@inproceedings{zhang-etal-2025-thinking,
    title = "Thinking Before Running! Efficient Code Generation with Thorough Exploration and Optimal Refinement",
    author = "Zhang, Xiaoqing  and
      Liu, Yuhan  and
      Sung, Flood  and
      Chen, Xiuying  and
      Shang, Shuo  and
      Yan, Rui",
    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/ingestion-acl-25/2025.findings-acl.1195/",
    pages = "23268--23281",
    ISBN = "979-8-89176-256-5",
    abstract = "Code generation is crucial in software engineering for automating the coding process efficiently. While test-time computation methods show promise, they suffer from high latency due to multiple computation rounds.To overcome this, we introduce \textbf{ThinkCoder}, a framework that combines thorough exploration with optimal refinement.The exploration phase diversifies the solution space by searching for potential solutions, followed by a refinement phase that enhances precision.This approach allows us to select the best solution through careful consideration before taking action, avoiding excessive trial and error.To further minimize test-time computation overhead, we introduce preference-driven optimization with Reinforced Self-Training (ReST), which uses exploration trajectories from ThinkCoder to guide LLM{'}s evolution.This approach enhances LLM{'}s exploration efficiency via preference learning, cutting costs while maintaining accuracy.ThinkCoder boosts the performance with a single LLM, excelling on benchmarks like HumanEval and MBPP. Compared to SOTA models, it improves Pass@1 by 3.0{\%} over MapCoder with just 6.4{\%} of the computation cost.Against AgentCoder, ThinkCoder achieves a 0.5{\%} higher Pass@1 after 2 rounds, outperforming AgentCoder{'}s 5 rounds.Additionally, ReST with success trajectories enhances efficiency, allowing models like LLaMA2-7B to achieve competitive results using only 20{\%} of the computational resources. These results highlight the framework{'}s effectiveness and scalability."
}