CircuitFormer model translates natural language prompts into analog circuit designs

Researchers have developed CircuitFormer, a new language model specifically designed for analog circuit topology design from natural language prompts. This model addresses limitations in existing LLMs by introducing a novel circuit graph tokenizer (CKT) that efficiently captures circuit connectivity and a curated dataset of over 31,000 netlist-description pairs. CircuitFormer demonstrates a high success rate in generating syntactically correct and functionally sound analog circuits, outperforming general-purpose LLMs. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Introduces a specialized language model and tokenizer for analog circuit design, potentially accelerating hardware development.

RANK_REASON This is a research paper detailing a new model and dataset for analog circuit design. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• CircuitFormer
• CKT
• Transformer
• LLM
• Electronic Design Automation
• arXiv

• paper
• model release