Thinking Before Running! Efficient Code Generation with Thorough Exploration and Optimal Refinement

Zhang, Xiaoqing, Liu, Yuhan, Sung, Flood, Chen, Xiuying, Yan, Rui

arXiv.org Artificial Intelligence 

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 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. By learning preferences, this approach improves LLM's exploration efficiency, reducing computational costs while maintaining accuracy. ThinkCoder boosts the performance of multiple base LLMs, excelling on benchmarks like HumanEval and MBPP. Compared to SOTA models, it improves Pass@1 by 1.5\% over MapCoder with just 21.7\% of the computation cost. Against AgentCoder, ThinkCoder achieves a 0.6\% 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.