Reproduce “Game-Theoretic Solvers with Bayesian Opponent Modeling and Moral Rhetoric Framing for GLEE” 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
Hayden Arnold
The GLEE agent separates numeric decisions from language in sequential bargaining, negotiation, and persuasion, using game-theoretic solvers, online opponent estimates, and a language model for messages. In a synthetic ablation, removing buyer-trust estimation raised persuasion’s average normalized score from +0.269 to +0.312. Observed framing differences are associations, not causal evidence, and the ablation does not establish live-game effects.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.