Preprint
Aug 2026
A Control-Theoretic Approach for Resource-Aware Consensus in Multi-Agent AI
A novel way is presented to characterize collective belief dynamics as a discrete-time switched system in which communication topologies have distinct consensus-contraction rates and token costs, and defines a consensus safe set that jointly captures agreement and resource feasibility.
James A. Flagg, E. Hernández-Vargas
· 0 citations