做LLM代码生成或提示词工程的开发者，这个框架直接解决了提示词敏感性问题——用RL自动优化提示词，比手动调参高效得多，建议关注其混合动作空间和奖励设计。
研究人员提出一个基于强化学习的框架，将提示词优化建模为序列决策问题。PPO代理通过混合动作空间（直接生成、遗传变异、语义重写）迭代改进提示词，并利用单元测试反馈的奖励信号驱动优化。在MBPP+、HumanEval+和APPS基准上，使用CodeT5+、CodeLLaMA和DeepSeek-Coder作为冻结代码生成器，PPO代理在MBPP+的500任务测试集上分别达到57.58%、64.80%和85.50%的严格Pass@1，优于EPiC、Reflexion和随机混合方法。软Pass@1分别达到67.90%、73.10%和88.20%。结果表明，带形状奖励的强化学习能显著提升LLM代码生成的功能正确性。
Prompt Optimization for LLM Code Generation via Reinforcement Learning
Large Language Models (LLMs) can generate code from natural language, but their performance is highly sensitive to prompt formulation. We propose a reinforcement-learning-based framework that models prompt refinement as a sequential decision-making problem. A Proximal Policy Optimization (PPO) agent iteratively improves prompts using a hybrid action space that combines direct generation, genetic lexical mutation and semantic rewriting, guided by shaped rewards derived from unit-test feedback. We evaluate the framework on MBPP+, HumanEval+, and APPS using CodeT5+, CodeLLaMA, and DeepSeek-Coder as frozen code generators. On the 500-task MBPP+ test set, the PPO agent achieves strict Pass@1 scores of 57.58%, 64.80%, and 85.50%, respectively, outperforming EPiC, Reflexion, and Random-Hybrid. Soft-Pass@1 reaches 67.90%, 73.10%, and 88.20%, respectively. Similar improvements are observed on HumanEval+ and APPS across all backbone models. The results demonstrate that reinforcement learning with shaped test-driven rewards improves functional correctness in LLM-based code generation.