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

arXiv: https://arxiv.org/abs/2605.13900 · HTML: https://mlsanity.com/paper/2605.13900/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 41 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [OptNet: Differentiable Optimization as a Layer in Neural Networks](https://mlsanity.com/paper/1703.00443/) (2017)
- [Differentiable Convex Optimization Layers](https://mlsanity.com/paper/1910.12430/) (2019)
- [Sim-to-Real: Learning Agile Locomotion For Quadruped Robots](https://mlsanity.com/paper/1804.10332/) (2018)
- [Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning](https://mlsanity.com/paper/1708.02596/) (2017)
- [Mean Field Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1802.05438/) (2018)
- [Do Differentiable Simulators Give Better Policy Gradients?](https://mlsanity.com/paper/2202.00817/) (2022)
- [Hindsight Learning for MDPs with Exogenous Inputs](https://mlsanity.com/paper/2207.06272/) (2022)
- [An Analysis of Multi-Agent Reinforcement Learning for Decentralized Inventory Control Systems](https://mlsanity.com/paper/2307.11432/) (2023)
- [Neural Coordination and Capacity Control for Inventory Management](https://mlsanity.com/paper/2410.02817/) (2024)
- [Learning an Inventory Control Policy with General Inventory Arrival Dynamics](https://mlsanity.com/paper/2310.17168/) (2023)
- [Consensus Planning with Primal, Dual, and Proximal Agents](https://mlsanity.com/paper/2408.16462/) (2024)

## Built on by (most cited first, 1 of 1)

- [Forecasting from Counterfactual Simulator Rollouts: A Sim2Real Evaluation](https://mlsanity.com/paper/2610.03662/) (2026)

## Abstract (arXiv)

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 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.