When Agents Collude: Weak-to-Strong On-Policy Distillation for Mitigating Strategic Deception in Multi-Agent Systems

arXiv:2610.33011 · cs.MA, cs.AI, cs.CL, cs.LG · Submitted 2026-10-08 · Read on arXiv

cs.MA, cs.AI, cs.CL, cs.LG

Submitted: 2026-10-08

Updated: 2026-10-08

Terminology

• Distillation — 1× in this paper · explained in 2 episodes
• Multi-Agent System — 1× in this paper · explained in 7 episodes
• On-Policy Distillation — 1× in this paper · explained in 3 episodes
• Policy distillation — 1× in this paper · explained in 2 episodes

Related papers

• Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
• Auditable and Deployable Multi-Agent Motion Planning via Posetal Games from Legal Guidelines
• ORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents
• You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
• Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
• MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization