@inproceedings{yang-etal-2026-perfcoder,
    title = "{P}erf{C}oder: Large Language Models for Interpretable Code Performance Optimization",
    author = "Yang, Jiuding  and
      Lu, Shengyao  and
      Liu, Hongxuan  and
      Bagi, Shayan Shirahmad Gale  and
      Fazel, Zahra  and
      Czajkowski, Tomasz  and
      Niu, Di",
    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.675/",
    pages = "13807--13823",
    ISBN = "979-8-89176-395-1",
    abstract = "Large language models (LLMs) have achieved remarkable progress in automatic code generation, yet their ability to produce high-performance code remains limited, despite its importance in real-world software systems. We argue that this limitation stems not only from data scarcity, but more fundamentally from the lack of supervision that guides interpretable and effective performance improvements. We introduce PerfCoder, a family of LLMs designed to generate performance-enhanced code through interpretable and customized optimization strategies. PerfCoder is fine-tuned on curated real-world optimization trajectories with human-readable annotations and further aligned via reinforcement fine-tuning using runtime feedback, enabling it to generate input-specific strategies and apply them directly without iterative refinement. On the PIE code performance benchmark, PerfCoder outperforms all existing models in both runtime speedup and effective optimization rate, demonstrating that code performance optimization requires strategy awareness rather than scale alone. Moreover, PerfCoder produces interpretable feedback that can guide larger LLMs in a planner{--}optimizer workflow, substantially improving the performance of 32B models and GPT-5 on code optimization."
}