Xuhui Zhou

Social Gym and SPaRTan: Benchmarking and Improving LLM Social Reasoning via Multi-Agent Game Tournaments

Social Gym is introduced, an environment of 21 multi-agent social games whose rule-decided outcomes make agent performance verifiable and objective, and SPaRTan (Self-Play and Reflect-Transfer), a training-free self-improvement loop that offers a reproducible, verifiable foundation for measuring and improving LLM socia...