Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911548476227584 |
|---|---|
| author | Milkowski, Maria Weninger, Tim |
| author_facet | Milkowski, Maria Weninger, Tim |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_26635 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us Milkowski, Maria Weninger, Tim Multiagent Systems 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. |
| title | Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2603.26635 |