Reproduce “An LLM-Agentic Framework for Intelligent Work Order Management in Industrial Maintenance” 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
Nianjun Zhou, Dhaval Patel
The authors present CodeReAct, an agent that turns natural-language maintenance requests into executable Python analyses of structured industrial records, including work orders and alerts. It uses a language model’s Thought and Action steps, execution feedback, and an outer reflection loop. On 36 chiller tasks, it completed 29 with Thought versus 20 without; next-work-order matches varied by chiller, not establishing general prediction.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.