@inproceedings{liu-etal-2025-interactive-expressive,
    title = "Interactive and Expressive Code-Augmented Planning with Large Language Models",
    author = "Liu, Anthony Zhe  and
      Wang, Xinhe  and
      Sansom, Jacob  and
      Fu, Yao  and
      Choi, Jongwook  and
      Sohn, Sungryull  and
      Kim, Jaekyeom  and
      Lee, Honglak",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-long.994/",
    pages = "20330--20354",
    ISBN = "979-8-89176-251-0",
    abstract = "Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making, but often struggle with complex, long-horizon planning tasks. Recent techniques have sought to structure LLM outputs using control flow and code to improve planning performance. However, code-based approaches can be error-prone and insufficient for handling ambiguous or unstructured data. To address these challenges, we propose REPL-Plan, an LLM planning approach that is fully code-expressive (it can utilize all the benefits of code) while also being dynamic (it can flexibly adapt from errors and use the LLM for soft reasoning). In REPL-Plan, an LLM solves tasks by interacting with a Read-Eval-Print Loop (REPL), which iteratively executes and evaluates code, similar to language shells or interactive code notebooks, allowing the model to flexibly correct errors and handle tasks dynamically. We demonstrate that REPL-Plan achieves strong results across various planning domains compared to previous methods."
}