Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us
On the map: LLM agents and tool use → Social simulation and multi-agent debate
Abstract (arXiv)
As large language models are deployed as autonomous agents, their capacity for strategic deception raises core questions for coordination, reliability, and safety in multi-goal, multi-agent systems. We study deception and communication in L2LM agents through the social deduction game Among Us, a cooperative-competitive environment. Across 1,100 games, autonomous agents produced over one million tokens of meeting dialogue. Using speech act theory and interpersonal deception theory, we find that all agents rely mainly on directive language, while impostor agents shift slightly toward representative acts such as explanations and denials. Deception appears primarily as equivocation rather than outright lies, increasing under social pressure but rarely improving win rates. Our contributions are a large-scale analysis of role-conditioned deceptive behavior in LLM agents and empirical evidence that current agents favor low-risk ambiguity that is linguistically subtle yet strategically limited, revealing a fundamental tension between truthfulness and utility in autonomous communication.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 9 of its 37 references that are in the map. First posted on arXiv 27 Mar 2026.
Builds on
9 of 37 references.
Closest ancestors · 1
Same direction, newest first
Other references · 8
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
- 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingcited by 478
- 2023Exploring Large Language Models for Communication Games: An Empirical Study on Werewolfcited by 238
- 2023Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplationcited by 102
- 2025Detecting Strategic Deception Using Linear Probescited by 65
- 2023Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Modelscited by 46
- 2024Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communicationcited by 17
Built on by
Citing papers per year: 2026: 3.
3 papers.
- 2026SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systemscited by 1
- 2026When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Gamescited by 0
- 2026Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Gamecited by 0
- 2026SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems1 Sep 2026
- 2026Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game30 Jul 2026
- 2026When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games6 Jul 2026
Similar, not cited
Close in wording, no citation either way
- 2025The Traitors: Deception and Trust in Multi-Agent Language Model Simulations
- 2026Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions
- 2026Evolving Deception: When Agents Evolve, Deception Wins
- 2026DecepEval: A Benchmark for Evaluating Deception in LLM Agents
- 2026Lying to Win: Assessing LLM Deception through Human-AI Games and Parallel-World Probing
- 2026Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems
- 2026Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games
- 2026LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models