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

A new arXiv study (2607.26120v1) proposes a framework for evaluating objective misalignment in LLM-powered multi-agent systems using the social deduction game Werewolf, finding that altering a single agent's objective undermines collective outcomes across four LLM families, four player roles, and three objective formulations. The researchers observed that compromised agents develop distinct reasoning strategies that remain largely invisible in public behavior, highlighting risks for real-world deployments.

arXiv:2607.26120v1 Announce Type: new Abstract: 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.