White-Box Op-Amp Design via Human-Mimicking Reasoning

TL;DR

White-Op presents a human-mimicking, interpretable workflow for op-amp design that converts implicit expert reasoning into explicit hypothetical constraints, enabling tractable TF simplification, approximate PZ extraction, and deliberate PZ positioning. It couples a white-box optimization, solved with gekko, to behavioral-level simulations and a corrective feedback loop, ensuring designs remain valid through transistor-level mapping. Across 9 op-amp topologies, White-Op achieves reliable behavioral-level designs with an average Th→BL error of 8.52% and robust TL performance, outperforming a black-box baseline in interpretability and design resilience. The approach is open-sourced and scalable to other topology families, offering a practical path toward trustworthy, human-understandable analog design automation.

Abstract

This brief proposes \emph{White-Op}, an interpretable operational amplifier (op-amp) parameter design framework based on the human-mimicking reasoning of large-language-model agents. We formalize the implicit human reasoning mechanism into explicit steps of \emph{\textbf{introducing hypothetical constraints}}, and develop an iterative, human-like \emph{\textbf{hypothesis-verification-decision}} workflow. Specifically, the agent is guided to introduce hypothetical constraints to derive and properly regulate positions of symbolically tractable poles and zeros, thus formulating a closed-form mathematical optimization problem, which is then solved programmatically and verified via simulation. Theory-simulation result analysis guides the decision-making for refinement. Experiments on 9 op-amp topologies show that, unlike the uninterpretable black-box baseline which finally fails in 5 topologies, White-Op achieves reliable, interpretable behavioral-level designs with only 8.52\% theoretical prediction error and the design functionality retains after transistor-level mapping for all topologies. White-Op is open-sourced at \textcolor{blue}{https://github.com/zhchenfdu/whiteop}.

Figures (2)

• Figure 1: Behavioral-level modeling. Fig. \ref{['figure:basic_opa_bl']} is an MZC topology example (loads omitted). Fig. \ref{['figure:basic_opa_ssm']} shows the small-signal model.
• Figure 2: The overall workflow of White-Op.