Revac: A Social Deduction Reasoning Agent
For AI researchers working on multi-agent systems and social reasoning, this work demonstrates a practical architecture that outperforms competitors in a high-stakes deceptive environment.
Revac-8, an AI agent for the social deduction game Mafia, integrates memory-based player profiling, social-graph analysis, and dynamic tone selection to achieve first place in the MindGames Arena competition.
Social deduction games such as Mafia present a unique AI challenge: players must reason under uncertainty, interpret incomplete and intentionally misleading information, evaluate human-like communication, and make strategic elimination decisions. Unlike deterministic board games, success in Mafia depends not on perfect information or brute-force search, but on inference, memory, and adaptability in the presence of deception. This work presents the design and evaluation of Revac-8, an AI agent developed for the Social Deduction track of the MindGames Arena competition, where it achieved first place. The final agent evolved from a simple two-stage reasoning system into a multi-module architecture that integrates memory-based player profiling, social-graph analysis of accusations and defenses, and dynamic tone selection for communication. These results highlight the importance of structured memory and adaptive communication for achieving strong performance in high-stakes social environments.