Reproduce “Agentic-Priors: Using Large Language Models to Address the Cold Start Problem in Preference Elicitation” 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
Bruno Arcanjo, Zhaoxing Li, Sebastian Stein
Agentic-Priors uses an LLM to estimate trade-offs from a task and user profile, mapping them to a prior for a multinomial logit model that Bayesian learning updates as choices arrive. Across seven datasets, it improves cold-start accuracy over an uninformed prior by 5–40 points. On LPMC, accuracy is 61.9% versus 21.6%, but hierarchical Bayes models generally perform better using population choices.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.