LLM-Assisted Op-Amp Behavioral-Level Design via Agentic Human-Mimicking Reasoning

TL;DR

This paper introduces White-Op, a framework using large language models to assist in behavioral-level op-amp design through symbolic reasoning, optimization, and iterative refinement, achieving interpretable results.

Contribution

It presents a novel LLM-assisted symbolic reasoning approach for op-amp design, combining human-mimicking reasoning with automated verification and refinement.

Findings

White-Op achieves 8.52% average prediction error.

It successfully designs all tested topologies with retained functionality.

Black-box methods failed in 5 to 7 topologies.

Abstract

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.