Skip to content

LLMs in Digital EDA: A perspective on shifting roles from Generation to Orchestration

Aug 2026 · arXiv.org · Vol abs/2608.27184 · 1 citation · 69 references
Computer Science

TL;DR

This Perspective defines three hierarchical roles that reveal how capability accumulates: a Generator that produces design artifacts in a single pass, an Agent that refines outputs through iterative tool feedback, and an Orchestrator that coordinates decisions across EDA-stages.

Abstract

Electronic design automation (EDA) has advanced engineering productivity through successive generations of tooling that progressively automate synthesis, optimisation, and verification. Large language models (LLMs) extend this trajectory by enabling direct translation from design intent to hardware implementations. In most of the EDA literature, LLM-based solutions are typically assisting siloed design stages or tasks, however this obscured the drivers by which capability emerges and systems scale. In this Perspective, we instead define three hierarchical roles that reveal how capability accumulates: a Generator that produces design artifacts in a single pass, an Agent that refines outputs through iterative tool feedback, and an Orchestrator that coordinates decisions across EDA-stages. Across published systems, this reveals a syntax trap in which models are trained to produce plausible code rather than physically correct hardware, compounded by fragmented tools and loss of design context that obscure how decisions affect later stages. Comparisons across the three roles show that current approaches struggle to scale to industrial designs, motivating a shift towards a standardised, physics-aware orchestrator that connects tools and agents across the EDA flow for more reliable and accessible hardware design.

View source

Similar papers

Preprint Nov 2026

ChipOmni: A General-Purpose AI Agent for Electronic Design Automation

Electronic design automation (EDA) workflows remain highly fragmented, requiring engineers to coordinate heterogeneous representations, specialised software tools, and iterative verification across multiple design stages. Although large language models have brought more general reasoning and code-generation capabilitie...

Peng-Kun Wang, Rui Mao, Zhe Zhao et al. · 0 citations
#artificial intelligence Preprint Oct 2026

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

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 7...

Je Yang, Ivan Lobov, Thomas Karpati · 0 citations

ChipMEM: Verification-Grounded Memory for EDA Agents

ChipMEM, a verification-grounded memory layer for EDA agents, is introduced, a verification-grounded memory layer for EDA agents that combines cross-task procedural memory with within-trajectory statistical guidance.

Abdulrahman Alrabah, Joshua Mabry, Dilek Z. Hakkani-Tür et al. · 0 citations
Preprint Oct 2026

Design Anything, Design at Scale

As multimodal resources are transformed into media outputs, agentic AI is expected to stay aligned with design intent over long horizons. Designers follow briefs specifying goals, constraints, and deliverables, with later work building on earlier decisions. Recent work reuses design experience across tasks, yet alignme...

Xu-Chao Ren, Si-Yuan Feng, Jing-Yi Huang et al. · 0 citations
Book Open access Oct 2026

Decompose to Conquer: A Multi-agent LLM Pipeline for Requirements Engineering and Software Design

Results provide empirical evidence that the decomposition of RE and the design into specialized agents is likely to increase the quality of the design beyond what a single agent can achieve, and the effectiveness of RAG is contingent on the specificity and domain relevance of the knowledge-base rather than mere retriev...

Mesfin Tibebu, Mohamed Nabeel · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.