Large Language Models (LLMs) have seen increasing use in various software development tasks, especially in code generation. The most advanced recent methods attempt to incorporate feedback from code execution into prompts to help guide LLMs in generating correct code in an iterative process. While effective, these methods could be costly due to numerous interactions with the LLM and extensive token usage. To address this issue, we propose an alternative approach named E volutionary P rompt Eng i neering for C ode ( EPiC ), which leverages a lightweight evolutionary algorithm to refine the original prompts into improved versions that generate high-quality code, with minimal interactions with the LLM. Our evaluation against state-of-the-art (SOTA) LLM-based code generation agents shows that EPiC not only achieves up to 5% improvement in pass@k but is also 1.2–10 times more cost-effective than the baselines.
Taherkhani et al. (Sat,) studied this question.