papers_sft.yaml

- short_name: SWE-ZERO to SWE-HERO
  title: 'From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning
    for Software Engineering Agents'
  authors: Nikolai Ludwig, Wasi Uddin Ahmad, Somshubra Majumdar, Boris Ginsburg
  year: '2026'
  venue: arXiv preprint arXiv:2604.01496
  month: 2026-04
  links:
    arxiv: https://arxiv.org/abs/2604.01496
- short_name: OpenSWE
  title: 'daVinci-Env: Open SWE Environment Synthesis at Scale'
  authors: Dayuan Fu, Shenyu Wu, Yunze Wu, Zerui Peng, Yaxing Huang, Jie Sun, Ji Zeng,
    Mohan Jiang, Lin Zhang, Yukun Li, Jiarui Hu, Liming Liu, Jinlong Hou, Pengfei
    Liu
  year: '2026'
  venue: arXiv preprint arXiv:2603.13023
  month: 2026-03
  links:
    arxiv: https://arxiv.org/abs/2603.13023
    github: https://github.com/GAIR-NLP/OpenSWE
    huggingface: https://huggingface.co/datasets/GAIR/OpenSWE
- short_name: Scale-SWE
  title: 'Immersion in the GitHub Universe: Scaling Coding Agents to Mastery'
  authors: Jiale Zhao, Guoxin Chen, Fanzhe Meng, Minghao Li, Jie Chen, Hui Xu, Yongshuai
    Sun, Xin Zhao, Ruihua Song, Yuan Zhang, Peng Wang, Cheng Chen, Jirong Wen, Kai
    Jia
  year: '2026'
  venue: arXiv preprint arXiv:2602.09892
  month: 2026-02
  links:
    arxiv: https://arxiv.org/abs/2602.09892
    github: https://github.com/AweAI-Team/ScaleSWE
    huggingface: https://huggingface.co/collections/AweAI-Team/scale-swe
- short_name: SWE-Lego
  title: 'SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue
    Resolving'
  authors: Chaofan Tao, Jierun Chen, Yuxin Jiang, Kaiqi Kou, Shaowei Wang, Ruoyu Wang,
    Xiaohui Li et al.
  year: '2026'
  venue: arXiv preprint arXiv:2601.01426
  month: 2026-01
  links:
    arxiv: https://arxiv.org/abs/2601.01426
- short_name: SWE-Replay
  title: 'SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents'
  authors: Yifeng Ding, Lingming Zhang
  year: '2026'
  venue: arXiv preprint arXiv:2601.22129
  month: 2026-01
  links:
    arxiv: https://arxiv.org/abs/2601.22129
- short_name: SWE-Compressor
  title: 'Context as a Tool: Context Management for Long-Horizon SWE-Agents'
  authors: Shukai Liu, Jian Yang, Bo Jiang, Yizhi Li, Jinyang Guo, Xianglong Liu,
    Bryan Dai
  year: '2025'
  venue: arXiv preprint arXiv:2512.22087
  month: 2025-12
  links:
    arxiv: https://arxiv.org/abs/2512.22087
- short_name: Devstral
  title: 'Devstral: Fine-tuning Language Models for Coding Agent Applications'
  authors: Abhinav Rastogi, Adam Yang, Albert Q. Jiang, Alexander H. Liu, Alexandre
    Sablayrolles, Amélie Héliou, Amélie Martin et al.
  year: '2025'
  venue: arXiv preprint arXiv:2509.25193
  month: 2025-09
  links:
    arxiv: https://arxiv.org/abs/2509.25193
- short_name: MCTS-Refined CoT
  title: 'MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository
    Issue Resolution'
  authors: Yibo Wang, Zhihao Peng, Ying Wang, Zhao Wei, Hai Yu, Zhiliang Zhu
  year: '2025'
  venue: arXiv preprint arXiv:2506.12728
  month: 2025-06
  links:
    arxiv: https://arxiv.org/abs/2506.12728
- short_name: Search for training
  title: Guided Search Strategies in Non-Serializable Environments with Applications
    to Software Engineering Agents
  authors: Karina Zainullina, Alexander Golubev, Maria Trofimova, Sergei Polezhaev,
    Ibragim Badertdinov, Daria Litvintseva, Simon Karasik et al.
  year: '2025'
  venue: arXiv preprint arXiv:2505.13652
  month: 2025-05
  links:
    arxiv: https://arxiv.org/abs/2505.13652
- short_name: Co-PatcheR
  title: 'Co-PatcheR: Collaborative Software Patching with Component(s)-specific Small
    Reasoning Models'
  authors: Yuheng Tang, Hongwei Li, Kaijie Zhu, Michael Yang, Yangruibo Ding, Wenbo
    Guo
  year: '2025'
  venue: arXiv preprint arXiv:2505.18955
  month: 2025-05
  links:
    arxiv: https://arxiv.org/abs/2505.18955
- short_name: CGM
  title: 'Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level
    Software Engineering Tasks'
  authors: Hongyuan Tao, Ying Zhang, Zhenhao Tang, Hongen Peng, Xukun Zhu, Bingchang
    Liu, Yingguang Yang, Ziyin Zhang, Zhaogui Xu, Haipeng Zhang, Linchao Zhu, Rui
    Wang, Hang Yu, Jianguo Li, Peng Di
  year: '2025'
  venue: arXiv preprint arXiv:2505.16901
  month: 2025-05
  links:
    arxiv: https://arxiv.org/abs/2505.16901
    github: https://github.com/codefuse-ai/CodeFuse-CGM
    huggingface: https://huggingface.co/codefuse-ai/CodeFuse-CGM-72B
- short_name: Thinking Longer
  title: 'Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling
    Test-Time Compute'
  authors: Yingwei Ma, Yongbin Li, Yihong Dong, Xue Jiang, Rongyu Cao, Jue Chen, Fei
    Huang et al.
  year: '2025'
  venue: arXiv preprint arXiv:2503.23803
  month: 2025-03
  links:
    arxiv: https://arxiv.org/abs/2503.23803
- short_name: ReSAT
  title: Repository Structure-Aware Training Makes SLMs Better Issue Resolver
  authors: Zexiong Ma, Shengnan An, Zeqi Lin, Yanzhen Zou, Bing Xie
  year: '2024'
  venue: arXiv preprint arXiv:2412.19031
  month: 2024-12
  links:
    arxiv: https://arxiv.org/abs/2412.19031
- short_name: Scaling data collection
  title: Scaling Data Collection for Training SWE Agents
  authors: Nebius
  year: '2024'
  venue: '2024'
  month: 2024-12
  links:
    website: https://nebius.com/blog/posts/scaling-data-collection-for-training-swe-agents
- short_name: SWE-Gym
  title: Training Software Engineering Agents and Verifiers with SWE-Gym
  authors: Pan, Jiayi, Wang, Xingyao, Neubig, Graham, Jaitly, Navdeep, Ji, Heng, Suhr,
    Alane, Zhang, Yizhe
  year: '2024'
  venue: Forty-second International Conference on Machine Learning
  month: 2024-12
  links:
    arxiv: https://arxiv.org/abs/2412.21139v2
- short_name: Lingma SWE-GPT
  title: 'SWE-GPT: A Process-Centric Language Model for Automated Software Improvement'
  authors: Ma, Yingwei, Cao, Rongyu, Cao, Yongchang, Zhang, Yue, Chen, Jue, Liu, Yibo,
    Liu, Yuchen et al.
  year: '2024'
  venue: Proceedings of the ACM on Software Engineering 2025
  month: 2024-11
  links:
    arxiv: https://arxiv.org/abs/2411.00622
    github: https://github.com/LingmaTongyi/Lingma-SWE-GPT
    doi: https://dl.acm.org/doi/abs/10.1145/3728981
- short_name: CodeXEmbed
  title: 'CodeXEmbed: A Generalist Embedding Model Family for Multilingual and Multi-task
    Code Retrieval'
  authors: Ye Liu, Rui Meng, Shafiq Joty, silvio savarese, Caiming Xiong, Yingbo Zhou,
    Semih Yavuz
  year: '2024'
  venue: Second Conference on Language Modeling 2025
  month: 2024-11
  links:
    arxiv: https://arxiv.org/abs/2411.12644
    openreview: https://openreview.net/forum?id=z3lG70Azbg