Reproduce “Large Decision Models: Repurposing Large Language Models as Single-Pass Decision Makers” 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

Ziyi Chen, Yan Zhang, Jianhui Wei, Jianing Yin, Daoan Zhang

The authors train a single-pass interface for typed decisions, returning probabilities over labels supplied at run time without generating answer sequences. Diverse Decision Supervision broadens training data, and Self-Posed Reasoning Distillation adds filtered answer-vote targets. Against a step-matched baseline, the combined recipe improves macro-accuracy by 1.8 percentage points on synthetic and 1.5 on human-labelled tests; against a selected baseline, the synthetic gain is not significant.

Summary by alphaXiv.

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