Reproduce “Hierarchical Multi-Agent Reasoning Systems for Knowledge-Grounded Material Substitution” 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
Tarjei Paule Hage, Subhadeep Pal, Wei Lu, Yu-Chuan Hsu, Gayla Lyon, Jiezhu Jin, Markus J. Buehler
The authors present MARS, a multi-agent system for proposing material substitutions through requirement analysis, evidence-grounded candidate search, and processing assessment that can return blockers to the search. In a THV case, it proposed an ENGAGE/EVOH/OTS stack judged internally manufacturable. On the THV evaluation, it scored 5.47 versus 2.99 for a matched single-call baseline; neither proposal nor route was experimentally validated.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.