To combat the prohibitive communication costs of ``free-for-all" multi-agent systems (MAS), we introduce \textbf{Agent-GSPO}, a framework that directly optimizes for token economy using sequence-level reinforcement learning. Agent-GSPO leverages the stable and memory-efficient Group Sequence Policy Optimization (GSPO) algorithm to train agents on a communication-aware reward that explicitly penalizes verbosity. Across seven reasoning benchmarks, Agent-GSPO not only achieves new state-of-the-art performance but does so with a fraction of the token consumption of existing methods. By fostering emergent strategies like ``strategic silence," our approach provides a practical blueprint for developing scalable and economically viable multi-agent systems.
@article{arxiv.2510.22477,
title = {Agent-GSPO: Communication-Efficient Multi-Agent Systems via Group Sequence Policy Optimization},
author = {Yijia Fan and Jusheng Zhang and Jing Yang and Keze Wang},
journal= {arXiv preprint arXiv:2510.22477},
year = {2025}
}