TACS-RF: Tool-driven Agentic Circuit Synthesis of RF and mmWave Modules

arXiv:2610.31882v1 Announce Type: new Abstract: We present the framework of TACS-RF - a Tool-driven Agentic Circuit Synthesis of RF and mmWave modules. In this framework, a large-language-model (LLM) coding agent (Claude Opus 4.8) directly drives industry-standard electronic-design-automation (EDA) tools such as Cadence Virtuoso/Spectre, Calibre, Cadence EMX, and Ansys HFSS to design RF and mmWave modules. We validate the framework through the agentic design of a 240-251 GHz sub-THz transmitter in a 90 nm SiGe BiCMOS process. The agent semi-autonomously designed the sub-blocks including a 60 GHz push-push Colpitts VCO with second-harmonic extraction, multistage differential cascode power drivers, a push-push frequency doubler, a differential bowtie antenna, and all the interstage matching networks. The transmitter chain with parasitic-extracted devices and EM-verified passives delivers +5.1 to +6.3 dBm across an 11 GHz varactor-only tuning range, phase noise of -80 to -88 dBc/Hz at 1 MHz offset while consuming a DC power of 361 mW. We describe the agent-driven design flow and the resulting division of labor between human and agent, taking a step toward a "text-to-ASIC" future for designing RF/mmWave hardware.

Improved circuit synthesis may increase efficiency and innovation

The framework automates complex RF/mmWave circuit design, reducing human labor and potentially accelerating development, which is a positive impact. However, increased automation can disrupt skilled employment in engineering and may create dependencies on AI tools, posing economic and workforce risks.

This is a legitimate technical demonstration of an LLM agent successfully using EDA tools to design a working mmWave chip, with real performance numbers. It signals incremental progress toward automating specialized engineering labor, a moderate but real societal shift, not an existential or transformative event on its own.

SOURCE     arXiv cs.AI (tier 1)
   ↓
DOCUMENT   3be471d5-a5de-41ce-ac21-998701a2040c
           https://arxiv.org/abs/2610.31882
   ↓
EVIDENCE   3 extracted excerpts
   ↓
MODEL RUN  3 runs, methodology 1.0.1
   ↓
SCORE      +27  (Favourable)
   ↓
CONFIDENCE 73%