Explorerโ€บArtificial Intelligenceโ€บAI
Research PaperResearchia:202610.06065

Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification

Je Yang

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 ...

Submitted: October 6, 2026Subjects: AI; Artificial Intelligence

Description / Details

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.


Source: arXiv:2610.06790v1 - http://arxiv.org/abs/2610.06790v1 PDF: https://arxiv.org/pdf/2610.06790v1 Original Link: http://arxiv.org/abs/2610.06790v1

Please sign in to join the discussion.

No comments yet. Be the first to share your thoughts!

Access Paper
View Source PDF
Submission Info
Date:
Oct 6, 2026
Topic:
Artificial Intelligence
Area:
AI
Comments:
0
Bookmark
Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification | Researchia