AI RESEARCH
Model Capability Dominates: Inference-Time Optimization Lessons from AIMO 3
arXiv CS.CL
•
ArXi:2603.27844v1 Announce Type: new Majority voting over multiple LLM attempts improves mathematical reasoning, but correlated errors limit the effective sample size. A natural fix: assign structurally different reasoning strategies to different voters to decorrelate errors. We test this Diverse Prompt Mixer in the AIMO~3 competition: 3 models, 23+ experiments, and 50 IMO-level problems on a single H100 80 GB with a 5-hour limit. Every intervention fails.