Ready from Day 1: Population-Aware Coordination for Large-Scale Constrained Multi-Agent Systems

TL;DR

This paper introduces population-aware coordination interfaces for large-scale multi-agent systems, enabling efficient resource planning and transferability across populations with improved accuracy and reduced violations.

Contribution

It proposes learned primal and dual maps conditioned on population summaries that remain reliable across evolving populations without retraining, enhancing large-scale multi-agent coordination.

Findings

Reduced forecast error by 16-19% compared to baselines.

Achieved 20-51% reduction in capacity violations.

Supported accurate coordination of 500K-agent populations with 20K-agent trained maps.

Abstract

In large-scale multi-agent systems with shared resource constraints, an upstream planner must iteratively evaluate candidate resource plans -- assessing feasibility, aggregate response, and marginal cost -- before committing to one. Lagrangian relaxation separates local decisions through a broadcast cost signal, but the planner still needs the cost-to-utilization response map to explore plan space, and this map depends on population composition that changes across planning cycles. We propose \emph{population-aware coordination interfaces}: learned primal and dual maps, conditioned on compact population summaries, that the planner queries inside its iterative loop. The primal map predicts aggregate utilization under a proposed cost trajectory; the dual map predicts the cost trajectory for a target plan. By encoding response-relevant population structure, these maps remain reliable across evolving populations without per-cycle retraining, and support coordination of large populations from compact subsamples. We additionally cast Sim2Real transfer as a backtestable procedure, enabling evaluation before deployment. In a supply-chain capacity-control case study, population-aware interfaces reduce forecast error by 16--19\% and capacity violations by 20--51\% relative to population-unaware baselines under composition shift; 20K-agent cohorts support accurate coordination of 500K-agent populations; and simulator-trained primal maps achieve 11.1\% MAPE on real observations versus 13--24\% for baselines.