected' : ''}${paper.featured ? ' row-featured' : ''}">
674677
<td class="cb-col">
675678
<input type="checkbox" class="paper-checkbox" data-id="${paper.id}"
676679
${checked} onchange="togglePaperSelection(this, ${paper.id})">
677680
</td>
681+
<td class="featured-col">
682+
<button class="${featuredClass}" data-id="${paper.id}"
683+
title="${featuredTitle}" onclick="toggleFeatured(${paper.id}, this)">★</button>
684+
</td>
678685
<td><span class="badge badge-primary">${paper.short_name}</span></td>
679686
<td class="editable-cell truncate" data-field="title" data-value="${escapeHtml(paper.title)}" title="${paper.title}">${paper.title}</td>
680687
<td class="editable-cell truncate" data-field="authors" data-value="${escapeHtml(paper.authors)}" title="${paper.authors}">${paper.authors}</td>
@@ -695,6 +702,31 @@ function renderPapersTable(items) {
695702
return html;
696703
}
697704

705+
706+
// Toggle featured status for a paper
707+
function toggleFeatured(paperId, btn) {
708+
fetch(`${API_BASE}/papers/${paperId}/toggle-featured`, { method: 'POST' })
709+
.then(r => r.json())
710+
.then(data => {
711+
if (data.error) { showToast(data.error, 'error'); return; }
712+
const row = btn.closest('tr');
713+
if (data.featured) {
714+
btn.classList.add('active');
715+
btn.title = 'Remove from Recent Papers';
716+
row.classList.add('row-featured');
717+
} else {
718+
btn.classList.remove('active');
719+
btn.title = 'Pin to Recent Papers';
720+
row.classList.remove('row-featured');
721+
}
722+
// Update local data cache
723+
const paper = currentData.find(p => p.id === paperId);
724+
if (paper) paper.featured = data.featured;
725+
showToast(data.featured ? '★ Added to Recent Papers' : '☆ Removed from Recent Papers', 'success');
726+
})
727+
.catch(() => showToast('Failed to update featured status', 'error'));
728+
}
729+
698730
// Attach column sort listeners
699731
function attachColumnSortListeners(tableType) {
700732
const headers = document.querySelectorAll('.sortable-header');

admin/templates/papers.html

Lines changed: 17 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -249,6 +249,23 @@
249249
.paper-checkbox { width: 16px; height: 16px; cursor: pointer; accent-color: #667eea; }
250250
tr.row-selected { background: #f0f0ff !important; }
251251

252+
/* Featured star column */
253+
.featured-col { width: 52px; text-align: center; padding: 0 4px !important; }
254+
.featured-star {
255+
background: none;
256+
border: none;
257+
font-size: 18px;
258+
cursor: pointer;
259+
color: #ccc;
260+
line-height: 1;
261+
padding: 2px 4px;
262+
border-radius: 4px;
263+
transition: color 0.2s, transform 0.15s;
264+
}
265+
.featured-star:hover { color: #f5a623; transform: scale(1.2); }
266+
.featured-star.active { color: #f5a623; }
267+
tr.row-featured { background: #fffbf0 !important; }
268+
252269
.badge-primary {
253270
background: #e3f2fd;
254271
color: #1976d2;

controllers/api_controller.py

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -167,6 +167,21 @@ def update_paper(paper_id):
167167
return jsonify({'error': str(e)}), 400
168168

169169

170+
@api.route('/papers/<int:paper_id>/toggle-featured', methods=['POST'])
171+
def toggle_featured(paper_id):
172+
"""Toggle the featured flag on a paper"""
173+
paper = session.query(Paper).get(paper_id)
174+
if not paper:
175+
return jsonify({'error': 'Paper not found'}), 404
176+
try:
177+
paper.featured = not bool(paper.featured)
178+
session.commit()
179+
return jsonify({'id': paper.id, 'featured': bool(paper.featured)})
180+
except Exception as e:
181+
session.rollback()
182+
return jsonify({'error': str(e)}), 400
183+
184+
170185
@api.route('/papers/<int:paper_id>', methods=['DELETE'])
171186
def delete_paper(paper_id):
172187
"""Delete a paper"""

data/papers_evaluation_datasets.yaml

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -39,6 +39,17 @@
3939
links:
4040
arxiv: https://arxiv.org/abs/2602.22764
4141
github: https://github.com/GhabiX/Rust-SWE-Bench
42+
- short_name: SWE-Bench Mobile
43+
title: 'SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level
44+
Mobile Applications?'
45+
authors: Muxin Tian, Zhe Wang, Blair Yang, Zhenwei Tang, Kunlun Zhu, Honghua Dong,
46+
Hanchen Li, Xinni Xie, Guangjing Wang, Jiaxuan You
47+
year: '2026'
48+
venue: arXiv preprint arXiv:2602.09540
49+
month: 2026-02
50+
links:
51+
arxiv: https://arxiv.org/abs/2602.09540
52+
website: https://swebenchmobile.com/
4253
- short_name: SWE-InfraBench
4354
title: 'SWE-InfraBench: Evaluating Language Models on Cloud Infrastructure Code'
4455
authors: Natalia Tarasova, Enrique Balp-Straffon, Aleksei Iancheruk, Yevhenii Sielskyi,

database/migrate.py

Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -352,6 +352,20 @@ def migrate_table5_foundation_models():
352352
print(f"[OK] Migrated {count} foundation models")
353353

354354

355+
def add_missing_columns():
356+
"""Add any columns that exist in the model but are missing from the DB (safe to re-run)."""
357+
from models import get_engine
358+
import sqlalchemy as sa
359+
engine = get_engine()
360+
with engine.connect() as conn:
361+
inspector = sa.inspect(engine)
362+
existing = {col['name'] for col in inspector.get_columns('papers')}
363+
if 'featured' not in existing:
364+
conn.execute(sa.text('ALTER TABLE papers ADD COLUMN featured BOOLEAN DEFAULT 0'))
365+
conn.commit()
366+
print("[OK] Added 'featured' column to papers table")
367+
368+
355369
def main():
356370
print("\n" + "="*70)
357371
print(" Data Migration: CSV/YAML → SQLite")
@@ -360,6 +374,10 @@ def main():
360374
# Initialize database
361375
print("[INFO] Initializing database...")
362376
init_db()
377+
378+
# Add any new columns to existing tables
379+
print("[INFO] Checking for schema updates...")
380+
add_missing_columns()
363381

364382
# Migrate data
365383
print("\n[INFO] Migrating papers from YAML files...")

docs/admin/data.json

Lines changed: 15 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,8 @@
11
{
22
"generated": "2026-03-05",
33
"stats": {
4-
"total": 197,
5-
"data": 49,
4+
"total": 198,
5+
"data": 50,
66
"methods": 128,
77
"analysis": 21
88
},
@@ -34,6 +34,19 @@
3434
"arxiv": "https://arxiv.org/abs/2603.01327"
3535
}
3636
},
37+
{
38+
"id": 199,
39+
"short_name": "SWE-Bench Mobile",
40+
"title": "SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications?",
41+
"authors": "Muxin Tian, Zhe Wang, Blair Yang, Zhenwei Tang, Kunlun Zhu, Honghua Dong, Hanchen Li, Xinni Xie, Guangjing Wang, Jiaxuan You",
42+
"venue": "arXiv preprint arXiv:2602.09540",
43+
"month": "2026-02",
44+
"category": "evaluation_datasets",
45+
"links": {
46+
"arxiv": "https://arxiv.org/abs/2602.09540",
47+
"website": "https://swebenchmobile.com/"
48+
}
49+
},
3750
{
3851
"id": 198,
3952
"short_name": "Rust-SWE-bench",

docs/admin/index.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -40,7 +40,7 @@ Then open **[http://localhost:5000/admin](http://localhost:5000/admin)** in your
4040
| `python start.py` | Full update + start server (port 5000) |
4141
| `python start.py --init` | Re-import from YAML/CSV, then full update + start |
4242
| `python start.py --no-update` | Start server immediately without update steps |
43-
| `python start.py --news` | Refresh "This Month's Papers" only |
43+
| `python start.py --news` | Refresh "Recent Papers" section only |
4444
| `python start.py --render` | Re-render README/docs from DB only |
4545
| `python start.py --build` | Build static site only |
4646

docs/index.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@
3030
<a href="https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution/graphs/contributors" target="_blank">
3131
<img src="https://img.shields.io/github/contributors/DeepSoftwareAnalytics/Awesome-Issue-Resolution?style=for-the-badge&color=green&logo=github" alt="Contributors">
3232
</a>
33-
<img src="https://img.shields.io/badge/papers-197-green?style=for-the-badge&logo=googlescholar&logoColor=white" alt="Papers Count">
33+
<img src="https://img.shields.io/badge/papers-198-green?style=for-the-badge&logo=googlescholar&logoColor=white" alt="Papers Count">
3434
</div>
3535

3636
<!-- Interactive Exploration Badges -->

0 commit comments

Comments
 (0)