Safe Equilibrium Policy Optimization for Strategic Agent Policies 事件

Safe Equilibrium Policy Optimization for Strategic Agent Policies arXiv:2605.30854v1 Announce Type: cross Abstract: Language models fine-tuned with reinforcement learning typically optimize for task reward, ignoring multi-agent strategic structure. Because these agents condition on natural language game-state descriptions and emit actions through free-form generation, strategic failure modes -- exploiting weaker opponents, coordinating on harmful equilibria, and externalizing costs are insepara