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

• URL: http://arxiv.org/abs/2607.26120v1
• Date: Tue, 28 Jul 2026 17:48:54 GMT
• Title: Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems
• Abstract summary: Large Language Models (LLMs)-powered multi-agent systems are increasingly deployed in mixed-motive environments.<n>We propose a novel framework for evaluating objective misalignment using the social deduction game Werewolf.<n>Our results show that objective misalignment undermines outcomes in inherently adversarial environments.
• Score: 13.111181135818184
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Persuasive and Compliant Tendencies Predict Group Decision-Making in Humans and Language Models [65.21691850622413]
  Large language models (LLMs) are increasingly involved in group decision-making with humans.<n>We introduce DecisionQE, a questionnaire-based framework for measuring each model's persuasive and compliant tendencies.<n>We show that stronger persuasive tendency does not significantly improve group outcomes, whereas compliant-oriented models show more stable advantages in cooperation.
  arXiv  Detail & Related papers  (2026-08-08T15:50:56Z)
• Fair Agents: Balancing Multistakeholder Alignment in Multi-Agent Personalization Systems [3.2672011446202656]
  We propose a conceptual framework for designing fair multi-agent multistakeholder personalization systems.<n>Our framework integrates (i) methods to align stakeholder objectives and LLM agents, (ii) aggregation strategies, e.g., based on social choice theory, to form fair collective decisions.<n>We showcase our framework through a tourism use case and discuss possible applications in other domains, such as education and healthcare.
  arXiv  Detail & Related papers  (2026-05-04T09:18:38Z)
• FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments [60.3427704389541]
  Large Language Models are being increasingly deployed as the decision-making core of autonomous agents.<n>Yet, in conversational benchmarks, these agents frequently fail due to the cascading effects of incorrect decision-making.<n>We present the Failure-Aware Meta-Agentic framework to tackle these challenges.
  arXiv  Detail & Related papers  (2026-04-28T02:21:53Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Framing Effects in Independent-Agent Large Language Models: A Cross-Family Behavioral Analysis [5.9342526365947625]
  We examine how prompt framing influences decisions in a threshold voting task involving individual-group interest conflict.<n>Results show that prompt framing significantly influences choice distributions, often shifting preferences toward risk-averse options.
  arXiv  Detail & Related papers  (2026-03-02T16:10:34Z)
• A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents [8.007212170802807]
  We propose a framework for evaluating goal-directedness that integrates behavioural evaluation with interpretability-based analyses of models' internal representations.<n>We evaluate an agent against an optimal policy across varying grid sizes, obstacle densities, and goal structures.<n>We then use probing methods to decode the agent's internal representations of the environment state and its multi-step action plans.
  arXiv  Detail & Related papers  (2026-02-09T18:00:28Z)
• Understanding LLM Agent Behaviours via Game Theory: Strategy Recognition, Biases and Multi-Agent Dynamics [1.6487772637295166]
  We extend the FAIRGAME framework to evaluate Large Language Models (LLMs) behaviour in repeated social dilemmas.<n>We show that LLMs exhibit systematic, model- and language-dependent behavioural intentions, with linguistic framing at times exerting effects as strong as architectural differences.
  arXiv  Detail & Related papers  (2025-12-08T11:40:03Z)
• Can an Individual Manipulate the Collective Decisions of Multi-Agents? [53.01767232004823]
  M-Spoiler is a framework that simulates agent interactions within a multi-agent system to generate adversarial samples.<n>M-Spoiler introduces a stubborn agent that actively aids in optimizing adversarial samples.<n>Our findings confirm the risks posed by the knowledge of an individual agent in multi-agent systems.
  arXiv  Detail & Related papers  (2025-09-20T01:54:20Z)
• AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents [0.0]
  Large Language Model (LLM) agents become more widespread, associated misalignment risks increase.<n>In this work, we approach misalignment as a conflict between the internal goals pursued by the model and the goals intended by its deployer.<n>We introduce a misalignment propensity benchmark, textscAgentMisalignment, a benchmark suite designed to evaluate the propensity of LLM agents to misalign in realistic scenarios.
  arXiv  Detail & Related papers  (2025-06-04T14:46:47Z)
• ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning [53.817538122688944]
  We introduce Reinforced Meta-thinking Agents (ReMA) to elicit meta-thinking behaviors from Reasoning of Large Language Models (LLMs)<n>ReMA decouples the reasoning process into two hierarchical agents: a high-level meta-thinking agent responsible for generating strategic oversight and plans, and a low-level reasoning agent for detailed executions.<n> Empirical results from single-turn experiments demonstrate that ReMA outperforms single-agent RL baselines on complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-12T16:05:31Z)
• Generative multitask learning mitigates target-causing confounding [61.21582323566118]
  We propose a simple and scalable approach to causal representation learning for multitask learning. The improvement comes from mitigating unobserved confounders that cause the targets, but not the input. Our results on the Attributes of People and Taskonomy datasets reflect the conceptual improvement in robustness to prior probability shift.
  arXiv  Detail & Related papers  (2022-02-08T20:42:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.