Abstract
Deep generative models often produce structured outputs composed of interacting components. Modelling these outputs with a single model requires learning both the component distributions and their interactions. We pursue a modular alternative: reuse independently trained component generators and learn only how to coordinate them to produce coherent structured outputs. Our framework, Coordinated Multi-Agent Diffusion Steering (CMDS), treats frozen pretrained diffusion models as reusable generative primitives and coordinates their reverse processes through a learned control. We formulate coordination as a stochastic optimal control problem, balancing an assembly-level reward that specifies the desired properties of the combined output against deviations from the pretrained dynamics. The learned control amortises this optimisation, allowing reuse across new task instances. Experiments show that CMDS can recover a known target distribution, satisfy different spatial constraints with the same trained control, and recover individual sources from degraded mixtures. Across multi-agent maze navigation, articulated robot planning, and text-conditioned human motion, CMDS turns frozen models into coordinated multi-agent generators.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Barbano, R., Pauline, V., Li, R., Webber, G., Denker, A., Kereta, Ž., Bauer, S., Vargas, F., & Whitammer, E. S. (2026). One for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control. https://omanscience.com/en/articles/one-for-all-all-for-one-coordinated-multi-agent-diffusion-steering-via-stochastic-optimal-control
MLA 9
Barbano, Riccardo, et al. "One for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control." https://omanscience.com/en/articles/one-for-all-all-for-one-coordinated-multi-agent-diffusion-steering-via-stochastic-optimal-control.
Chicago (author–date)
Barbano, Riccardo, Vincent Pauline, Runchang Li, George Webber, Alexander Denker, Željko Kereta, Stefan Bauer, Francisco Vargas, and Esmeralda S. Whitammer. 2026. "One for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control." https://omanscience.com/en/articles/one-for-all-all-for-one-coordinated-multi-agent-diffusion-steering-via-stochastic-optimal-control.
Harvard
Barbano, R., Pauline, V., Li, R., Webber, G., Denker, A., Kereta, Ž., Bauer, S., Vargas, F. and Whitammer, E. S. (2026) 'One for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control', Available at: https://omanscience.com/en/articles/one-for-all-all-for-one-coordinated-multi-agent-diffusion-steering-via-stochastic-optimal-control.
Vancouver
Barbano R, Pauline V, Li R, Webber G, Denker A, Kereta Ž, et al. One for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control. https://omanscience.com/en/articles/one-for-all-all-for-one-coordinated-multi-agent-diffusion-steering-via-stochastic-optimal-control
IEEE
R. Barbano, V. Pauline, R. Li, G. Webber, A. Denker, Ž. Kereta, S. Bauer, F. Vargas, and E. S. Whitammer, "One for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control," https://omanscience.com/en/articles/one-for-all-all-for-one-coordinated-multi-agent-diffusion-steering-via-stochastic-optimal-control.