docs: update papers

Nora · Nora · commit 78544b4bbfe9 · 2026-04-01T17:16:28.000+08:00
diff --git a/.github/ISSUE_TEMPLATE/missing_paper.yml b/.github/ISSUE_TEMPLATE/missing_paper.yml
@@ -71,6 +71,7 @@ body:
         - data_synthesis
         - data_analysis
         - methods_analysis
+        - others
     validations:
       required: true
   - type: input
diff --git a/README.md b/README.md
diff --git a/app/data/papers_data_collection.yaml b/app/data/papers_data_collection.yaml
@@ -10,6 +10,28 @@
     arxiv: https://arxiv.org/abs/2603.13023
     github: https://github.com/GAIR-NLP/OpenSWE
     huggingface: https://huggingface.co/datasets/GAIR/OpenSWE
+- short_name: SWE-Next
+  title: 'SWE-Next: Scalable Real-World Software Engineering Tasks for Agents'
+  authors: Jiarong Liang, Zhiheng Lyu, Zijie Liu, Xiangchao Chen, Ping Nie, Kai Zou,
+    Wenhu Chen
+  year: '2026'
+  venue: arXiv preprint arXiv:2603.20691
+  month: 2026-03
+  links:
+    arxiv: https://arxiv.org/abs/2603.20691
+    github: https://github.com/TIGER-AI-Lab/SWE-Next
+- short_name: RepoLaunch
+  title: 'RepoLaunch: Automating Build&Test Pipeline of Code Repositories on ANY Language
+    and ANY Platform'
+  authors: Kenan Li, Rongzhi Li, Linghao Zhang, Qirui Jin, Liao Zhu, Xiaosong Huang,
+    Geng Zhang, Yikai Zhang, Shilin He, Chengxing Xie, Xin Zhang, Zijian Jin, Bowen
+    Li, Chaoyun Zhang, Yu Kang, Yufan Huang, Elsie Nallipogu, Saravan Rajmohan, Qingwei
+    Lin, Dongmei Zhang
+  year: '2026'
+  venue: arXiv preprint arXiv:2603.05026
+  month: 2026-03
+  links:
+    arxiv: https://arxiv.org/abs/2603.05026
 - short_name: DockSmith
   title: 'DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder'
   authors: Jiaran Zhang, Luck Ma, Yanhao Li, Fanqi Wan, Di Qi, Xu Zhao, Jieyi Hou,
@@ -104,3 +126,11 @@
   links:
     arxiv: https://arxiv.org/abs/2505.20411v2
     openreview: https://openreview.net/forum?id=nMpJoVmRy1
+- short_name: SetUpAgent, SWEE-bench, SWA-bench
+  title: Automated Benchmark Generation for Repository-Level Coding Tasks
+  authors: Konstantinos Vergopoulos, Mark Niklas Müller, Martin Vechev
+  year: '2025'
+  venue: arXiv preprint arXiv:2503.07701
+  month: 2025-03
+  links:
+    arxiv: https://arxiv.org/abs/2503.07701
diff --git a/app/data/papers_evaluation_datasets.yaml b/app/data/papers_evaluation_datasets.yaml
@@ -40,6 +40,15 @@
   links:
     arxiv: https://arxiv.org/abs/2603.15401
     github: https://github.com/GeniusHTX/SWE-Skills-Bench
+- short_name: MobileDev-Bench
+  title: 'MobileDev-Bench: A Comprehensive Benchmark for Evaluating Language Models
+    on Mobile Application Development'
+  authors: Moshood A. Fakorede, Krishna Upadhyay, A. B. Siddique, Umar Farooq
+  year: '2026'
+  venue: arXiv preprint arXiv:2603.24946
+  month: 2026-03
+  links:
+    arxiv: https://arxiv.org/abs/2603.24946
 - short_name: SWE Context Bench
   title: 'SWE Context Bench: A Benchmark for Context Learning in Coding'
   authors: Jared Zhu, Minhao Hu, Junde Wu
@@ -219,6 +228,14 @@
   month: 2025-03
   links:
     arxiv: https://arxiv.org/abs/2503.06680v2
+- short_name: SetUpAgent, SWEE-bench, SWA-bench
+  title: Automated Benchmark Generation for Repository-Level Coding Tasks
+  authors: Konstantinos Vergopoulos, Mark Niklas Müller, Martin Vechev
+  year: '2025'
+  venue: arXiv preprint arXiv:2503.07701
+  month: 2025-03
+  links:
+    arxiv: https://arxiv.org/abs/2503.07701
 - short_name: SWE-Lancer
   title: "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World\n        \
     \          Freelance Software Engineering?"
diff --git a/app/data/papers_others.yaml b/app/data/papers_others.yaml
@@ -0,0 +1 @@
+[]
diff --git a/app/data/papers_rl.yaml b/app/data/papers_rl.yaml
@@ -1,3 +1,12 @@
+- short_name: SWE-Fuse
+  title: 'SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning
+    and Entropy-aware RLVR Training'
+  authors: Xin-Cheng Wen, Binbin Chen, Haoxuan Lan, Hang Yu, Peng Di, Cuiyun Gao
+  year: '2026'
+  venue: arXiv preprint arXiv:2603.07927
+  month: 2026-03
+  links:
+    arxiv: https://arxiv.org/abs/2603.07927
 - short_name: SWE-Master
   title: 'SWE-Master: Unleashing the Potential of Software Engineering Agents via
     Post-Training'
diff --git a/app/docs/admin/data.json b/app/docs/admin/data.json
@@ -1,12 +1,61 @@
 {
-  "generated": "2026-03-28",
+  "generated": "2026-04-01",
   "stats": {
-    "total": 204,
-    "data": 53,
-    "methods": 130,
+    "total": 209,
+    "data": 57,
+    "methods": 131,
     "analysis": 23
   },
   "papers": [
+    {
+      "id": 210,
+      "short_name": "RepoLaunch",
+      "title": "RepoLaunch: Automating Build&Test Pipeline of Code Repositories on ANY Language and ANY Platform",
+      "authors": "Kenan Li, Rongzhi Li, Linghao Zhang, Qirui Jin, Liao Zhu, Xiaosong Huang, Geng Zhang, Yikai Zhang, Shilin He, Chengxing Xie, Xin Zhang, Zijian Jin, Bowen Li, Chaoyun Zhang, Yu Kang, Yufan Huang, Elsie Nallipogu, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang",
+      "venue": "arXiv preprint arXiv:2603.05026",
+      "month": "2026-03",
+      "category": "data_collection",
+      "links": {
+        "arxiv": "https://arxiv.org/abs/2603.05026"
+      }
+    },
+    {
+      "id": 209,
+      "short_name": "SWE-Fuse",
+      "title": "SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training",
+      "authors": "Xin-Cheng Wen, Binbin Chen, Haoxuan Lan, Hang Yu, Peng Di, Cuiyun Gao",
+      "venue": "arXiv preprint arXiv:2603.07927",
+      "month": "2026-03",
+      "category": "rl",
+      "links": {
+        "arxiv": "https://arxiv.org/abs/2603.07927"
+      }
+    },
+    {
+      "id": 208,
+      "short_name": "MobileDev-Bench",
+      "title": "MobileDev-Bench: A Comprehensive Benchmark for Evaluating Language Models on Mobile Application Development",
+      "authors": "Moshood A. Fakorede, Krishna Upadhyay, A. B. Siddique, Umar Farooq",
+      "venue": "arXiv preprint arXiv:2603.24946",
+      "month": "2026-03",
+      "category": "evaluation_datasets",
+      "links": {
+        "arxiv": "https://arxiv.org/abs/2603.24946"
+      }
+    },
+    {
+      "id": 207,
+      "short_name": "SWE-Next",
+      "title": "SWE-Next: Scalable Real-World Software Engineering Tasks for Agents",
+      "authors": "Jiarong Liang, Zhiheng Lyu, Zijie Liu, Xiangchao Chen, Ping Nie, Kai Zou, Wenhu Chen",
+      "venue": "arXiv preprint arXiv:2603.20691",
+      "month": "2026-03",
+      "category": "data_collection",
+      "links": {
+        "arxiv": "https://arxiv.org/abs/2603.20691",
+        "github": "https://github.com/TIGER-AI-Lab/SWE-Next"
+      }
+    },
     {
       "id": 206,
       "short_name": "RepoRepair",
@@ -1791,6 +1840,18 @@
         "doi": "http://dx.doi.org/10.1109/ICSE-Companion66252.2025.00075"
       }
     },
+    {
+      "id": 211,
+      "short_name": "SetUpAgent, SWEE-bench, SWA-bench",
+      "title": "Automated Benchmark Generation for Repository-Level Coding Tasks",
+      "authors": "Konstantinos Vergopoulos, Mark Niklas Müller, Martin Vechev",
+      "venue": "arXiv preprint arXiv:2503.07701",
+      "month": "2025-03",
+      "category": "data_collection,evaluation_datasets",
+      "links": {
+        "arxiv": "https://arxiv.org/abs/2503.07701"
+      }
+    },
     {
       "id": 160,
       "short_name": "CoSIL",
diff --git a/app/docs/index.md b/app/docs/index.md
@@ -30,7 +30,7 @@
         <a href="https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution/graphs/contributors" target="_blank">
             <img src="https://img.shields.io/github/contributors/DeepSoftwareAnalytics/Awesome-Issue-Resolution?style=for-the-badge&color=green&logo=github" alt="Contributors">
         </a>
-        <img src="https://img.shields.io/badge/papers-204-green?style=for-the-badge&logo=googlescholar&logoColor=white" alt="Papers Count">
+        <img src="https://img.shields.io/badge/papers-209-green?style=for-the-badge&logo=googlescholar&logoColor=white" alt="Papers Count">
     </div>
     
     <!-- Interactive Exploration Badges -->
@@ -392,6 +392,11 @@ This section includes research works that provide in-depth analysis and discussi
 * **Agents in the Wild** (2025) [![Website](https://img.shields.io/badge/Website-paper-5B9BD5?logo=googlechrome&logoColor=white)](https://insights.logicstar.ai/){: target="_blank" }
 <!-- END PAPERS:methods_analysis -->
 
+### Others
+
+<!-- START PAPERS:others -->
+<!-- END PAPERS:others -->
+
 ---
 
 ## 🚀 Challenges and Opportunities
diff --git a/app/docs/news.md b/app/docs/news.md
@@ -6,16 +6,15 @@
 
 <!-- START_RECENT_PAPERS -->
 - **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) [![GitHub](https://img.shields.io/badge/GitHub-code-181717?logo=github&logoColor=white)](https://github.com/AweAI-Team/BeyondSWE) [![HuggingFace](https://img.shields.io/badge/HuggingFace-model-FFD21E?logo=huggingface&logoColor=black)](https://huggingface.co/datasets/AweAI-Team/BeyondSWE) [![Website](https://img.shields.io/badge/Website-link-5B9BD5?logo=googlechrome&logoColor=white)](https://aweai-team.github.io/BeyondSWE/)
+- **MobileDev-Bench**: MobileDev-Bench: A Comprehensive Benchmark for Evaluating Language Models on Mobile Application Development [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.24946)
 - **RepoRepair**: RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.01048) [![GitHub](https://img.shields.io/badge/GitHub-code-181717?logo=github&logoColor=white)](https://github.com/ZhongQiangDev/RepoRepair)
 - **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)
 - **SWE-Atlas**: SWE-Atlas [![Website](https://img.shields.io/badge/Website-link-5B9BD5?logo=googlechrome&logoColor=white)](https://labs.scale.com/leaderboard/sweatlas-qna)
 - **SWE-CI**: SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.03823) [![GitHub](https://img.shields.io/badge/GitHub-code-181717?logo=github&logoColor=white)](https://github.com/SKYLENAGE-AI/SWE-CI) [![HuggingFace](https://img.shields.io/badge/HuggingFace-model-FFD21E?logo=huggingface&logoColor=black)](https://huggingface.co/datasets/skylenage/SWE-CI)
+- **SWE-Fuse**: SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.07927)
+- **SWE-Next**: SWE-Next: Scalable Real-World Software Engineering Tasks for Agents [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.20691) [![GitHub](https://img.shields.io/badge/GitHub-code-181717?logo=github&logoColor=white)](https://github.com/TIGER-AI-Lab/SWE-Next)
 - **SWE-Skills-Bench**: SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering? [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.15401) [![GitHub](https://img.shields.io/badge/GitHub-code-181717?logo=github&logoColor=white)](https://github.com/GeniusHTX/SWE-Skills-Bench)
 - **OpenSWE**: daVinci-Env: Open SWE Environment Synthesis at Scale [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.13023) [![GitHub](https://img.shields.io/badge/GitHub-code-181717?logo=github&logoColor=white)](https://github.com/GAIR-NLP/OpenSWE) [![HuggingFace](https://img.shields.io/badge/HuggingFace-model-FFD21E?logo=huggingface&logoColor=black)](https://huggingface.co/datasets/GAIR/OpenSWE)
-- **DockSmith**: DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder [![arXiv](https://img.shields.io/badge/arXiv-paper-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2602.00592) [![HuggingFace](https://img.shields.io/badge/HuggingFace-model-FFD21E?logo=huggingface&logoColor=black)](https://huggingface.co/collections/8sj7df9k8m5x8/docksmith)
-- **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)
-- **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) [![GitHub](https://img.shields.io/badge/GitHub-code-181717?logo=github&logoColor=white)](https://github.com/RUCAIBox/SWE-Master)
-- **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) [![GitHub](https://img.shields.io/badge/GitHub-code-181717?logo=github&logoColor=white)](https://github.com/RUCAIBox/SWE-World)
 <!-- END_RECENT_PAPERS -->
 
 ### Recent Updates
diff --git a/app/view/admin/static/js/admin.js b/app/view/admin/static/js/admin.js
@@ -9,6 +9,9 @@ let currentlyEditingCell = null;
 
 // Multi-select state: Map of paper.id → paper object for all checked papers
 const selectedPapers = new Map();
+const PAPER_CATEGORIES = ['sft', 'rl', 'data_collection', 'data_analysis', 'data_synthesis',
+    'evaluation_datasets', 'training_datasets', 'inference_scaling',
+    'methods_analysis', 'workflow', 'tool', 'memory', 'multi_agent', 'single_agent', 'others'];
 
 // Form field definitions for each entity type
 const FORM_FIELDS = {
@@ -19,9 +22,7 @@ const FORM_FIELDS = {
         { name: 'month', label: 'Date (YYYY-MM)', type: 'text', required: true, placeholder: '2026-01' },
         { name: 'venue', label: 'Venue', type: 'text', required: true },
         { name: 'category', label: 'Category', type: 'multiselect', required: true,
-          options: ['sft', 'rl', 'data_collection', 'data_analysis', 'data_synthesis',
-                    'evaluation_datasets', 'training_datasets', 'inference_scaling',
-                    'methods_analysis', 'workflow', 'tool', 'memory', 'multi_agent', 'single_agent'] },
+          options: PAPER_CATEGORIES },
         { name: 'abstract', label: 'Abstract', type: 'textarea', required: false },
         { name: 'arxiv_link', label: 'arXiv Link', type: 'url', required: false },
         { name: 'github_link', label: 'GitHub Link', type: 'url', required: false },
@@ -180,8 +181,7 @@ function initializeFilters() {
     // Initialize category options
     const categorySelect = document.getElementById('filter-category');
     if (categorySelect) {
-        const categories = ['sft', 'rl', 'data_collection', 'data_analysis', 'data_synthesis', 'evaluation_datasets', 'training_datasets', 'inference_scaling', 'methods_analysis', 'workflow', 'tool', 'memory', 'multi_agent', 'single_agent'];
-        categories.forEach(cat => {
+        PAPER_CATEGORIES.forEach(cat => {
             const option = document.createElement('option');
             option.value = cat;
             option.textContent = cat;
@@ -428,7 +428,7 @@ function startInlineEdit(cell) {
         // Category uses dropdown selection
         let categories = [];
         if (itemType === 'papers') {
-            categories = ['sft', 'rl', 'data_collection', 'data_analysis', 'data_synthesis', 'evaluation_datasets', 'training_datasets', 'inference_scaling', 'methods_analysis', 'workflow', 'tool', 'memory', 'multi_agent', 'single_agent'];
+            categories = PAPER_CATEGORIES;
         } else if (itemType === 'datasets') {
             categories = ['single-pl', 'multi-pl'];
         }
diff --git a/app/view/render_papers.py b/app/view/render_papers.py
@@ -21,7 +21,7 @@
 CATEGORIES = [
     "evaluation_datasets", "training_datasets", "data_collection", "data_synthesis",
     "single_agent", "multi_agent", "workflow", "tool", "memory",
-    "sft", "rl", "inference_scaling", "data_analysis", "methods_analysis"
+    "sft", "rl", "inference_scaling", "data_analysis", "methods_analysis", "others"
 ]
 
 # shields.io badge URLs (different platforms use different colors and icons)
diff --git a/app/view/sync_readme.py b/app/view/sync_readme.py
@@ -106,6 +106,11 @@
         "title": "🔍 Methods Analysis",
         "yaml": "papers_methods_analysis.yaml",
         "description": "Comparative analysis of different methods"
+    },
+    "others": {
+        "title": "🧩 Others",
+        "yaml": "papers_others.yaml",
+        "description": "Papers that do not fit existing categories"
     }
 }
 
@@ -281,6 +286,7 @@ def generate_papers_section() -> str:
     
     # Track unique works for accurate count
     unique_papers = set()
+    category_count = 0
     
     for category_id, category_info in CATEGORIES.items():
         yaml_file = category_info["yaml"]
@@ -289,6 +295,7 @@ def generate_papers_section() -> str:
         entries = load_yaml(yaml_path)
         if not entries:
             continue
+        category_count += 1
         
         # Add category title and description
         content.append(f"\n### {category_info['title']}\n")
@@ -318,7 +325,7 @@ def generate_papers_section() -> str:
     
     # Add summary at the beginning with unique count
     total_unique = len(unique_papers)
-    summary = f"\n> **Total: {total_unique} works** across {len(CATEGORIES)} categories\n"
+    summary = f"\n> **Total: {total_unique} works** across {category_count} categories\n"
     content.insert(1, summary)
     
     # Add empty line at the end to separate from comment marker
diff --git a/scripts/add_paper.py b/scripts/add_paper.py
@@ -40,6 +40,7 @@
     "12": ("data_synthesis", "🔬 Data Synthesis Methods"),
     "13": ("data_analysis", "📈 Data Analysis"),
     "14": ("methods_analysis", "🔍 Methods Analysis"),
+    "15": ("others", "🧩 Others"),
 }
 
 
diff --git a/scripts/batch_import.py b/scripts/batch_import.py
@@ -27,7 +27,7 @@
 VALID_CATEGORIES = [
     "evaluation_datasets", "training_datasets", "single_agent", "multi_agent",
     "workflow", "tool", "memory", "sft", "rl", "inference_scaling",
-    "data_collection", "data_synthesis", "data_analysis", "methods_analysis"
+    "data_collection", "data_synthesis", "data_analysis", "methods_analysis", "others"
 ]
 
 
