@inproceedings{cui-etal-2026-reward,
    title = "A Reward-Guided Dual-Phase Framework for Adaptive Inference-Time Reasoning",
    author = "Cui, Yingqian  and
      Dai, Zhenwei  and
      He, Pengfei  and
      He, Bing  and
      Liu, Hui  and
      Shi, Zhan  and
      Tang, Xianfeng  and
      Zeng, Jingying  and
      Wang, Suhang  and
      Xing, Yue  and
      Tang, Jiliang  and
      Dumoulin, Benoit",
    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.511/",
    pages = "10506--10531",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Models (LLMs) have made strong progress in reasoning. To enhance the reasoning performance, a common inference-time approach is tree-based search, which decomposes the reasoning process into multiple steps, expands multiple reasoning paths, and uses reward models to prune and select candidates. However, based on our exploration, the simple decomposition may lead to suboptimal searching efficiency: while planning is generally harder, it is the execution errors that are more likely to propagate to later steps. This indicates that planning and execution play different roles in reasoning and should be treated differently during tree-based search. Given this, to enhance the searching efficiency, we propose a dual-phase test-time scaling framework that separates reasoning into planning and execution, and performs search over each phase independently. To further refine the algorithm, we also introduce a dynamic budget allocation mechanism that adaptively redistributes sampling effort based on reward feedback, allowing early stopping on confident steps and reallocation of computation to more challenging steps. Experiments on both math reasoning and code generation benchmarks demonstrate that our approach consistently improves accuracy while reducing redundant computation."
}