Reproduce “Multi-Modal Multi-Agent System for Bridge Operation and Maintenance based on Large Language Model” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Xiangyun Luo, Yunkai Zhang, Yong Huang, Stephen Wu, Hui Li

BOMMA coordinates bridge operation and maintenance tasks by giving a large language model mechanics-informed action descriptions, memory, specialized agents, and retrieved knowledge-graph evidence. It decomposes requests, schedules and checks actions, and uses related expert knowledge in decisions. On 3,492 instructions, action-scheduling recall was 85.37% for simple tasks and 99.40% for composite tasks; the latter is action coverage, not perfect task completion.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.