Agentic AI Automates RTL Waveform Analysis And Debugging (Columbia, Google)

Researchers at Columbia University, Google DeepMind, and Google published a technical paper titled “Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification.”

Abstract

“The unprecedented computational scale of modern artificial intelligence depends on complex, multi-billion-transistor Systems-on-Chip, yet the workflows that verify these chips remain stubbornly manual. Although Large Language Models (LLMs) have made rapid inroads into Electronic Design Automation (EDA), approximately 74.6% of existing studies target static Register-Transfer Level (RTL) code generation, leaving post-simulation verification and interactive waveform debugging largely untouched. We introduce Back-to-the-Future (BTTF), an end-to-end agentic framework that closes this infrastructural gap. BTTF distills massive, unstructured simulation dumps into a normalized relational SQLite database and couples it with a collaborative multi-agent orchestration engine that translates natural-language verification queries into schema-aware SQL while correlating signal anomalies with versioned RTL repositories. Across a 150-query benchmark, BTTF attains 95.33% execution accuracy, charting a practical path toward autonomous EDA verification.”

Find the technical paper here. October 2026.

Yang, Je, Ivan Lobov, and Thomas Karpati. “Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification.” arXiv preprint arXiv:2610.06790 (2026).

The post Agentic AI Automates RTL Waveform Analysis And Debugging (Columbia, Google) appeared first on Semiconductor Engineering.