# When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games

arXiv: https://arxiv.org/abs/2607.05132 · HTML: https://mlsanity.com/paper/2607.05132/

## Key facts

- No citing papers in the map yet (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 25 of its 39 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 25 of 25)

- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Playing repeated games with Large Language Models](https://mlsanity.com/paper/2305.16867/) (2023)
- [AI Deception: A Survey of Examples, Risks, and Potential Solutions](https://mlsanity.com/paper/2308.14752/) (2023)
- [Deception Abilities Emerged in Large Language Models](https://mlsanity.com/paper/2307.16513/) (2023)
- [How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis](https://mlsanity.com/paper/2402.05863/) (2024)
- [Honesty Is the Best Policy: Defining and Mitigating AI Deception](https://mlsanity.com/paper/2312.01350/) (2023)
- [The Traitors: Deception and Trust in Multi-Agent Language Model Simulations](https://mlsanity.com/paper/2505.12923/) (2025)
- [Simulating Cooperative Prosocial Behavior with Multi-Agent LLMs: Evidence and Mechanisms for AI Agents to Inform Policy Decisions](https://mlsanity.com/paper/2502.12504/) (2025)
- [When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models](https://mlsanity.com/paper/2506.04909/) (2025)
- [CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas](https://mlsanity.com/paper/2604.15267/) (2026)
- [When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas](https://mlsanity.com/paper/2505.19212/) (2025)
- [WOLF: Werewolf-based Observations for LLM Deception and Falsehoods](https://mlsanity.com/paper/2512.09187/) (2025)
- [When Do Large Language Models Exhibit Unsolicited Deception?](https://mlsanity.com/paper/2504.00285/) (2025)
- [LLM Bidders Preserve the Mechanism-Level Orderings of Human Bidders](https://mlsanity.com/paper/2507.09083/) (2025)
- [Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL](https://mlsanity.com/paper/2510.14318/) (2025)
- [Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia](https://mlsanity.com/paper/2509.23023/) (2025)
- [GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory](https://mlsanity.com/paper/2602.12316/) (2026)
- [LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models](https://mlsanity.com/paper/2603.06874/) (2026)
- [Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us](https://mlsanity.com/paper/2603.26635/) (2026)
- [Cheap Talk, Empty Promise: Frontier LLMs easily break public promises for self-interest](https://mlsanity.com/paper/2604.04782/) (2026)
- [Evaluating Creativity and Deception in Large Language Models: A Simulation Framework for Multi-Agent Balderdash](https://mlsanity.com/paper/2411.10422/) (2024)

## Abstract (arXiv)

As large language models are deployed as autonomous agents that communicate intentions before acting, a critical safety question is whether agents that publicly commit to actions will honor those commitments. We place LLM agents in repeated n-player games with a three-stage protocol that separates private intent, public announcement, and final action, allowing us to identify whether each deviation from a stated announcement was already planned during private deliberation. Evaluating three frontier models across six games in homogeneous and heterogeneous groups over 10 rounds, we report two findings. First, when agents deviate from their announcements, the deviation is predominantly already stated in their private plan (exceeding 90% in the highest-deception conditions), yet this is not a fixed model property: the same model ranges from perfect honesty to near-total deviation across games. Second, different models interpret announcements incompatibly, some as binding commitments and others as cheap talk, producing payoff gaps that emerge in Round~0 and persist across all 10 rounds. Systems that combine models from different providers therefore cannot assume shared announcement semantics and require empirical testing of model interactions before deployment.