Microsoft 论文提出 ActiveSaddler：自适应场景优化智能体 harness
微软这篇论文把训练场景也动态调整了，GAIA2 上直接提 4.4 分，做智能体优化的人值得看。
Microsoft 等机构发布论文 ActiveSaddler，针对当前 harness 优化器只更新 harness、训练场景固定的问题，把场景也纳入自适应调整。方法上将反复出现的失败归纳为失败模式，把每个模式当作非平稳多臂老虎机的一个臂，追踪各模式还能带来多少学习信号并在已知弱点和探索新模式间分配预算。使用相同优化器的情况下，测试 Pass@1 在 GAIA2 上提升 4.4 分，在 Terminal-Bench 2.0 上提升 7.5 分。
Great paper from Microsoft and colleagues on optimizing agent harnesses.
Current harness optimizers change how the harness is updated but keep the training scenarios fixed, so feedback keeps coming from tasks that stop being informative as the harness improves.
This work adapts the scenarios as well.
ActiveSaddler groups recurring failures into failure patterns and treats each pattern as an arm in a non-stationary bandit.
It tracks how much the harness is still learning from each pattern and splits the budget between revisiting known weaknesses and finding new ones.
With the same optimizer, test Pass@1 improves by 4.4 points on GAIA2 and 7.5 points on Terminal-Bench 2.0 compared with a fixed scenario order.
Paper: https://t.co/7HgcTkAReK
