MenTeR: A fully-automated Multi-agenT workflow for end-to-end RF/Analog Circuits Netlist Design

--RF/Analog design is essential for bridging digital technologies with real-world signals, ensuring the functionality and reliability of a wide range of electronic systems. However, analog design procedures are often intricate, time-consuming and reliant on expert intuition, and hinder the time and cost efficiency of circuit development. T o overcome the limitations of the manual circuit design, we introduce MenT eR - a multi-agent workflow integrated into an end-to-end analog design framework. By employing multiple specialized AI agents that collaboratively address different aspects of the design process, such as specification understanding, circuit optimization, and test bench validation, MenT eR reduces the dependency on frequent trial-and-error-style intervention. MenT eR not only accelerates the design cycle time but also facilitates a broader exploration of the design space, demonstrating robust capabilities in handling real-world analog systems. We believe that MenT eR lays the groundwork for future "RF/Analog Copilots" that can collaborate seamlessly with human designers. The recent progress of Large Language Models (LLMs) has led to an increasing numbers of LLM applications in scientific and engineering fields such as mathematical reasoning, pharmaceutical development, and chip design. For instance, in the field of digital circuit design, Liu et al. [1] introduced the first domain-adapted LLM, which demonstrated the potential of using legacy chip design documents to increase the design capabilities of LLM.