@inproceedings{wang-etal-2025-exploracoder,
    title = "{E}xplora{C}oder: Advancing Code Generation for Multiple Unseen {API}s via Planning and Chained Exploration",
    author = "Wang, Yunkun  and
      Zhang, Yue  and
      Qin, Zhen  and
      Zhi, Chen  and
      Li, Binhua  and
      Huang, Fei  and
      Li, Yongbin  and
      Deng, Shuiguang",
    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/ingestion-acl-25/2025.acl-long.887/",
    pages = "18124--18145",
    ISBN = "979-8-89176-251-0",
    abstract = "Large language models face intrinsic limitations in coding with APIs that are unseen in their training corpora. As libraries continuously evolve, it becomes impractical to exhaustively retrain LLMs with new API knowledge. This limitation hampers LLMs from solving programming problems which require newly introduced or privately maintained libraries. Inspired by exploratory programming paradigm in human behavior, we propose **ExploraCoder**, a training-free framework that empowers LLMs to invoke multiple unseen APIs in code solution by (1) planning a complex problem into several API invocation subtasks, and (2) experimenting with correct API usage at intermediate steps through a novel chain-of-API-exploration. We conduct evaluation on program synthesizing tasks involving complex API interactions. Experimental results demonstrate that ExploraCoder significantly improves performance for models lacking prior API knowledge, achieving absolute increases of up to 11.99{\%} over retrieval-based approaches and 17.28{\%} over pretraining-based methods in pass@10."
}