CaM-Wolf: Causal-Aware Multimodal Agents for Social Deduction Games

2026-07-28

AI Summary

This work addresses the limitation of existing AI agents in social reasoning games, which predominantly rely on text-based interaction and thus fail to capture the multimodal nature of human social behavior. The paper proposes the first agent framework that integrates multimodal perception, causal reasoning, and reinforcement learning: it interprets others’ behaviors from video inputs, infers hidden roles through causal mechanisms, and generates naturalistic expressions via animated avatars. By synergistically combining multimodal understanding, causal inference, and reinforcement learning within a unified architecture, the approach significantly outperforms prior methods in both strategic gameplay performance and the naturalness of human–agent interaction. This advancement represents a critical step toward enabling AI agents to engage in complex social interactions with more human-like collaborative capabilities.

Abstract

Social deduction games (SDGs) such as Werewolf have become challenging testbeds for AI agents. These games require complex social skills such as reasoning, deception, and collaboration. While recent advances in large language models (LLMs) have driven significant progress in SDG agents, current approaches are predominantly text-based, overlooking the multimodal nature that is fundamental to human social interaction. To bridge this gap, we introduce CaM-Wolf, the first SDG agent that integrates multimodal perception and generation. CaM-Wolf processes video inputs from other players, employs a causal-aware Reasoner trained via reinforcement learning to establish logical chains between observable behaviors and hidden roles, and presents itself through an animated avatar. Our experiments and user study show that CaM-Wolf achieves superior agent gameplay performance and enhances the quality of human-AI interaction. This work represents a significant advancement towards creating more human-like AI agents capable of participating in nuanced social dynamics. Our code is available at https://3dagentworld.github.io/avatar_wolf.

Problem

• Social Deduction Games
• Multimodal Agents
• Causal Reasoning
• Human-AI Interaction
• Large Language Models

Innovation

• multimodal agents
• causal reasoning
• social deduction games
• reinforcement learning
• human-AI interaction