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.
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
Back-to-the-Future (BTTF) is introduced, an end-to-end agentic framework that closes this infrastructural gap toward autonomous EDA verification and charting a practical path toward autonomous EDA 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...
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.· arXiv.org· 0 citations
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
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· Proceedings of the 2nd Inter...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.