@inproceedings{he-etal-2026-swe,
    title = "{SWE}-{S}wiss: A Multi-Task Fine-Tuning and {RL} Recipe for High-Performance Issue Resolution",
    author = "He, Zhenyu  and
      Yang, Qingping  and
      Shen, Wei  and
      Zhong, Xiaojian  and
      Zhang, Kechi  and
      An, Chenxin  and
      Shi, Wenlei  and
      Cai, Tianle  and
      He, Di  and
      Chen, Jiaze  and
      Xu, Jingjing",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.790/",
    pages = "16102--16114",
    ISBN = "979-8-89176-395-1",
    abstract = "Automated software engineering, particularly resolving real-world issues on benchmarks like SWE-bench, remains a significant challenge for Large Language Models (LLMs). To address this, we introduce SWE-Swiss, a two-phase training recipe that systematically develops these capabilities. Our approach first decomposes issue resolution into three core skills: Localization, Repair, and Unit Test Generation. In the first phase, we perform multi-task Supervised Fine-Tuning (SFT) on three new, meticulously curated datasets to build a versatile foundation. The second phase applies targeted Reinforcement Learning (RL), using direct feedback from test execution to boost the critical skill of code repair. The resulting model, SWE-Swiss-32B, establishes a new state-of-the-art for open-source models in its size class, achieving a 60.2{\%} score on the SWE-bench Verified benchmark and placing it in the same top-tier performance bracket as much larger models. Finally, we show that despite its specialized training, SWE-Swiss-32B demonstrates strong generalization to other common LLM benchmarks. To accelerate research in the community, we are open-sourcing the models and our complete training datasets."
}