unsupervised-environment-design

该论文提出 TURTLE，一种无监督环境设计方法，通过 proposer、solver 和 feedback generator 自动演化出自我调优的长时程工具使用基准，可在 AppWorld、τ-Bench 等评测中提升任务难度、多样性并揭示更广的失败模式。

This paper introduces PATH, a framework for active curriculum refinement in reinforcement learning that leverages curriculum graph structure to improve robustness and generalization across diverse environments.