Story
arxiv_agent_systems_research · Nov 12, 2026 · paper
Source brief
Shared Item-Level Error Limits the Aggregation of Small Language Models in Fermi Estimation
arxiv.orgNov 12, 2026
original source linked
In brief
Multi-agent systems of language models are often motivated by an averaging argument: if the agents' errors are unbiased and independent, the error of an aggregate of N answers falls as 1/sqrt(N). Fermi estimation, whose continuous answers are aggregated on the logarithmic scale,