HeaRT: A Hierarchical Circuit Reasoning Tree-Based Agentic Framework for AMS Design Optimization
This addresses the problem of inefficient and non-adaptive circuit design optimization for engineers, representing a novel method for a known bottleneck rather than incremental.
The paper tackles the problem of AI-driven AMS design automation being constrained by dataset reliance, poor transferability, and lack of adaptability by proposing HeaRT, a hierarchical circuit reasoning tree-based agentic framework, which achieves >97% reasoning accuracy and >98% Pass@1 performance on a 40-circuit benchmark while operating at <0.5x real-time token budget of SOTA baselines.
Conventional AI-driven AMS design automation algorithms remain constrained by their reliance on high-quality datasets to capture underlying circuit behavior, coupled with poor transferability across architectures, and a lack of adaptive mechanisms. This work proposes HeaRT, a foundational reasoning engine for automation loops and a first step toward intelligent, adaptive, human-style design optimization. HeaRT consistently demonstrates reasoning accuracy >97% and Pass@1 performance >98% across our 40-circuit benchmark repository, even as circuit complexity increases, while operating at <0.5x real-time token budget of SOTA baselines. Our experiments show that HeaRT yields >3x faster convergence in both sizing and topology design adaptation tasks across diverse optimization approaches, while preserving prior design intent.