Revac: A Social Deduction Reasoning Agent

TL;DR

Revac-8 is an AI agent designed for social deduction games like Mafia, emphasizing inference, memory, and adaptive communication to outperform competitors in complex social reasoning tasks.

Contribution

The paper introduces Revac-8, a multi-module AI architecture that combines memory, social graph analysis, and dynamic communication for social deduction games.

Findings

Revac-8 achieved first place in the MindGames Arena competition.

Structured memory and adaptive communication are crucial for success in social deduction AI.

The multi-module architecture outperforms simpler reasoning systems.

Abstract

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.