Verbal Werewolf: Engage Users with Verbalized Agentic Werewolf Game Framework
This addresses the need for more engaging and anthropomorphic AI-human collaboration in social deduction games, particularly in post-pandemic contexts, though it is incremental as it builds on existing LLM capabilities with TTS optimization.
The researchers tackled the problem of latency and lack of user engagement in AI-powered social deduction games like Werewolf by proposing Verbal Werewolf, a system that integrates LLMs with a fine-tuned TTS module for near real-time verbal gameplay, resulting in significantly improved user engagement compared to text-only frameworks.
The growing popularity of social deduction games has created an increasing need for intelligent frameworks where humans can collaborate with AI agents, particularly in post-pandemic contexts with heightened psychological and social pressures. Social deduction games like Werewolf, traditionally played through verbal communication, present an ideal application for Large Language Models (LLMs) given their advanced reasoning and conversational capabilities. Prior studies have shown that LLMs can outperform humans in Werewolf games, but their reliance on external modules introduces latency that left their contribution in academic domain only, and omit such game should be user-facing. We propose \textbf{Verbal Werewolf}, a novel LLM-based Werewolf game system that optimizes two parallel pipelines: gameplay powered by state-of-the-art LLMs and a fine-tuned Text-to-Speech (TTS) module that brings text output to life. Our system operates in near real-time without external decision-making modules, leveraging the enhanced reasoning capabilities of modern LLMs like DeepSeek V3 to create a more engaging and anthropomorphic gaming experience that significantly improves user engagement compared to existing text-only frameworks.