NTH

PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers?

AuthorsYue Zhang, Jilei Sun, Liqiang Jing, Yijie Wei, Ruohan Yang

AffiliationsThe University of Texas at Dallas · Texas Instruments Inc · Iowa State University

November 13, 2026 2 min read
Watch on YouTube
The one-line take

PCBRouteAgent pairs an LLM’s board-level routing plans with KiCad’s routing engine to tackle complex PCB layouts.

Key results

247
Boards evaluated

Total synthetic and real-world PCB boards in the benchmark.

94.9%
D3-A clean-pass rate

Claude Opus 5.5 result on small real-world boards.

100%
D3-B clean-pass rate

Claude Opus 5.5 result on medium real-world boards.

40%
D3-C clean-pass rate

Claude Opus 5.5 result on large real-world boards.

13.9
D3-A improvement over strongest baseline

Percentage-point increase in clean-pass rate.

80.3%
D3-C design-rule violation reduction

Reduction in average violations versus Freerouting.

What the paper found

PCBRouteAgent tackles PCB routing by separating board-level strategy from trace-by-trace execution. Its multimodal planner uses board images and structured electrical and geometric data to build minimum-spanning-tree connection plans, prioritize nets, and define routing corridors and layer transitions. A detailed executor then uses KiCad’s native push-and-shove router, bounded local recovery, and A* detours; when a route still fails, structured feedback prompts targeted plan revisions while preserving accepted connections. Evaluated with Anthropic’s Claude Opus 5.5 on 247 boards, the system achieved clean-pass rates of 94.9% on D3-A, 100% on D3-B, and 40% on the largest-board split, D3-C. Those results beat the strongest evaluated baselines by 13.9 percentage points on D3-A, 36 points on D3-B, and 10 points on D3-C. On D3-C, it also cut average design-rule violations from 32.0 to 6.3, an 80.3% reduction, despite leaving six of ten boards incomplete. The study also compares against interactive agents using OpenAI’s GPT-5.4 and Anthropic’s Claude Haiku 5.5. Its central caveat is that connected, rule-clean traces are not necessarily electrically validated: in one example, the agent routed USB D+ and D- independently rather than as a differential pair, while crowded-board routing order remains a challenge.

Original abstract

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.

Read the original paper

More in AI Hardware

Browse all 40 papers →