AI RESEARCH
From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution
arXiv CS.CL
•
ArXi:2604.15097v1 Announce Type: cross This beta technical report asks how reusable experience should be represented so that it can function as effective test-time control and as a substrate for iterative evolution. We study this question in 4.590 controlled trials across 45 scientific code-solving scenarios. We find that documentation-oriented Skill packages provide unstable control: their useful signal is sparse, and expanding a compact experience object into a fuller documentation package often fails to help and can degrade the overall average.