arXiv cs.AI
On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification
자기 개선 에이전트의 취약성에 관하여: 분산, 작업 순서, 그리고 언더스페시피케이션
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.