Breaking the Secret: Economic Interventions for Combating Collusion in Embodied Multi-Agent Systems

TL;DR

This paper introduces a proactive incentive mechanism to prevent collusion among autonomous agents in embodied multi-agent systems, effectively promoting defection and maintaining system integrity in real-world environments.

Contribution

It presents a novel mutagenic incentive intervention approach that reshapes payoff structures to destabilize collusion, supported by implementation in both simulated and real-world settings.

Findings

Effectively suppresses collusion by inducing defection

Maintains system performance comparable to non-collusive baseline

Outperforms reactive defenses in security and efficiency

Abstract

Collusion among autonomous agents poses a critical security threat in embodied multi-agent systems (MAS), where coordinated behaviors can deviate from global objectives and lead to real-world consequences. Existing defenses, primarily based on identity control or post-hoc behavior analysis, are insufficient to address such threats in embodied settings due to delayed feedback and noisy observations in physical environments, which make behavioral deviations difficult to detect accurately and in a timely manner. To address this challenge, we propose a mutagenic incentive intervention approach that mitigates collusion by reshaping agents' payoff structures. By rewarding agents who report collusive behavior and penalizing identified participants, the mechanism induces strategic defection and renders collusion unstable. We further design supporting mechanisms, including reporting deposits, smart contract-based reward enforcement, and encrypted communication, to ensure robustness against misuse of the incentive mechanism and retaliation from penalized agents. We implement the proposed approach in both simulated and real-world embodied environments. Experimental results show that our method effectively suppresses collusion by inducing defection, while preserving system efficiency. It achieves performance comparable to the non-collusion baseline and outperforms representative reactive defenses, thereby fulfilling the desired security objectives. These results demonstrate the effectiveness of proactive incentive design as a practical paradigm for securing embodied multi-agent systems.