快讯
Meta Superintelligence Labs训练9B用户模拟器MIMESIS
Meta Superintelligence Labs相关论文介绍MIMESIS：这是一个9B用户模拟器，基于真实对话和13种真实用户行为模式训练。文中称其行为保真度比Claude Opus 5高13.4分，且针对它训练的Agent在九个未见过的用户模拟器上优于用GPT-5.5训练的Agent。
事件来源
查看原文
Banger paper from Meta Superintelligence Labs on user simulators for agent training. Agent RL setups usually let an assistant LLM play the user, so the simulated user is too cooperative and too explicit. A fixed GPT-5.5 agent finds tau-bench tasks easier with these users than with real people. This work trains MIMESIS, a 9B user simulator, on human conversations and 13 behavior patterns observed in real users. It beats Claude Opus 5 on behavioral fidelity by 13.4 points. Agents trained against it outperform agents trained against GPT-5.5 under all nine user simulators they never saw. They find that adding a coaching step that turns the simulator's private reasoning into feedback adds further gains. Paper: https://academy.dair.ai/papers/mimesis-learning-user-simulators-as-training-environments-for-interactive-agents-2610.09484