@inproceedings{zheng-etal-2026-scalebox,
    title = "{S}cale{B}ox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models",
    author = "Zheng, Jiasheng  and
      Zheng, Xin  and
      Cao, Boxi  and
      Wang, Pengbo  and
      Ma, Zhengzhao  and
      Zhu, Qiming  and
      Jiang, Jiazhen  and
      Lu, Yaojie  and
      Lin, Hongyu  and
      Han, Xianpei  and
      Sun, Le",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.30/",
    pages = "307--317",
    ISBN = "979-8-89176-392-0",
    abstract = "Code sandboxes have emerged as a critical infrastructure for advancing the coding capabilities of large language models, providing verifiable feedback for both RL training and evaluation. However, existing systems fail to provide accurate verification and efficiency under high-concurrency workloads. We present ScaleBox, a high-fidelity and scalable system designed to address these limitations in large-scale code training. ScaleBox introduces automated special-judge generation and management, fine-grained parallel execution across test cases with seamless multi-node coordination, and a configuration-driven evaluation suite for reproducible benchmarking. A series of experiments demonstrates that ScaleBox significantly enhances code verification accuracy and efficiency. Our further RLVR experiments show that ScaleBox substantially improves both performance on LiveCodeBench and training stability, significantly outperforming heuristic-matching baselines. By providing a reliable and high-throughput infrastructure, ScaleBox facilitates more effective research and development in large-scale code training."
}