用大模型模拟人类设计思维，自动优化运算放大器行为级参数。
LLM-Assisted Op-Amp Behavioral-Level Design via Agentic Human-Mimicking Reasoning
- 通过符号推理与数值求解分离，将设计过程转化为可解释的白盒优化问题。
- 平均理论预测误差仅8.52%，所有拓扑在晶体管级映射后仍保持功能正常。
- 适合电路设计自动化、AI辅助硬件开发的研究者和工程师使用。
本文提出White-Op框架，利用大语言模型代理模拟人类推理，实现运算放大器（op-amp）行为级参数设计。采用符号推理-数值求解解耦范式：代理逐步进行符号推理，将设计转化为白盒优化问题，再程序化求解、仿真验证并迭代优化。为引导该过程，隐含的人类设计思维被形式化为转移函数简化、极点零点提取与定位调节中的假设约束引入步骤，将设计启发式转化为数学表达。编程映射协议标准化了符号设计到可执行代码的转换。最后，基于因果关系的优化循环使代理能追溯仿真与理论间的偏差至具体符号推理步骤，并针对性修正直至收敛。在9种运放拓扑上的实验表明，White-Op实现了可解释的行为级设计，平均理论预测误差为8.52%，且所有拓扑在晶体管级映射后均保留电路功能；而黑箱基线方法在5至7种拓扑上失败。项目开源地址：https://github.com/zhchenfdu/whiteop。
原文摘要 · Abstract (English)
This paper proposes White-Op, an operational amplifier (op-amp) behavioral-level parameter design framework assisted by the human-mimicking reasoning of large language model agents. A symbolic reasoning-numerical solving decoupled paradigm is adopted: the agent performs step-by-step symbolic reasoning and formulates the design as a white-box optimization problem, which is then solved programmatically, verified via simulation, and refined iteratively. To guide this symbolic design process, implicit human reasoning mechanisms are formalized into explicit steps of introducing hypothetical constraints during transfer function simplification, pole-zero extraction and position regulation, converting design heuristics into mathematical formulations. A programming mapping protocol then standardizes the translation from symbolic designs to executable programs. Finally, a causality-driven refinement loop enables the agent to trace simulation-theory mismatches back to specific symbolic reasoning steps and make targeted corrections iteratively until convergence. Experiments on 9 op-amp topologies demonstrate that White-Op achieves interpretable behavioral-level designs with an average of 8.52\% theoretical prediction error and retains circuit functionality after transistor-level mapping for all topologies, whereas black-box baselines fail in 5 to 7 topologies. White-Op is open-sourced at https://github.com/zhchenfdu/whiteop.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。