@inproceedings{xu-etal-2026-scaler,
    title = "{SCALER}: Synthetic Scalable Adaptive Learning Environment for Reasoning",
    author = "Xu, Caijun  and
      Xiao, Changyi  and
      Peng, Zhongyuan  and
      Wang, Xinrun  and
      Cao, Yixin",
    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.1596/",
    pages = "31905--31923",
    ISBN = "979-8-89176-395-1",
    abstract = "Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain informative as models evolve. In practice, RL progress often slows when task difficulty becomes poorly aligned with model capability or when training is dominated by a narrow set of recurring problem patterns.To jointly address these issues, we propose \textbf{SCALER} (\textbf{S}ynthetic s\textbf{C}alable \textbf{A}daptive \textbf{L}earning \textbf{E}nvironment for \textbf{R}easoning), a framework that sustains effective learning signals through adaptive environment design.SCALER introduces a scalable synthesis pipeline that converts real-world programming problems into verifiable reasoning environments with controllable difficulty and unbounded instance generation, enabling RL training beyond finite datasets while preserving strong correctness guarantees. Building on this, SCALER further employs an adaptive multi-environment RL strategy that dynamically adjusts instance difficulty and curates the active set of environments to track the model{'}s capability frontier and maintain distributional diversity. This co-adaptation prevents reward sparsity, mitigates overfitting to narrow task patterns, and supports sustained improvement throughout training. Extensive experiments show that SCALER consistently outperforms other RL baselines across diverse reasoning benchmarks and exhibits more stable, long-horizon training dynamics."
}