@inproceedings{zhang-etal-2026-budget,
    title = "Budget-Aware Anytime Reasoning with {LLM}-Synthesized Preference Data",
    author = "Zhang, Xuanming  and
      Ashrafi, Shwan  and
      Mirsaidova, Aziza  and
      Rezaeian, Amir H.  and
      Ballesteros, Miguel  and
      Chilton, Lydia  and
      Yu, Zhou  and
      Roth, Dan",
    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.417/",
    pages = "8587--8599",
    ISBN = "979-8-89176-395-1",
    abstract = "We study the reasoning behavior of large language models (LLMs) under limited computation budgets. In such settings, producing useful partial solutions quickly is often more practical than exhaustive reasoning, which incurs high inference costs. Many real-world tasks, such as trip planning, require models to deliver the best possible output within a fixed reasoning budget. We introduce an anytime reasoning framework and the Anytime Index, a metric that quantifies how effectively solution quality improves as reasoning tokens increase. To further enhance efficiency, we propose an inference-time self-improvement method using LLM-synthesized preference data, where models learn from their own reasoning comparisons to produce better intermediate solutions. Experiments on NaturalPlan (Trip), AIME, and GPQA datasets show consistent gains across Grok-3, GPT-oss, GPT-4.1/4o, and LLaMA models, improving both reasoning quality and efficiency under budget constraints."
}