OmniRouting：面向PCB布线中约束感知空间推理的语义耦合多模态基准
OmniRouting: A Semantic-Coupled Multimodal Benchmark for Constraint-Aware Spatial Reasoning in PCB Routing
AI总结：
本研究针对LLMs在PCB布线推理上的能力缺口，构建了OmniRouting基准，含1681个工业级PCB设计及四项任务，发现现有LMMs存在显著局限并计划开源相关资源。
AI中文摘要：
近期，大型语言模型（LLMs）在约束感知导航、迷宫推理和图推理方面取得了显著进展。然而，尽管布线是电子设计自动化（EDA）中最具挑战性和最关键的阶段之一，它们在严格的几何、拓扑和电气约束下对复杂布线问题进行推理的能力仍在很大程度上未被探索。为了弥合这一差距，我们引入了OmniRouting，这是首个旨在评估LLMs在印刷电路板（PCB）布线推理方面能力的大规模基准，其基于真实工业设计规则、可制造性和连接性约束。OmniRouting包含1681个工业级、与原理图耦合的PCB设计，涵盖板几何形状、由人类工程师完成的可布线元件布局、封装、焊盘位置、网表、叠层信息以及布线约束。该基准包含四项任务：（1）几何布线推理，生成物理上有效的铜走线、过孔和层分配，以在受限板区域内连接电路网络；（2）设计规则感知布线推理，生成满足间距、走线宽度、过孔、避障和板边界约束的可布线布局；（3）电气功能推理，在推理网络名称和功能角色的同时保留原理图指定的连接性，以产生电气上正确的布线；（4）工具增强型智能体布线，利用外部工具完成任务（1）至（3）。我们的结果显示，当前多模态大型语言模型（LMMs）在PCB布线方面存在显著局限性，包括路径规划能力薄弱、对设计规则约束的遵守性差，以及电气功能的一致性保留不足。我们将开源所有基准数据、评估代码和工具接口，以促进未来的研究。
英文摘要：
Recent large language models (LLMs) have demonstrated remarkable progress in constraint-aware navigation, maze reasoning, and graph reasoning. However, their ability to reason about complex routing problems under strict geometric, topological, and electrical constraints remains largely unexplored, despite routing being one of the most challenging and critical stages of electronic design automation (EDA). To bridge this gap, we introduce OmniRouting, the first large-scale benchmark designed to evaluate LLMs on printed-circuit-board (PCB) routing reasoning under real-world industrial design-rule, manufacturability, and connectivity constraints. OmniRouting contains 1,681 industrial-grade schematic-coupled PCB designs, including board geometries, routable component placements by human engineers, footprints, pad locations, netlists, stackup information, and routing constraints. The benchmark comprises four tasks: (1) geometric routing reasoning, generating physically valid copper traces, vias, and layer assignments to connect circuit nets within constrained board regions; (2) design-rule-aware routing reasoning, producing routable layouts that satisfy clearance, trace-width, via, obstacle-avoidance, and board-boundary constraints; (3) electrical functionality reasoning, preserving schematic-specified connectivity while reasoning over net names and functional roles to produce electrically correct routing; and (4) tool-augmented agentic routing, leveraging external tools for tasks (1)-(3). Our results reveal substantial limitations of current LMMs in PCB routing, including weak path-planning capabilities, poor adherence to design-rule constraints, and inconsistent preservation of electrical functionality. We will open-source all benchmark data, evaluation code, and tool interfaces to facilitate future research.
