SkillEvo: Self-renewing evolution gradients for sustained agent skill improvement

zju · hf · 2026-08-21

SkillEvo introduces a method for self-renewing evolution gradients derived from multi-turn interaction feedback. It employs active governance to sustain evolutionary gradients, thereby improving agent skills over time and addressing the issue of capability stagnation in long-term interactions.

Original post →

More from Research

Research channel →