@inproceedings{li-etal-2026-selfbudgeter,
    title = "{S}elf{B}udgeter: Adaptive Token Allocation for Efficient {LLM} Reasoning",
    author = "Li, Zheng  and
      Dong, Qingxiu  and
      Ma, Jingyuan  and
      Zhang, Di  and
      Jia, Kai  and
      Sui, Zhifang",
    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.1063/",
    pages = "21135--21156",
    ISBN = "979-8-89176-395-1",
    abstract = "Recently, large reasoning models demonstrate exceptional performance on various tasks. However, reasoning models always consume excessive tokens even for simple queries, leading to resource waste and prolonged user latency. To address this challenge, we propose SelfBudgeter - a self-adaptive reasoning strategy for efficient and controllable reasoning. Specifically, we first train the model to self-estimate the required reasoning budget based on the query. We then introduce budget-guided GRPO for reinforcement learning, which effectively maintains accuracy while reducing output length. Experimental results demonstrate that SelfBudgeter dynamically allocates budgets according to problem complexity, achieving an average response length compression of 61{\%} on math reasoning tasks while maintaining accuracy. Furthermore, SelfBudgeter allows users to see how long generation will take and decide whether to continue or stop. Additionally, users can directly control the reasoning length by setting token budgets upfront."
}