# Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games

arXiv: https://arxiv.org/abs/2506.05309 · HTML: https://mlsanity.com/paper/2506.05309/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 15 of 15)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game](https://mlsanity.com/paper/2310.18940/) (2023)
- [Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation](https://mlsanity.com/paper/2310.01320/) (2023)
- [Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs](https://mlsanity.com/paper/2403.05020/) (2024)
- [TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog](https://mlsanity.com/paper/2010.10874/) (2020)
- [AvalonBench: Evaluating LLMs Playing the Game of Avalon](https://mlsanity.com/paper/2310.05036/) (2023)
- [Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics](https://mlsanity.com/paper/2503.01174/) (2025)
- [Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence](https://mlsanity.com/paper/2210.07109/) (2022)
- [Putting the Con in Context: Identifying Deceptive Actors in the Game of Mafia](https://mlsanity.com/paper/2207.02253/) (2022)
- [The Mafiascum Dataset: A Large Text Corpus for Deception Detection](https://mlsanity.com/paper/1811.07851/) (2018)
- [Beyond Turn-taking: Introducing Text-based Overlap into Human-LLM Interactions](https://mlsanity.com/paper/2501.18103/) (2025)
- [SAUCE: Synchronous and Asynchronous User-Customizable Environment for Multi-Agent LLM Interaction](https://mlsanity.com/paper/2411.03397/) (2024)

## Built on by (most cited first, 6 of 6)

- [Shall We Play a Game? Language Models for Open-ended Wargames](https://mlsanity.com/paper/2509.17192/) (2025)
- [Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games](https://mlsanity.com/paper/2601.13709/) (2026)
- [RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue](https://mlsanity.com/paper/2606.13310/) (2026)
- [Cooperation Breakdown in LLM Agents Under Communication Delays](https://mlsanity.com/paper/2602.11754/) (2026)
- [Detecting AI Impostors: How Do Middle Schoolers Identify LLM Agents in a Live Collaborative Setting?](https://mlsanity.com/paper/2608.30948/) (2026)
- [Communication Shapes Collective Inference in Self-Adapting LLM Societies: Evidence from Mafia](https://mlsanity.com/paper/2610.05041/) (2026)

## Abstract (arXiv)

LLMs are used predominantly in synchronous communication, where a human user and a model communicate in alternating turns. In contrast, many real-world settings are asynchronous. For example, in group chats, online team meetings, or social games, there is no inherent notion of turns. In this work, we develop an adaptive asynchronous LLM agent consisting of two modules: a generator that decides what to say, and a scheduler that decides when to say it. To evaluate our agent, we collect a unique dataset of online Mafia games, where our agent plays with human participants. Overall, our agent performs on par with human players, both in game performance metrics and in its ability to blend in with the other human players. Our analysis shows that the agent's behavior in deciding when to speak closely mirrors human patterns, although differences emerge in message content. We make all of our code and data publicly available. This work paves the way for integration of LLMs into realistic human group settings, from assistance in team discussions to educational and professional environments where complex social dynamics must be navigated.