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

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Sizhong Qin, Yi Gu, Yao Jiang, Ao Cai, Changjian Zhou, Shaoxuan Shuai, Jiachang Wang, Tianhao Shen, Yueqiang Li, Xinhao Li, Li Zeng, Yueshi Chen, Dachen Gao, Genrong Xu, Wenjie Liao, Xinzheng Lu
• Venue: arXiv: cs.SE
• Published: 2026-07-16
• Collected: 2026-07-17
• URL: http://arxiv.org/abs/2607.14896v1
• PDF: https://arxiv.org/pdf/2607.14896v1
• DOI: UNKNOWN

Plain-Language Brief

Researchers have developed StructureClaw, an artifact-centered workbench that uses LLM (Language Model) agents to operate through governed engineering skills and checks for completion, consistency, and execution of structural engineering tasks. The study includes an executable benchmark with 150 controlled scenarios to evaluate the performance of various agent-model configurations. StructureClaw-Bench ensures success only when all required artifact and execution-level assertions pass in a single run. The findings show that this approach can expose workflow-level failures not easily identified from final responses alone, providing a more rigorous basis for evaluating and improving structural engineering agents.

What the Document Says

• The paper presents StructureClaw, an artifact-centered workbench for LLM agents that operate through governed engineering skills, typed tools, shared artifact state, and local analysis backends.
• StructureClaw-Bench is introduced as an executable benchmark with 150 controlled scenarios for standard workflow execution, interactive robustness, and multimodal structural-model reconstruction.
• A scenario's success depends on all required artifact- and execution-level assertions passing in a single run.
• The study evaluates ten agent-model configurations on the same 50 standard cases, with the average Success Rate rising from 56.8% with the generic-skill baseline to 88.6% with the full automatic workflow.
• Interactive and multimodal evaluations identify two prominent remaining challenges: safe handling of invalid numerical inputs and fixture-consistent reconstruction of structural models.
• The findings suggest that artifact-centered evaluation can expose workflow-level failures not easily identified from final responses alone, providing a more rigorous basis for evaluating and improving structural engineering agents.

Key Concepts Mentioned

• StructureClaw
• LLM agents
• structural engineering
• artifact-centered workbench
• executable benchmark
• standard cases
• Success Rate
• invalid numerical inputs
• fixture-consistent reconstruction

Claims Made by the Document

• StructureClaw can improve the evaluation of structural engineering agents by focusing on artifacts and execution.
• The proposed approach can expose workflow-level failures not easily identified from final responses alone.

Evidence Used

• Across ten agent-model configurations, each evaluated on the same 50 standard cases, the average Success Rate rises from 56.8% with the generic-skill baseline to 88.6% with the full automatic workflow.
• The interactive and multimodal evaluations identify two prominent remaining challenges.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Addressing a structural-engineering request requires more than a single answer; it requires a chain of interdependent artifacts: interpreted requirements, a computable model, validation records, solver outputs, code-check records, and a final report. Evaluations centered on question answering or script generation rarely verify this complete evidence chain and may therefore reward fluent outputs even when the underlying engineering workflow is incomplete, internally inconsistent, or non-executable. To address this limitation, we present StructureClaw, an artifact-centered workbench in which LLM agents operate through governed engineering skills, typed tools, shared artifact state, and local analysis backends. We also introduce StructureClaw-Bench, an executable benchmark of 150 controlled scenarios spanning standard workflow execution, interactive robustness, and multimodal structural-model reconstruction. A scenario succeeds only when all required artifact- and execution-level assertions pass in a single run. Across ten agent-model configurations, each evaluated on the same 50 standard cases, the average Success Rate rises from 56.8% with the generic-skill baseline to 88.6% with the full automatic workflow. The interactive and multimodal evaluations identify two prominent remaining challenges: safe handling of invalid numerical inputs and fixture-consistent reconstruction of structural models. These findings show that artifact-centered evaluation can expose workflow-level failures that are difficult to identify from final responses alone, providing a more rigorous basis for evaluating and improving structural-engineering agents. The code and benchmark are available at https://github.com/structureclaw/structureclaw.