@inproceedings{feng-etal-2026-stratagem,
    title = "Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play",
    author = "Feng, Xiachong  and
      Yin, Deyi  and
      Feng, Xiaocheng  and
      Jiang, Yi  and
      Qin, Libo  and
      Ye, Yangfan  and
      Huang, Lei  and
      Ma, Weitao  and
      Li, Qiming  and
      Gu, Yuxuan  and
      Qin, Bing  and
      Kong, Lingpeng",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.897/",
    pages = "19595--19614",
    ISBN = "979-8-89176-390-6",
    abstract = "Games offer a compelling paradigm for developing general reasoning capabilities in language models, as they naturally demand strategic planning, probabilistic inference, and adaptive decision-making. However, existing self-play approaches rely solely on terminal game outcomes, providing no mechanism to distinguish transferable reasoning patterns from game-specific heuristics. We present STRATAGEM, which addresses two fundamental barriers to reasoning transfer: domain specificity, where learned patterns remain anchored in game semantics, and contextual stasis, where static game contexts fail to cultivate progressive reasoning. STRATAGEM selectively reinforces trajectories exhibiting abstract, domain-agnostic reasoning through a Reasoning Transferability Coefficient, while incentivizing adaptive reasoning development via a Reasoning Evolution Reward. Experiments across mathematical reasoning, general reasoning, and code generation benchmarks demonstrate substantial improvements, with particularly strong gains on competition-level mathematics where multi-step reasoning is critical. Ablation studies and human evaluation confirm that both components contribute to transferable reasoning."
}