English

MaRCA: Multi-Agent Reinforcement Learning for Dynamic Computation Allocation in Large-Scale Recommender Systems

Information Retrieval 2026-01-01 v1 Machine Learning Multiagent Systems

Abstract

Modern recommender systems face significant computational challenges due to growing model complexity and traffic scale, making efficient computation allocation critical for maximizing business revenue. Existing approaches typically simplify multi-stage computation resource allocation, neglecting inter-stage dependencies, thus limiting global optimality. In this paper, we propose MaRCA, a multi-agent reinforcement learning framework for end-to-end computation resource allocation in large-scale recommender systems. MaRCA models the stages of a recommender system as cooperative agents, using Centralized Training with Decentralized Execution (CTDE) to optimize revenue under computation resource constraints. We introduce an AutoBucket TestBench for accurate computation cost estimation, and a Model Predictive Control (MPC)-based Revenue-Cost Balancer to proactively forecast traffic loads and adjust the revenue-cost trade-off accordingly. Since its end-to-end deployment in the advertising pipeline of a leading global e-commerce platform in November 2024, MaRCA has consistently handled hundreds of billions of ad requests per day and has delivered a 16.67% revenue uplift using existing computation resources.

Keywords

Cite

@article{arxiv.2512.24325,
  title  = {MaRCA: Multi-Agent Reinforcement Learning for Dynamic Computation Allocation in Large-Scale Recommender Systems},
  author = {Wan Jiang and Xinyi Zang and Yudong Zhao and Yusi Zou and Yunfei Lu and Junbo Tong and Yang Liu and Ming Li and Jiani Shi and Xin Yang},
  journal= {arXiv preprint arXiv:2512.24325},
  year   = {2026}
}

Comments

12 pages, 5 figures

R2 v1 2026-07-01T08:45:56.321Z