@inproceedings{xu-etal-2026-adapthink,
    title = "{A}dap{T}hink: Adaptive Thinking Preferences for Reasoning Language Models",
    author = "Xu, Wenyue  and
      Wan, Xu  and
      Wang, Wei  and
      Huang, Wenqi  and
      Yin, Wotao  and
      Zhao, Shengjie  and
      Sun, Mingyang",
    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.477/",
    pages = "9808--9825",
    ISBN = "979-8-89176-395-1",
    abstract = "The slow thinking paradigm has been widely validated to enhance the reasoning capabilities of Large Language Models (LLMs), but it introduces notable reasoning inefficiencies: models often overthink simple tasks while prematurely shifting their reasoning paths when addressing complex problems. To address this, we propose AdapThink, a simple yet efficient framework for adaptive reasoning preference control. Unlike methods imposing uniform length constraints, AdapThink dynamically adjusts reflection preferences based on group-level distributional statistics of reasoning length and reflection intensity. We further introduce a dispersion-based diversity sampling mechanism that maximizes the geometric spread of reasoning patterns, accelerating learning through exposure to diverse problem-solving strategies. Across mathematical reasoning and code generation benchmarks, AdapThink reduces average response length by 17.1{\%}-21.4{\%} while improving performance by 6.12-6.59 points under 32K token budgets, demonstrating superior efficiency and robustness against reward hacking compared to strong baselines."
}