Detecting Multi-Agent Collusion Through Multi-Agent Interpretability

arXiv:2604.01151 · cs.AI, cs.LG, cs.MA · Submitted 2026-04-01 · Read on arXiv

cs.AI, cs.LG, cs.MA

Submitted: 2026-04-01

Updated: 2026-10-12

Terminology

• AUROC — 2× in this paper · explained in 2 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 7 episodes
• Linear probe — 1× in this paper · explained in 2 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes

Sources

• Understanding intermediate layers using linear classifier probes
• Caught in the Act: a mechanistic approach to detecting deception
• Discovering Latent Knowledge in Language Models Without Supervision
• The Traitors: Deception and Trust in Multi-Agent Language Model Simulations
• You Can't Escape Your Own Activations : Evaluation Awareness and Multi-Agent Monitoring
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Algorithmic Collusion by Large Language Models
• Detecting Strategic Deception Using Linear Probes
• AI Control: Improving Safety Despite Intentional Subversion
• Large Language Model based Multi-Agents: A Survey of Progress and Challenges
• Multi-Agent Risks from Advanced AI
• SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems
• MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
• Time-uniform, nonparametric, nonasymptotic confidence sequences
• Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection
• Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks
• The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
• Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs
• The Llama 3 Herd of Models
• Secret Collusion among AI Agents: Multi-Agent Deception via Steganography

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems