AINeutralarXiv – CS AI · 8h ago6/10
🧠
PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency
Researchers introduce PETS, a framework for optimizing how many reasoning trajectories to sample from AI models during inference to maintain accuracy while reducing computational costs. By modeling trajectory allocation as a crowdsourcing problem, the approach achieves up to 75% budget savings on benchmarks while maintaining perfect consistency, addressing a key efficiency challenge in test-time scaling.