Paper: Agents struggle to evolve via explicit skill libraries

rohanpaul_ai · x · 2026-08-24

The ContinualSkillBench paper suggests agents don't get proportionally better by accumulating hundreds of skills. The 16.9% relative gain from sequential execution stems largely from carrying forward context and feedback, not from reliable skill abstraction. In some tests, pure in-context learning outperformed explicit skill maintenance.

Original post →

More from Research

Research channel →