Choosing LLMs for Strategic Agent Interactions
Game-theoretic benchmarks claim that large language model (LLM) strategic decision-making varies across game types, interaction structures, and capability dimensions. However, they only evaluate strategic performance across individual fixed models. In parallel, contemporary LLM routers pick models under quality-cost tr...
Arastun Mammadli, Herbert Woisetschläger, Jawad Fayaz et al.
· 0 citations