PCBRouteAgent：LLM 智能体距离成为 PCB 布线工程师还有多远？
PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers?
Yue Zhang, Jilei Sun, Liqiang Jing, Yijie Wei, Ruohan Yang
AI 速读 基于摘要
提出一种受人类工程师“全局规划+局部执行”协作方式启发的多模态 PCB 布线智能体，并在 PCBWorld-Bench 的 247 块合成与真实电路板上评估其干净通过率。
cs.AI
查看原文摘要
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.