How does Adversarial Influence Scale in Multi-Agent Systems?

arXiv:2609.30028 · cs.AI, cs.CY · Submitted 2026-09-24 · Read on arXiv

cs.AI, cs.CY

Submitted: 2026-09-24

Updated: 2026-09-24

Terminology

• Multi-Agent System — 7× in this paper · explained in 6 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Sycophancy — 5× in this paper · explained in 4 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Robustness — 3× in this paper · explained in 5 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Commentary — 1× in this paper · explained in 2 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Multi-agent Collaborative Framework — 1× in this paper · explained in 2 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size
• Multi-Agent Risks from Advanced AI
• Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate
• AI safety via debate
• Towards a Science of Scaling Agent Systems
• Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows
• The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems
• Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
• Simple synthetic data reduces sycophancy in large language models
• Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness
• Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate
• Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection