The Dawn of Agentic EDA: A Survey of Autonomous Digital Chip Design

TL;DR

This survey introduces a new framework for autonomous digital chip design, emphasizing a shift from passive tools to agentic, neuro-symbolic optimization that enhances design flow efficiency and trustworthiness.

Contribution

It presents the first systematic taxonomy and framework for Agentic EDA, integrating perception, cognition, and action to advance autonomous chip design processes.

Findings

Shift from one-shot to dual-loop repair in frontend design

Dichotomy between algorithm-centric and agent-centric backend solutions

Highlighting the need for formal benchmarks to improve trustworthiness

Abstract

The semiconductor industry faces a critical "Productivity Gap" where design complexity outpaces human capacity. While the "AI for EDA" revolution (L2) successfully optimized specific point problems, a paradigm shift toward Agentic EDA (L3) is emerging, evolving from passive prediction to autonomous orchestration of the RTL-to-GDSII flow. This survey presents the first systematic framework for this transition, framing Agentic EDA not merely as "Chat with Tools," but as a Constrained Neuro-Symbolic Optimization problem. We propose a novel taxonomy rooted in a Cognitive Stack--Perception (aligning multimodal semantics), Cognition (planning under strict constraints), and Action (deterministic tool execution)--to dissect how probabilistic agents navigate zero-tolerance physical laws. Through this lens, we analyze the landscape: (1) in Frontend, the shift from one-shot generation to dual-loop syntactic-semantic repair; (2) in Backend, the dichotomy between algorithm-centric solvers and agent-centric orchestrators that treat executable code as a latent space. Finally, we critically examine the Trustworthiness gap, advocating for Sim-to-Silicon benchmarks and formal grounding to transform brittle prototypes into resilient engineering systems.