# Among Us: A Sandbox for Measuring and Detecting Agentic Deception

arXiv: https://arxiv.org/abs/2504.04072 · HTML: https://mlsanity.com/paper/2504.04072/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 5 Apr 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)
- Mechanistic interpretability / [Probing deception, bias and beliefs](https://mlsanity.com/mechinterp/probing-deception-bias-and-beliefs/)

## Builds on (most cited first, 24 of 24)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Detecting Pretraining Data from Large Language Models](https://mlsanity.com/paper/2310.16789/) (2023)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [AI Control: Improving Safety Despite Intentional Subversion](https://mlsanity.com/paper/2312.06942/) (2023)
- [A Survey on Large Language Model-Based Game Agents](https://mlsanity.com/paper/2404.02039/) (2024)
- [Detecting Strategic Deception Using Linear Probes](https://mlsanity.com/paper/2502.03407/) (2025)
- [Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning](https://mlsanity.com/paper/2210.05492/) (2022)
- [Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models](https://mlsanity.com/paper/2308.01404/) (2023)
- [Gradual Disempowerment: Systemic Existential Risks from Incremental AI Development](https://mlsanity.com/paper/2501.16946/) (2025)
- [Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy](https://mlsanity.com/paper/2407.06813/) (2024)
- [AMONGAGENTS: Evaluating Large Language Models in the Interactive Text-Based Social Deduction Game](https://mlsanity.com/paper/2407.16521/) (2024)
- [Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models](https://mlsanity.com/paper/2501.16513/) (2025)
- [Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2502.06060/) (2025)
- [Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models](https://mlsanity.com/paper/2412.17128/) (2024)
- [Line Goes Up? Inherent Limitations of Benchmarks for Evaluating Large Language Models](https://mlsanity.com/paper/2502.14318/) (2025)
- [Multi-Agent Training for Pommerman: Curriculum Learning and Population-based Self-Play Approach](https://mlsanity.com/paper/2407.00662/) (2024)
- [LLMs are Superior Feedback Providers: Bootstrapping Reasoning for Lie Detection with Self-Generated Feedback](https://mlsanity.com/paper/2408.13915/) (2024)

## Built on by (most cited first, 26 of 26)

- [TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems](https://mlsanity.com/paper/2506.04133/) (2025)
- [Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage](https://mlsanity.com/paper/2601.01685/) (2026)
- [Difficulties with Evaluating a Deception Detector for AIs](https://mlsanity.com/paper/2511.22662/) (2025)
- [Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia](https://mlsanity.com/paper/2509.23023/) (2025)
- [Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems](https://mlsanity.com/paper/2602.05176/) (2026)
- [Detecting Multi-Agent Collusion Through Multi-Agent Interpretability](https://mlsanity.com/paper/2604.01151/) (2026)
- [A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i](https://mlsanity.com/paper/2505.00808/) (2025)
- [LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models](https://mlsanity.com/paper/2603.06874/) (2026)
- [PhenoAssistant: A Conversational Multi-Agent AI System for Automated Plant Phenotyping](https://mlsanity.com/paper/2504.19818/) (2025)
- [Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence](https://mlsanity.com/paper/2604.08169/) (2026)
- [Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us](https://mlsanity.com/paper/2603.26635/) (2026)
- [Shall We Play a Game? Language Models for Open-ended Wargames](https://mlsanity.com/paper/2509.17192/) (2025)
- [MaMa: A Game-Theoretic Approach for Designing Safe Agentic Systems](https://mlsanity.com/paper/2602.04431/) (2026)
- [MafiaScope: Non-Invasive, Time-Resolved Belief Probing for LLM Agents in Social Deduction Games](https://mlsanity.com/paper/2607.10645/) (2026)
- [Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation](https://mlsanity.com/paper/2607.15434/) (2026)
- [Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models](https://mlsanity.com/paper/2512.00349/) (2025)
- [ElecTwit: A Framework for Studying Persuasion in Multi-Agent Social Systems](https://mlsanity.com/paper/2601.00994/) (2026)
- [Evaluating Large Language Models in a Complex Hidden Role Game](https://mlsanity.com/paper/2605.22826/) (2026)
- [Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network](https://mlsanity.com/paper/2605.25815/) (2026)
- [RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue](https://mlsanity.com/paper/2606.13310/) (2026)
- [Disentangling Deception and Hallucination Failures in LLMs](https://mlsanity.com/paper/2602.14529/) (2026)
- [SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems](https://mlsanity.com/paper/2604.16022/) (2026)
- [Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems](https://mlsanity.com/paper/2607.26120/) (2026)
- [Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game](https://mlsanity.com/paper/2607.28146/) (2026)
- [MARBO: Relational Belief Grounding for LLM Agents in Social Deduction Games](https://mlsanity.com/paper/2609.06563/) (2026)
- [MCAIR: Monitoring and Correcting Agent Unfaithfulness via Internal Representations](https://mlsanity.com/paper/2610.19679/) (2026)

## Abstract (arXiv)

Prior studies on deception in language-based AI agents typically assess whether the agent produces a false statement about a topic, or makes a binary choice prompted by a goal, rather than allowing open-ended deceptive behavior to emerge in pursuit of a longer-term goal. To fix this, we introduce Among Us, a sandbox social deception game where LLM-agents exhibit long-term, open-ended deception as a consequence of the game objectives. While most benchmarks saturate quickly, Among Us can be expected to last much longer, because it is a multi-player game far from equilibrium. Using the sandbox, we evaluate 18 proprietary and open-weight LLMs and uncover a general trend: models trained with RL are comparatively much better at producing deception than detecting it. We evaluate the effectiveness of methods to detect lying and deception: logistic regression on the activations and sparse autoencoders (SAEs). We find that probes trained on a dataset of "pretend you're a dishonest model:.." generalize extremely well out-of-distribution, consistently obtaining AUROCs over 95% even when evaluated just on the deceptive statement, without the chain of thought. We also find two SAE features that work well at deception detection but are unable to steer the model to lie less. We hope our open-sourced sandbox, game logs, and probes serve to anticipate and mitigate deceptive behavior and capabilities in language-based agents.