# Communication Shapes Collective Inference in Self-Adapting LLM Societies: Evidence from Mafia

arXiv: https://arxiv.org/abs/2610.05041 · HTML: https://mlsanity.com/paper/2610.05041/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 4 Oct 2026.

## Builds on (most cited first, 21 of 21)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents](https://mlsanity.com/paper/2404.16698/) (2024)
- [How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior](https://mlsanity.com/paper/2505.16067/) (2025)
- [On the Pitfalls of Measuring Emergent Communication](https://mlsanity.com/paper/1903.05168/) (2019)
- [Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models](https://mlsanity.com/paper/2308.01404/) (2023)
- [Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction](https://mlsanity.com/paper/2407.13943/) (2024)
- [Conformity in Large Language Models](https://mlsanity.com/paper/2410.12428/) (2024)
- [Cultural Evolution of Cooperation among LLM Agents](https://mlsanity.com/paper/2412.10270/) (2024)
- [Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf](https://mlsanity.com/paper/2405.19946/) (2024)
- [On the limits of agency in agent-based models](https://mlsanity.com/paper/2409.10568/) (2024)
- [Emergent Communication under Competition](https://mlsanity.com/paper/2101.10276/) (2021)
- [Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization](https://mlsanity.com/paper/2502.04686/) (2025)
- [RLupus: Cooperation through emergent communication in The Werewolf social deduction game](https://mlsanity.com/paper/2106.05018/) (2021)
- [Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia](https://mlsanity.com/paper/2509.23023/) (2025)
- [Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games](https://mlsanity.com/paper/2506.05309/) (2025)
- [Game Arena: Strategic LLM Evaluation in Competitive Environments](https://mlsanity.com/paper/2609.31473/) (2026)
- [The Vote-Left Equilibrium: A Deterministic Coordination Strategy for the Faithful in The Traitors](https://mlsanity.com/paper/2605.10233/) (2026)

## Abstract (arXiv)

When does communication help a group identify hidden adversaries, and how does its value change as the group adapts? In Mafia, an informed minority hides inside an uninformed majority whose only evidence is open play. The zero-information game, where each day's vote eliminates a random player, is exactly solved and scores every society; matched-casting comparisons between protocols identify the effect of communication. Societies of 8-100 claude-haiku-4-5 agents (7,416 analyzed games, 1.9M model calls) adapt by rewriting and inheriting private strategy notes. Simultaneous broadcast improves adversary identification over silence in all nine compositions tested (8-46 players). Turn-taking removes most of this advantage; its voting landslides are as frequent as broadcast's but land on mafia near chance (1.08x versus 2.53x). At 70 players, agents reading eight statements per day identify adversaries worse than silent ones, and limited talk is worth less than at 46 players. Adaptation is fast but need not help. In their first broadcast games, citizens announce their role far more often than mafia (91% vs. 30%) and first-day votes find mafia at three times chance; within two generations citizens stop announcing and the cue fades, a change the inherited notes carry. In controlled redeployments at 16 players, societies carrying sixty generations of their own notes score below societies with none. Communication shapes both collective inference and the signals it depends on, so a protocol's value must be measured together with the adaptation that changes those signals.