AI RESEARCH
Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information
arXiv CS.AI
•
ArXi:2510.01499v2 Announce Type: replace-cross With the rapid progress of multi-agent large language model (LLM) reasoning, how to effectively aggregate answers from multiple LLMs has emerged as a fundamental challenge. Standard majority voting treats all answers equally, failing to consider latent heterogeneity and correlation across models. In this work, we design two new aggregation algorithms called Optimal Weight (OW) and Inverse Surprising Popularity (ISP), leveraging both first-order and second-order information.