SuanNi
Apr 26, 2026 · Artificial Intelligence
Why Overly Detailed AI Skills Hurt Performance: The Golden Rule for Large Model Experience Reuse
A Tsinghua and EvoMap study of 4,590 controlled experiments across 45 scientific tasks shows that feeding large language models with a 2,500‑token detailed Skill degrades pass rates, while a compact 230‑token strategy gene boosts performance by up to 3 percentage points.
AI evaluationEvoMapLarge Language Models
0 likes · 10 min read