PCBWorld: A Benchmark Environment for Engine-Grounded PCB Design Automation
Quick Answer
PCBWorld is an open-source PCB routing environment utilizing the KiCad EDA engine, enabling agents to interactively route boards while adhering to design rules.
Quick Take
PCBWorld is an open-source PCB routing environment utilizing the KiCad EDA engine, enabling agents to interactively route boards while adhering to design rules. Experiments show that agents in PCBWorld outperform traditional RL policies and LLM baselines, demonstrating significant potential for enhancing PCB design automation.
Key Points
- PCBWorld enables interactive routing using native KiCad operations and DRC feedback.
- Supports both RL policies and tool-using LLM agents for PCB design.
- Includes PCBWorld-Bench with three dataset families and 679 real boards.
- Agents consistently outperformed grid-action RL policies in benchmark tests.
- Zero-shot transfer from synthetic to real boards approaches rule-based routing performance.
Paper Resources
📖 Reader Mode
~2 min readAbstract:PCB routing is the task of connecting the nets of a board with copper traces under strict design rules, yet learning-based methods still lag behind rule-based routers. We introduce PCBWorld, an open-source engine-grounded PCB routing environment built on the KiCad EDA engine. As a human engineer does, agents in PCBWorld interactively route a board through the engine's native operations, using its Design Rule Check (DRC) feedback to keep the routing within the design rules. The environment supports both RL policies and tool-using LLM agents. Alongside the environment, PCBWorld-Bench provides three dataset families in KiCad's native board format (.kicad_pcb), covering two types of controllable synthetic instances and 679 real open-source boards. It scores any completed board with eight engine-checked evaluation metrics, regardless of the routing method. In our experiments, agents in PCBWorld consistently outperformed grid-action RL policies and open-loop LLM baselines, and an RL policy trained only on synthetic boards transferred zero-shot to real boards, approaching rule-based routers. These results position the engine-grounded, interactive approach of PCBWorld as a promising foundation for advancing the routing ability of both RL and LLM agents.
| Comments: | Accepted to the KDD 2026 Workshop on Evaluation and Trustworthiness of Agentic AI (non-archival). Main text with appendix |
| Subjects: | Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.6; I.2.8; B.7.2; J.6 |
| Cite as: | arXiv:2607.05915 [cs.AI] |
| (or arXiv:2607.05915v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.05915 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hyungseok Song [view email]
[v1]
Tue, 7 Jul 2026 07:09:46 UTC (3,637 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Onnes: A Physics-Grounded LLM Simulator for Cryogenic Fault Diagnosis in Quantum Computing Infrastructure
Onnes is a physics-grounded digital twin simulator for dilution refrigerators, enhancing cryogenic fault diagnosis in quantum computing. It achieves a classification accuracy of 99.0% using few-shot demonstrations, matching a supervised ML classifier, while maintaining a low false alarm rate of 6.4% on real hardware.