基于多目标强化学习与大语言模型的帕累托最优RTL代码生成
原标题：Pareto-Optimal RTL Code Generation via Multi-Objective Reinforcement Learning with Large Language Models
AI 摘要
该论文提出一种基于多目标强化学习的方法，让大语言模型从自然语言规格生成RTL电路时，不再将功耗、性能、面积（PPA）聚合为单一标量奖励，而是优化多次生成所得整个电路集合在PPA目标空间中的质量与多样性。方法包含将帕累托解集覆盖度改进重构为序列生成问题的训练流程，以及基于超体积贡献（HVC）的奖励函数。在RTLLM v2基准上，相对超体积较无PPA优化基线提升13.3个百分点，较单目标强化学习方法提升14.4个百分点，并在电路多样性上表现更优。
正文节选
Pareto-Optimal RTL Code Generation via Multi-Objective Reinforcement Learning with Large Language Models Abstract Recent studies have proposed reinforcement learning with verifiable rewards (RLVR) methods that enable LLMs to generate high-quality RTL circuits from natural-language specifications. Existing approaches optimize circuit PPA (Power, Performance, Area) by aggregating multiple objectives into a single scalar reward, making it difficult to simultaneously generate diverse Pareto-optimal