Reproduce “Automating Modelica Module Generation Using Large Language Models: A Case Study on Building Control Description Language” 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
Hanlong Wan, Xing Lu, Yan Chen, Karthik Devaprasad, Laura Hinkle
The authors develop a workflow for LLM-generated HVAC control modules in Modelica using CDL library parts. It turns task descriptions into code, compiles and simulates it with OpenModelica, and retains human review of behavior. Across five component-level control tasks, authors report an 83% pipeline success rate; this does not establish whole-building control.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.