@inproceedings{kim-etal-2025-tree,
    title = "Tree-of-Prompts: Abstracting Control-Flow for Prompt Optimization",
    author = "Kim, Jihyuk  and
      Garg, Shubham  and
      Poddar, Lahari  and
      Hwang, Seung-won  and
      Hench, Chris",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.995/",
    pages = "19436--19459",
    ISBN = "979-8-89176-256-5",
    abstract = "Prompt optimization (PO) generates prompts to guide Large Language Models (LLMs) in performing tasks. Existing methods, such as PromptAgent, rely on a single static prompt, which struggles with disjoint cases in complex tasks. Although MoP uses multiple prompts, it fails to account for variations in task complexity. Inspired by programmatic control flow, we introduce a nested if-else structure to address both varying similarities and complexities across diverse cases. We propose Tree-of-Prompts (ToP), which implements this structure by recursively expanding child prompts from a parent prompt. Sibling prompts tackle disjoint cases while inheriting shared similarities from their parent, and handle cases more complex than the parent. Evaluated on Gorilla (understanding), MATH (reasoning), and a subset of BBH benchmarks, ToP outperforms PromptAgent and MoP, with improvements of 1.4{\%} and 4.6{\%} over PromptAgent and 3.2{\%} and 4.5{\%} over MoP, when tested with GPT-4o-mini and Llama 3.2-3B, respectively."
}