# Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems

arXiv: https://arxiv.org/abs/2607.26120 · HTML: https://mlsanity.com/paper/2607.26120/

## 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 20 of its 45 references that are in the map.
- First posted on arXiv 28 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, 20 of 20)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast](https://mlsanity.com/paper/2402.08567/) (2024)
- [Red-Teaming LLM Multi-Agent Systems via Communication Attacks](https://mlsanity.com/paper/2502.14847/) (2025)
- [Evil Geniuses: Delving into the Safety of LLM-based Agents](https://mlsanity.com/paper/2311.11855/) (2023)
- [Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities](https://mlsanity.com/paper/2407.07791/) (2024)
- [Multi-Agent Systems Execute Arbitrary Malicious Code](https://mlsanity.com/paper/2503.12188/) (2025)
- [Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction](https://mlsanity.com/paper/2407.13943/) (2024)
- [Neither Valid nor Reliable? Investigating the Use of LLMs as Judges](https://mlsanity.com/paper/2508.18076/) (2025)
- [Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy](https://mlsanity.com/paper/2407.06813/) (2024)
- [textitAgents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks](https://mlsanity.com/paper/2504.00218/) (2025)
- [AMONGAGENTS: Evaluating Large Language Models in the Interactive Text-Based Social Deduction Game](https://mlsanity.com/paper/2407.16521/) (2024)
- [Among Us: A Sandbox for Measuring and Detecting Agentic Deception](https://mlsanity.com/paper/2504.04072/) (2025)
- [TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems](https://mlsanity.com/paper/2511.05269/) (2025)
- [Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf](https://mlsanity.com/paper/2405.19946/) (2024)
- [The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process](https://mlsanity.com/paper/2506.01080/) (2025)
- [Combating Adversarial Attacks with Multi-Agent Debate](https://mlsanity.com/paper/2401.05998/) (2024)
- [Helmsman of the Masses? Evaluate the Opinion Leadership of Large Language Models in the Werewolf Game](https://mlsanity.com/paper/2404.01602/) (2024)
- [Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia](https://mlsanity.com/paper/2509.23023/) (2025)
- [When to adjust alpha during multiple testing: A consideration of disjunction, conjunction, and individual testing](https://mlsanity.com/paper/2107.02947/) (2021)

## Abstract (arXiv)

Large Language Models (LLMs)-powered multi-agent systems are increasingly deployed in mixed-motive environments, where agents operate under asymmetric information and strategic deception due to conflicting or hidden objectives. In these settings, misalignment with collective goals becomes a central concern. We propose a novel framework for evaluating objective misalignment using the social deduction game Werewolf, modifying the objective of a single agent while preserving its assigned role. Across LLMs from four different model families and sizes, four player roles, and three objective formulations, we introduce a dual analysis of the agents' internal reasoning and their public cheap-talk behavior (i.e costless, non-binding communication that does not directly affect the agents' utilities), complemented by an analysis of game outcomes. Our results show that objective misalignment undermines outcomes in inherently adversarial environments, an effect exacerbated by asymmetric information and specialized roles. While compromised agents consistently develop distinct objective-dependent reasoning strategies, these adaptations remain largely invisible in their public behavior. More broadly, our findings suggest that even subtle objective misalignment can profoundly affect collective decision-making, highlighting the need for effective mitigation strategies for LLM-based multi-agent systems.