AnalogSAGE: Self-evolving Analog Design Multi-Agents with Stratified Memory and Grounded Experience

TL;DR

AnalogSAGE introduces a multi-agent framework with stratified memory and grounded simulation feedback, significantly improving the automation, reliability, and efficiency of analog circuit design across complex specifications.

Contribution

It presents a novel self-evolving multi-agent system with stratified memory layers for iterative analog design, surpassing existing prompt-based methods in automation and success rate.

Findings

Achieves 10× higher overall pass rate in benchmark tests.

Reduces parameter search space by 4× compared to prior frameworks.

Demonstrates effective design automation for complex operational amplifiers.

Abstract

Analog circuit design remains a knowledge- and experience-intensive process that relies heavily on human intuition for topology generation and device parameter tuning. Existing LLM-based approaches typically depend on prompt-driven netlist generation or predefined topology templates, limiting their ability to satisfy complex specification requirements. We propose AnalogSAGE, an open-source self-evolving multi-agent framework that coordinates three-stage agent explorations through four stratified memory layers, enabling iterative refinement with simulation-grounded feedback. To support reproducibility and generality, we release the source code. Our benchmark spans ten specification-driven operational amplifier design problems of varying difficulty, enabling quantitative and cross-task comparison under identical conditions. Evaluated under the open-source SKY130 PDK with ngspice, AnalogSAGE achieves a 10$\times$ overall pass rate, a 48$\times$ Pass@1, and a 4$\times$ reduction in parameter search space compared with existing frameworks, demonstrating that stratified memory and grounded reasoning substantially enhance the reliability and autonomy of analog design automation in practice.