Search papers, labs, and topics across Lattice.
This paper introduces OmniRouting, a comprehensive benchmark designed to assess large language models (LLMs) on their ability to perform constraint-aware spatial reasoning in printed-circuit-board (PCB) routing. The benchmark includes 1,681 industrial-grade designs and evaluates LLMs across four distinct tasks, revealing significant shortcomings in their path-planning abilities and adherence to critical design-rule and electrical functionality constraints. The findings underscore the necessity for improved models in the domain of electronic design automation, as current LLMs struggle with complex routing challenges that are essential for real-world applications.
Current LLMs fail to meet the rigorous demands of PCB routing, showing major weaknesses in path planning and constraint adherence.
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.
