The Dawn of Agentic EDA: A Survey of Autonomous Digital Chip Design
Authors:
Preprint
Abstract
This survey provides a comprehensive overview of the integration of Generative AI and Agentic AI within the field of Digital Electronic Design Automation (EDA). The paper first reviews the paradigmatic evolution from traditional Computer-Aided Design (CAD) to AI-assisted EDA (AI4EDA), and finally to the emerging AI-Native and Agentic design paradigms. We detail the application of these paradigms across the digital chip design flow, including the construction of agentic cognitive architectures based on multimodal foundation models, frontend RTL code generation and intelligent verification, and backend physical design featuring algorithmic innovations and tool orchestration. We validate these methodologies through integrated case studies, demonstrating practical viability from microarchitecture definition to GDSII. Special emphasis is placed on the potential for cross-stage feedback loops where agents utilize backend PPA metrics to autonomously refine frontend logic. Furthermore, this survey delves into the dual-faceted impact on security, covering novel adversarial risks, automated vulnerability repair, and privacy-preserving infrastructure. Finally, the paper critically summarizes current challenges related to hallucinations, data scarcity, and black-box tools, and outlines future trends towards L4 autonomous chip design. Ultimately, this work aims to define the emerging field of Agentic EDA and provide a strategic roadmap for the transition from AI-assisted tools to fully autonomous design engineers.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- The Rise of Agentic AI: Synthesis of Current Knowledge and Future Research AgendaGlobal Business and Organizational Excellence, 2025
- Revolution or Hype? Seeking the Limits of Large Models in Hardware Design2025
- Deep Multimanifold Transformation-Based Multivariate Time Series Fault DetectionIEEE Transactions on Neural Networks and Learning Systems, 2025
- ORFS-agent: Tool-Using Agents for Chip Design Optimization2025
- SANGAM: SystemVerilog Assertion Generation via Monte Carlo Tree Self-Refine2025
- GenURL: A General Framework for Unsupervised Representation LearningIEEE Transactions on Neural Networks and Learning Systems, 2024
- Structure-preserving visualization for single-cell RNA-Seq profiles using deep manifold transformation with batch-correctionCommunications Biology, 2023
- DMT-EV: An Explainable Deep Network for Dimension ReductionIEEE Transactions on Visualization and Computer Graphics, 2022
- Deep manifold embedding of attributed graphsNeurocomputing, 2022
- CircuitNet: an open-source dataset for machine learning applications in electronic design automation (EDA)Science China Information Sciences, 2022