MIMESIS：学习用户模拟器作为交互智能体的训练环境

arXiv 2610.09484 · 20 人推荐 · 附代码 VietHoang1512/mimesis（5 stars）。Training and evaluating interactive language agents typically requires rich user interactions, yet collecting human feedback is expensive and difficult to scale. Simulated users offer a scalable alternative, but they must both resemble real user behavior and provide useful learning experiences for agents. In contrast, most agent-training frameworks rely on off-the-shelf assistant LLMs, whose helpfulness can make them overly cooperative, explicit, and behaviorally homogeneous compared with real u