pcbGPT: Automatic PCB Schematic Synthesis from Natural Language Requirements
Not on the map. Why?
Abstract (arXiv)
Translating natural-language hardware requirements into correct printed circuit board (PCB) schematics remains difficult in embedded, IoT, and wearable development. Designers must choose compatible components, interpret datasheets, add support circuitry, and expose correct interfaces before layout and prototyping can begin, while many such circuits cannot be validated through straightforward simulation. We present pcbGPT, a grounded system for generating editable KiCad schematics from natural-language specifications. pcbGPT represents circuits in a Python DSL and combines tool-augmented synthesis with component-library search, datasheet-grounded design knowledge, execution-based checking, structural and semantic validation, and an interactive web workflow that supports iterative refinement and synchronization with KiCad projects. We evaluate the system on 20 embedded schematic-generation tasks with reference implementations, required components, and interface constraints that enable automatic comparison. The best model reaches overall pass@1 of 0.90 and pass@5 of 1.00; pass@1 is 1.00 on basic and easy tasks, 0.91 on medium tasks, and 0.72 on hard tasks. These results, together with failure analysis, show that pcbGPT can already generate useful, reviewable first-draft schematics for early prototyping, but is not yet reliable enough to replace expert review.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 12 of its 31 references that are in the map. First posted on arXiv 31 May 2026.
Builds on
12 of 31 references.
References · 12
- 2021Evaluating Large Language Models Trained on Codecited by 8,053
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
- 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
- 2023Teaching Large Language Models to Self-Debugcited by 963
- 2023Chip-Chat: Challenges and Opportunities in Conversational Hardware Designcited by 136
- 2023ChipGPT: How far are we from natural language hardware designcited by 101
- 2024AnalogCoder: Analog Circuit Design via Training-Free Code Generationcited by 82
- 2018Learning to Design Circuitscited by 17
- 2025AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generationcited by 10
- 2025HARNode: A Time-Synchronised, Open-Source, Multi-Device, Wearable System for Ad Hoc Field Studiescited by 2
- 2025τ-Ring: A Smart Ring Platform for Multimodal Physiological and Behavioral Sensingcited by 2
- 2025TypedSchematics: A Block-based PCB Design Tool with Real-time Detection of Common Connection Errorscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026From Agent Output to Authorized Transitioncited by 0
- 2026From Agent Output to Authorized Transition23 Sep 2026