Saved in:
Bibliographic Details
Main Authors: Arya, Mihir Shriniwas, Anish, Avinash, Ranjan, Aditya
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.19523
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914495235883008
author Arya, Mihir Shriniwas
Anish, Avinash
Ranjan, Aditya
author_facet Arya, Mihir Shriniwas
Anish, Avinash
Ranjan, Aditya
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19523
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Revac: A Social Deduction Reasoning Agent
Arya, Mihir Shriniwas
Anish, Avinash
Ranjan, Aditya
Artificial Intelligence
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.
title Revac: A Social Deduction Reasoning Agent
topic Artificial Intelligence
url https://arxiv.org/abs/2604.19523