Tag
该论文提出MASP（心智化对抗自博弈）框架，将主动对话建模为系统与理性抗拒用户之间的部分可观测博弈，通过BDI潜在状态表示用户心智并交替自博弈更新，在多个主动对话基准上显著提升成功率并更好地对抗强硬用户。
The article introduces adversarial self-play as a technique to eliminate low-quality outputs ('slop') from coding agents, improving their reliability and performance.