#machine learning
May 2026
PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
PACEvolve++ is introduced, an advisor-model reinforcement learning framework for test-time policy adaptation in evolutionary search agents, which outperforms the state-of-the-art evolutionary search framework with frontier models, achieving faster convergence and stabilizing test-time training during evolutionary searc...
Minghao Yan, Bo Peng, Benjamin Coleman et al.
· arXiv.org · 4 citations