{"ID":2886994,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02518","arxiv_id":"2508.02518","title":"AnalogCoder-Pro: Unifying Analog Circuit Generation and Optimization via Multi-modal LLMs","abstract":"Despite recent advances, analog front-end design still relies heavily on expert intuition and iterative simulations, which limits the potential for automation. We present AnalogCoder-Pro, a multimodal large language model (LLM) framework that integrates generative and optimization techniques. The framework features a multimodal diagnosis-and-repair feedback loop that uses simulation error messages and waveform images to autonomously correct design errors. It also builds a reusable circuit tool library by archiving successful designs as modular subcircuits, accelerating the development of complex systems. Furthermore, it enables end-to-end automation by generating circuit topologies from target specifications, extracting key parameters, and applying Bayesian optimization for device sizing. On a curated benchmark suite covering 13 circuit types, AnalogCoder-Pro successfully designed 28 circuits and consistently outperformed existing LLM-based methods in figures of merit.","short_abstract":"Despite recent advances, analog front-end design still relies heavily on expert intuition and iterative simulations, which limits the potential for automation. We present AnalogCoder-Pro, a multimodal large language model (LLM) framework that integrates generative and optimization techniques. The framework features a m...","url_abs":"https://arxiv.org/abs/2508.02518","url_pdf":"https://arxiv.org/pdf/2508.02518v2","authors":"[\"Yao Lai\",\"Souradip Poddar\",\"Sungyoung Lee\",\"Guojin Chen\",\"Mengkang Hu\",\"Bei Yu\",\"Ping Luo\",\"David Z. Pan\"]","published":"2025-08-04T15:25:48Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}