Skip to content

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

Jul 2026 · arXiv.org · Vol abs/2607.26393 · 0 citations · 50 references
Computer Science

TL;DR

CaM-Wolf is introduced, the first SDG agent that integrates multimodal perception and generation and achieves superior agent gameplay performance and enhances the quality of human-AI interaction.

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.

View source

Similar papers

#small language model Book Open access Sep 2026

Evaluating LLM Social Cognition Through Multi-Agentic Strategic Games

A strategic game arena is introduced that situates LLM agents in social deduction scenarios inspired by Among Us, requiring theory of mind, deception detection, and cooperative deliberation under uncertainty, and motivates architectural changes for virtual agents that must cooperate with humans.

Kevin Kurian, Kevin Scroggins, Emmanuel Dorley et al. · 0 citations
Preprint Aug 2026

Social Gym and SPaRTan: Benchmarking and Improving LLM Social Reasoning via Multi-Agent Game Tournaments

Social Gym is introduced, an environment of 21 multi-agent social games whose rule-decided outcomes make agent performance verifiable and objective, and SPaRTan (Self-Play and Reflect-Transfer), a training-free self-improvement loop that offers a reproducible, verifiable foundation for measuring and improving LLM socia...

Keyu He, Xuhui Zhou, M. Sap · 1 citation
#computer vision Preprint Aug 2026

SocialReasonBench: A Video-QA Benchmark for Social Reasoning with Counterfactual Narrative Videos

SocialReasonBench is introduced, a video multiple-choice QA benchmark for evaluating socially grounded reasoning in scenarios derived from interactive narratives and develops a multi-agent curation pipeline that localizes socially meaningful clips, grounds answer labels in game-state signals, and generates theory-guide...

Zhe-Yu Huang, Zijing Shi, Hao-Zhe Luo et al. · 0 citations
2025

Collaborative Reasoner: Self-Improving Social Agents with Synthetic Conversations

This work presents Collaborative Reasoner, a framework to evaluate and improve the collaborative reasoning abilities of language models, and proposes a self-play method to generate synthetic multi-turn preference data and further train the language models to be better collaborators.

Ansong Ni, Ruta Desai, Yang Li et al. · 7 citations
Book Open access Sep 2026

Games of Diplomacy: Eliciting Spite Against Automated Opponents Through Structured Game Environments

This study successfully elicited spiteful behavior in human participants playing against an automated opponent compared to controls across all experimental conditions, and suggests that the decision to act spitefully may not be strongly influenced by associated costs and risks, contrary to initial hypotheses.

Noah Ari, Darryl Roman, Nusrath Jahan et al. · 0 citations

Do Personality-Tuned LLMs Make Better Social Agents?

This work investigates whether personality-aware fine-tuning can reduce the consistency and controllability of personality-conditioned dialogue generation compared with instruction prompting alone, and indicates that fine-tuned models are not better at role-playing different personalities than their respective baseline...

Tim Krabbe, Xiao-Dan Shi · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.