Welcome.AI
    Skip to content
    research

    TACS-RF: Streamlining RF and mmWave Module Design Process

    The research introduces TACS-RF, a new framework that leverages a large-language model (LLM) coding agent, specifically Claude Opus 4.8, to enhance the design process of radio frequency (RF) and milli...

    arxiv.org•October 26, 2026•3 min read

    Key Facts

    • Integrate TACS-RF with existing EDA tools to streamline RF module design processes.
    • Leverage AI-driven design frameworks to enhance efficiency and reduce development time.
    • Implement semi-autonomous design techniques for advanced sub-THz transmitter applications.
    • Utilize Claude Opus 4.8 to improve accuracy in complex RF circuit designs.
    • Adopt 90 nm SiGe BiCMOS technology for high-performance, cost-effective RF solutions.

    Summary

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

    Authors: Tristan Liang, Aravind Nagulu

    Executive Summary

    The research introduces TACS-RF, a new framework that leverages a large-language model (LLM) coding agent, specifically Claude Opus 4.8, to enhance the design process of radio frequency (RF) and millimeter-wave (mmWave) modules. This framework integrates with established electronic design automation (EDA) tools, such as Cadence Virtuoso/Spectre, Calibre, Cadence EMX, and Ansys HFSS, to facilitate a more efficient and potentially autonomous design process.

    The practical application of this framework was validated through the semi-autonomous design of a sub-terahertz (sub-THz) transmitter operating in the 240-251 GHz range, using a 90 nm silicon-germanium (SiGe) BiCMOS technology. The design process included the development of critical components such as a 60 GHz push-push Colpitts voltage-controlled oscillator (VCO), multistage differential cascode power drivers, a frequency doubler, a differential bowtie antenna, and various interstage matching networks.

    The resulting transmitter chain achieved significant performance metrics: it delivered output power levels ranging from +5.1 to +6.3 dBm across an 11 GHz tuning range that utilized only varactor components. Additionally, it maintained a phase noise performance of -80 to -88 dBc/Hz at a 1 MHz offset, while consuming a total DC power of 361 mW. These results were derived from simulations and benchmarks rather than real-world deployment, underscoring the framework's potential in a controlled environment.

    The research outlines a novel design flow that illustrates how responsibilities can be divided between human engineers and the coding agent. This division of labor is pivotal as it demonstrates a significant step toward a "text-to-ASIC" (application-specific integrated circuit) approach for designing RF and mmWave hardware. This could streamline the development process, making it faster and potentially more cost-effective.

    The implications of TACS-RF are noteworthy for companies in the telecommunications and electronics sectors, particularly those focused on developing high-frequency components. By automating parts of the design process, organizations may enhance their productivity and innovation capabilities. The framework could allow for more complex designs to be handled efficiently, reducing the time to market for new technologies.

    In summary, TACS-RF represents a forward-looking approach to electronic design, where advanced AI tools could play a significant role in shaping the future of RF and mmWave hardware development.

    Academic 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.

    Frequently Asked Questions

    What business problems does TACS-RF address in the design of RF and mmWave modules?

    TACS-RF could solve inefficiencies in the design process of RF and mmWave modules by facilitating a more efficient and potentially autonomous design workflow, reducing time and resource expenditure associated with traditional electronic design methods.

    Which industries could benefit most from the implementation of TACS-RF?

    Industries that may benefit most include telecommunications, consumer electronics, automotive (particularly in vehicle-to-everything communication), aerospace, and defense, where RF and mmWave technologies are critical for communication systems and sensor applications.

    What are the practical implementation considerations for adopting the TACS-RF framework?

    Practical implementation considerations could include the integration of TACS-RF with existing electronic design automation (EDA) tools and ensuring compatibility with current design workflows. Additionally, firms may need to assess the readiness of their infrastructure to support semi-autonomous design processes.

    What resources or expertise are needed to effectively utilize TACS-RF in a business setting?

    Companies may require access to advanced EDA tools, such as Cadence Virtuoso/Spectre and Ansys HFSS, as well as expertise in RF design, semiconductor technology, and proficiency with large-language models and AI-driven design processes to maximize the benefits of TACS-RF.

    What competitive advantages could businesses gain from implementing TACS-RF in their design processes?

    Businesses could gain competitive advantages through faster time-to-market for new RF and mmWave products, improved design accuracy and efficiency, and the ability to innovate more rapidly by leveraging the capabilities of AI-driven design automation.

    Where AI Leaders Stay Informed

    The latest AI intelligence, case studies, and research — delivered to your inbox every week.

    Free to read. Unsubscribe anytime.