Skip to content
AI News HubLIVE
Original source2 min read

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

Summary

Researchers introduce CaM-Wolf, the first social deduction game agent that integrates multimodal perception and generation. It processes video inputs from other players, uses a reinforcement-learning-trained causal-aware reasoner to link observable behaviors to hidden roles, and presents itself through an animated avatar. Experiments and a user study show improved gameplay performance and human-AI interaction quality. The paper is accepted by ACMMM 2026.

SourcearXiv AIAuthor: Zheng Zhang, Nanjie Yao, Jiarui He, Deheng Ye, Peilin Zhao, Hao Wang
CaM-Wolf: Causal-Aware Multimodal Agents for Social Deduction Games
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 29 Jul 2026]

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

View a PDF of the paper titled CaM-Wolf: Causal-Aware Multimodal Agents for Social Deduction Games, by Zheng Zhang and 5 other authors

View PDF HTML (experimental)

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 this https URL.

Comments: Accepted by ACMMM 2026

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2607.26393 [cs.AI]

(or arXiv:2607.26393v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2607.26393

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Zheng Zhang [view email] [v1] Wed, 29 Jul 2026 01:58:36 UTC (1,201 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled CaM-Wolf: Causal-Aware Multimodal Agents for Social Deduction Games, by Zheng Zhang and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-07

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • CaM-Wolf is the first social deduction game agent to combine multimodal perception and generation.
  • A reinforcement-learning-trained causal-aware reasoner links observable player behaviors to hidden roles.
  • The agent expresses itself through an animated avatar, enhancing natural human-AI interaction.
  • Experiments and a user study show superior gameplay performance and interaction quality, with code publicly available.

Highlights and analysis are generated automatically and may contain errors. Check the original source.