Mini-Mafia supplies an analytical model logit(p) = v*(m-d) for mafia win probability in LLM role interactions and uses Bayesian inference to estimate per-model parameters that predict tournament results with 76.6% Brier-score improvement over random.
Playing the werewolf game with artificial intelligence for language understanding
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2verdicts
UNVERDICTED 2representative citing papers
Revac-8, a multi-module AI with memory-based profiling, social-graph analysis, and dynamic tone selection, achieved first place in the MindGames Arena social deduction track.
citing papers explorer
-
Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia
Mini-Mafia supplies an analytical model logit(p) = v*(m-d) for mafia win probability in LLM role interactions and uses Bayesian inference to estimate per-model parameters that predict tournament results with 76.6% Brier-score improvement over random.
-
Revac: A Social Deduction Reasoning Agent
Revac-8, a multi-module AI with memory-based profiling, social-graph analysis, and dynamic tone selection, achieved first place in the MindGames Arena social deduction track.