Closing the Loop: Overcoming the Tool-Feedback Gap in Agentic Hardware Design

Mohammadnavid Tarighat1, Kevin Immanuel Gubbi1, Neusha Javidnia2, Noah Marosok2, Soheil Zibakhsh-shabgahi2, Marcus Halm3, Mahdi Pirayesh Shirazi Nejad3, Setareh Rafatirad4, Farinaz Koushanfar5, Houman Homayoun4
1University of California, Davis, 2Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA 92093, 3Department of Electrical and Computer Engineering, University of California Davis, Davis, CA 95616, 4University of California Davis, 5University of California San Diego


Abstract

LLM-driven hardware design remains unreliable because it is largely open-loop, producing syntactically correct RTL without the iterative grounding provided by EDA tools. We refer to this disconnect as the Tool-Feedback Gap, which is further compounded by PPA blindness, where post-synthesis power, performance, and area constraints are ignored. This paper surveys emerging closed-loop, agentic EDA systems that integrate simulation and synthesis, and highlights a growing shift toward multi-agent orchestration with specialized planner, executor, judge, and debug roles to filter noisy tool outputs and mitigate context-switching failures. It further calls for benchmarks that measure convergence efficiency and PPA-aware optimization, rather than simple pass/fail simulation, and warns that autonomous feedback loops can amplify security risks such as vulnerability injection, hardware Trojans, and vacuous verification. These risks motivate the need for standardized tool interfaces, dynamic routing to specialized smaller models, and reasoning-based repair to ensure safe and reliable agentic hardware design.