Electronic Design Automation
Also known as EDA
Overview
Electronic Design Automation (EDA) develops tools for turning hardware specifications into circuits, chip layouts, and printed circuit boards, then checking that designs work and meet constraints such as timing, power, area, and manufacturability. Traditional methods include logic synthesis, formal verification, physical-design heuristics, and circuit simulation; newer work adds graph neural networks, surrogate models, Bayesian optimization, and reinforcement learning to predict results or explore designs with fewer costly evaluations. Large language models are increasingly used to generate and repair RTL, create testbenches, and coordinate multi-step workflows with synthesis, simulation, and layout tools. A central challenge is ensuring that gains measured with proxies or on small benchmarks survive full tool flows and sign-off checks, especially for complex designs and long-running agent workflows.
Latest papers
215 papers36 papers in the last four weeks, up 112% on the four weeks before. 0.2% of all new papers.