Revac: A Social Deduction Reasoning Agent

• URL: http://arxiv.org/abs/2604.19523v1
• Date: Tue, 21 Apr 2026 14:45:10 GMT
• Title: Revac: A Social Deduction Reasoning Agent
• Abstract summary: Revac-8 is an AI agent developed for the Social Deduction track of the MindGames Arena competition.<n>Revac-8 integrates memory-based player profiling, social-graph analysis of accusations and defenses, and dynamic tone selection for communication.<n>Results highlight the importance of structured memory and adaptive communication for achieving strong performance in high-stakes social environments.
• Score: 1.0164807666962064
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs [54.81359054218573]
  We introduce Mindgames, a multi-game arena and evaluation platform for large language models (LLMs)<n>Mindgames provides a unified interaction interface, TrueSkill-based rating, and full trajectory logging across four game environments.<n>We analyze 29,571 multi-agent games with turn-level observations, actions, and rewards, together with MG-Ref, a deterministic offline tournament protocol.
  arXiv  Detail & Related papers  (2026-05-28T07:33:47Z)
• QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents [38.13248430205106]
  QUACK is an evaluation framework for auditing the grounding of agent language in multimodal social reasoning.<n>It reconstructs each agent's ground-truth trajectory from engine logs and checks every discussion claim against it.<n>We find that even the strongest agent hallucinates 15.1% of its verifiable spatial claims and makes over half of its accusations without grounded evidence.
  arXiv  Detail & Related papers  (2026-05-26T14:19:08Z)
• Communicate-Predict-Act: Evaluating Social Intelligence of Agents [15.575081867336529]
  We introduce a multiplayer arena of mixed cooperative and competitive social games to study large language model (LLM) social intelligence.<n>We analyze gameplay traces to extract sociocognitive metrics capturing action prediction, communicative influence, strategic reasoning, and tradeoffs under conflicting interests.
  arXiv  Detail & Related papers  (2026-04-09T19:40:15Z)
• Improvisational Games as a Benchmark for Social Intelligence of AI Agents: The Case of Connections [0.0]
  Playing Connections combines skills in knowledge retrieval, summarization and awareness of cognitive states of other agents.<n>We show how the game serves as a good benchmark for social intelligence abilities of language model based agents.
  arXiv  Detail & Related papers  (2026-03-31T22:16:25Z)
• Evaluating Language Models' Evaluations of Games [65.49017696754825]
  We advocate for a new paradigm that assesses AI systems' evaluation of games.<n>We leverage a large-scale dataset of over $100$ novel board games and over 450 human judgments.<n>Our results show that reasoning models are generally more aligned to people in their evaluations of games than non-reasoning language models.
  arXiv  Detail & Related papers  (2025-10-13T02:45:37Z)
• PokéAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red [4.558478169296784]
  We introduce Pok'eAI, the first text-based, multi-agent large language model (LLM) framework designed to autonomously play and progress through Pok'emon Red.<n>Our system consists of three specialized agents-Planning, Execution, and Critique-each with its own memory bank, role, and skill set.
  arXiv  Detail & Related papers  (2025-06-30T10:09:13Z)
• Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models [75.85319609088354]
  Sentient Agent as a Judge (SAGE) is an evaluation framework for large language models.<n>SAGE instantiates a Sentient Agent that simulates human-like emotional changes and inner thoughts during interaction.<n>SAGE provides a principled, scalable and interpretable tool for tracking progress toward genuinely empathetic and socially adept language agents.
  arXiv  Detail & Related papers  (2025-05-01T19:06:10Z)
• FAIRGAME: a Framework for AI Agents Bias Recognition using Game Theory [51.96049148869987]
  We present FAIRGAME, a Framework for AI Agents Bias Recognition using Game Theory.<n>We describe its implementation and usage, and we employ it to uncover biased outcomes in popular games among AI agents.<n>Overall, FAIRGAME allows users to reliably and easily simulate their desired games and scenarios.
  arXiv  Detail & Related papers  (2025-04-19T15:29:04Z)
• PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games [21.639516389561837]
  We introduce WellPlay, a reasoning dataset for multi-agent conversational inference in Murder Mystery Games (MMGs)<n>WellPlay comprises 1,482 inferential questions across 12 games, spanning objectives, reasoning, and relationship understanding.<n>We present PLAYER*, a novel framework for Large Language Model (LLM)-based agents in MMGs.
  arXiv  Detail & Related papers  (2024-04-26T19:07:30Z)
• Incorporating Rivalry in Reinforcement Learning for a Competitive Game [65.2200847818153]
  This work proposes a novel reinforcement learning mechanism based on the social impact of rivalry behavior. Our proposed model aggregates objective and social perception mechanisms to derive a rivalry score that is used to modulate the learning of artificial agents.
  arXiv  Detail & Related papers  (2022-08-22T14:06:06Z)
• Theoretical Modeling of Communication Dynamics [0.0]
  Reputation game focuses on the trustworthiness of the participating agents, their honesty as perceived by others. Various sender and receiver strategies are studied, like sycophant, egocentricity, pathological lying, and aggressiveness for senders. Minimalist malicious strategies are identified, like being manipulative, dominant, or destructive, which significantly increase reputation at others' costs.
  arXiv  Detail & Related papers  (2021-06-09T22:02:19Z)
• Signaling in Bayesian Network Congestion Games: the Subtle Power of Symmetry [66.82463322411614]
  The paper focuses on the problem of optimal ex ante persuasive signaling schemes, showing that symmetry is a crucial property for its solution. We show that an optimal ex ante persuasive scheme can be computed in time when players are symmetric and have affine cost functions.
  arXiv  Detail & Related papers  (2020-02-12T19:38:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.