ORACLE：一种基于多目标强化学习且结合大语言模型引导探索的模拟电路设计优化器
ORACLE: A Multi-Objective Reinforcement Learning-Based Analog Circuit Design Optimizer with Large Language Models-Guided Exploration
查看机构详情
- University of Utah（犹他大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
ORACLE是结合多目标强化学习与大语言模型引导探索的开源模拟电路设计优化框架，可无需重训即生成多权衡设计，运行时间大幅缩短且指标满足度与品质因数优异。
中文摘要 AI 辅助
采用强化学习（RL）的模拟电路设计自动化已成为减少人工工作量的有前景方法，但许多现有基于RL的方法聚焦于单目标优化，即便针对多目标（MO）问题设计的方法，也常将多个设计指标简化为单一标量奖励，这种简化限制了其捕捉竞争目标间真实帕累托权衡的能力，且常导致次优设计；此外，每当所需MO指标改变时要求模型从头重新训练仍是关键局限。为应对这些挑战，本文提出ORACLE，这是一种开源的基于RL的MO模拟电路设计优化框架，它用向量值学习和偏好感知条件替代标量奖励优化，ORACLE是真正的MO模拟电路设计优化器，它用偏好向量指定多个目标的相对权重，使单个训练好的模型无需重新训练即可在不同权衡设置下生成设计；本文还提出两种偏好引导策略，即归一化权重引导和余弦对齐引导，以提升收敛性，此外，本文融入大语言模型（LLM）引导的动作选择机制，以过滤可能导致次优设计或增加运行时间的动作。实验结果显示，在2000个测试用例的多种电路拓扑上，与最先进方法相比，ORACLE将运行时间减少20.4倍至104.4倍，还满足2000个目标指标中的99.9%，且在所得输出指标上的品质因数提升5.1倍至318.6倍。
英文摘要
Analog circuit design automation using reinforcement learning (RL) has emerged as a promising approach for reducing manual effort. However, many existing RL-based methods focus on single-objective optimization. Even methods designed for multi-objective (MO) problems often reduce multiple design specifications to a single scalar reward. This simplification limits the ability to capture the true Pareto trade-off among competing objectives and often leads to suboptimal designs. Moreover, requiring the model to be retrained from scratch whenever the desired MO specifications change remains a key limitation. To address these challenges, we present ORACLE, an open-source RL-based framework for MO analog circuit design optimization that replaces scalar reward optimization with vector-valued learning and preference-aware conditioning. ORACLE represents a true MO analog circuit design optimizer that uses a preference vector to specify the relative weights of multiple objectives, enabling a single trained model to generate designs across diverse trade-off settings without retraining. We further propose two preference-guidance strategies, namely normalized-weight guidance and cosine-aligned guidance, to improve convergence. In addition, we incorporate a large language model (LLM)-guided action selection mechanism to filter actions that are likely to lead to suboptimal designs or increased runtime. Our results show that, on multiple circuit topologies with 2,000 test cases, ORACLE reduces runtime by 20.4x - 104.4x compared to state-of-the-art approaches. It also meets 99.9% of the 2,000 target specifications, and achieves 5.1x - 318.6x better figure of merit in the resulting output specs.
