On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification
A comprehensive re-evaluation of two memory-based methods for self-improving agents is conducted, broadening the scope of evaluation along two axes and hypothesizing that task and environment underspecification contribute to this fragility.
Qinyuan Ye, Yu Li, Yada Pruksachatkun et al.
· 0 citations