StructureClaw: Traceable LLM Agents and Executable Benchmark for Structural Engineering Workflows

Jul 17, 2026

StructureClaw introduces an artifact-centered workbench for evaluating LLM agents in structural engineering, emphasizing governed skills, typed tools, and shared artifact state. The accompanying StructureClaw-Bench provides 150 executable scenarios that test standard workflow execution, robustness, and multimodal reconstruction, requiring all assertions to pass for success. Results show that average agent success rates improved from 56.8% with generic skills to 88.6% with full automation, and the benchmark reveals key challenges in handling invalid inputs and model reconstruction.

Why it matters: This work establishes a rigorous, workflow-level evaluation framework for structural engineering agents, enabling the identification of failures that are missed by traditional final-response checks.

Full story at: arXiv Multiagent Systems ↗