Preprint
Aug 2026
MARA: Flow-Matching-Guided Multi-Agent Resource Allocation for Computational Resource Efficient Learning
This work proposes MARA, which predicts future loss trajectories with conditional flow matching and coordinates compute nodes through a cooperative multi-agent autoregressive policy and reduces remaining-resource prediction error relative to weighted least squares.
Hanye Zhao, Muning Wen, Yong Yu et al.
· 0 citations