Zishuo Xun

Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute

This paper presents a simple, effective, and cost-efficient strategy, named ModelSwitch, to improve LLM performance by scaling test-time compute. ModelSwitch builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple models, even weaker ones, to leverage the