CircuitLM: A Multi-Agent LLM-Aided Design Framework for Generating Circuit Schematics from Natural Language Prompts

TL;DR

CircuitLM is a multi-agent framework that converts natural language prompts into accurate, physically viable circuit schematics by combining retrieval, reasoning, and verification steps, addressing hallucination issues in LLM-based design.

Contribution

This work introduces CircuitLM, a novel multi-agent pipeline that produces structured, verifiable circuit schematics from natural language prompts, integrating knowledge grounding and multi-level evaluation.

Findings

Effective reduction of hallucinations in schematic generation

High accuracy in producing physically viable circuit designs

Robust evaluation methodology combining rule-based and semantic checks

Abstract

Generating accurate circuit schematics from high-level natural language descriptions remains a persistent challenge in electronic design automation (EDA), as large language models (LLMs) frequently hallucinate components, violate strict physical constraints, and produce non-machine-readable outputs. To address this, we present CircuitLM, a multi-agent pipeline that translates user prompts into structured, visually interpretable $\texttt{CircuitJSON}$ schematics. The framework mitigates hallucination and ensures physical viability by grounding generation in a curated, embedding-powered component knowledge base through five sequential stages: (i) component identification, (ii) canonical pinout retrieval, (iii) chain-of-thought reasoning, (iv) JSON schematic synthesis, and (v) interactive force-directed visualization. We evaluate the system on a dataset of 100 unique circuit-design prompts using five state-of-the-art LLMs. To systematically assess performance, we deploy a rigorous dual-layered evaluation methodology: a deterministic Electrical Rule Checking (ERC) engine categorizes topological faults by strict severity (Critical, Major, Minor, Warning), while an LLM-as-a-judge meta-evaluator identifies complex, context-aware design flaws that bypass standard rule-based checkers. Ultimately, this work demonstrates how targeted retrieval combined with deterministic and semantic verification can bridge natural language to structurally viable, schematic-ready hardware and safe circuit prototyping. Our code and data will be made public.