Metraipolis › archive › dc_28333dfbeed7
PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers? — arXiv:2611.08175
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08175
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:41:53.767Z
- SHA-256 of the archived text
c6abc16db8a0468c050cd337a476dfba6b44b49bf2670b1bcacd48ec09aad392- Stable URL of this page
https://metraipolis.com/documento/dc_28333dfbeed7
How to cite
PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers? — arXiv:2611.08175 — arXiv (en), https://arxiv.org/abs/2611.08175 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_28333dfbeed7 (Metraipolis archive dc_28333dfbeed7, sha256 c6abc16db8a0468c050cd337a476dfba6b44b49bf2670b1bcacd48ec09aad392)
BibTeX
@misc{dc28333dfbeed7,
title = {PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers? — arXiv:2611.08175},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08175},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_28333dfbeed7; sha256 c6abc16db8a0468c050cd337a476dfba6b44b49bf2670b1bcacd48ec09aad392},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08175. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Automating printed circuit board (PCB) routing requires coordinating board-level connectivity decisions with geometric execution under strict design rules. Although recent agents can interact with native routing tools, reliable routing on complex boards remains challenging. We present PCBRouteAgent, a multimodal PCB routing agent inspired by how human engineers coordinate global strategy with local execution. A Global Routing Planner combines board images and structured electrical and geometric information to specify connection topology, routing order, corridors, and layer transitions. A Detailed Routing Executor realizes these guides through KiCad's native routing engine and performs bounded local recovery. Unresolved failures are returned as structured feedback, enabling targeted guide revisions while preserving accepted routes. We evaluate PCBRouteAgent on 247 synthetic and real-world boards from four PCBWorld-Bench test splits. It achieves clean-pass rates of 100%, 94.9%, 100%, and 40% on D2, D3-A, D3-B, and D3-C, respectively. On the three real-world subsets, PCBRouteAgent outperforms the best evaluated baseline in clean-pass rate by 13.9, 36, and 10 percentage points, respectively. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.08175 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-06T14:18:42.652Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).