Game-Theoretic Solvers with Bayesian Opponent Modeling and Moral Rhetoric Framing for GLEE

We describe the agent we submitted to the GLEE competition, which plays bargaining, negotiation, and persuasion games against a shared pool of human and AI opponents. The agent is built around three components: a classical game-theoretic solver computes numeric moves, an online Bayesian layer estimates each opponent's hidden type to feed that solver, and a language model writes accompanying messages. We utilize Rubinstein bargaining for bargaining, Faratin concession for negotiation, and Kamenica--Gentzkow disclosure for persuasion, and adapt those models to live opponents using two separate layers: a Bayesian estimate of the opponent's hidden discount factor, reservation value, or signaling reliability, and a Thompson sampling bandit over five moral-foundation framings coupled with an evidence-intuition spectrum to establish message register. Most of the development effort went into a recurring problem, that a policy optimal under an idealized assumption performs poorly in certain settings; we report associated failure modes, guardrails we built, and our hypotheses. We additionally evaluate our model over 13,200 Monte Carlo games against 11 synthetic opponent archetypes, an ablation of the opponent-modeling layer, and an extensive analysis of 9,337 live-game messages in which moral rhetoric framing in the persuasion setting is strongly correlated with whether the buyer purchased ($\chi^2=616.7$, $p \approx 3.7\times10^{-132}$), surviving controls for quality, round, and configuration.