{"ID":2837786,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.19669","arxiv_id":"2511.19669","title":"HeaRT: A Hierarchical Circuit Reasoning Tree-Based Agentic Framework for AMS Design Optimization","abstract":"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 hierarchical circuit reasoning-based agentic framework for automation loops and a step toward adaptive, human-style design optimization. HeaRT consistently improves F1(subcircuits) by \u003e= 13.5% and F1(loops) by \u003e= 37.8% over few-shot prompting baselines across multiple LLM backbones on our 40-circuit AMS benchmark of flattened SPICE netlists, even as circuit complexity increases. Our experiments further show that HeaRT achieves \u003e= 3x faster convergence in incremental design adaptation tasks under specification shifts across diverse optimization approaches, supporting both topology reconfiguration and sizing.","short_abstract":"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 hierarchical circuit reasoning-based agenti...","url_abs":"https://arxiv.org/abs/2511.19669","url_pdf":"https://arxiv.org/pdf/2511.19669v2","authors":"[\"Souradip Poddar\",\"Chia-Tung Ho\",\"Ziming Wei\",\"Weidong Cao\",\"Haoxing Ren\",\"David Z. Pan\"]","published":"2025-11-24T20:11:06Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}