# Agent-GSPO: Communication-Efficient Multi-Agent Systems via Group Sequence Policy Optimization

arXiv: https://arxiv.org/abs/2510.22477 · HTML: https://mlsanity.com/paper/2510.22477/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 25 references that are in the map.
- First posted on arXiv 26 Oct 2025.

## Builds on (most cited first, 24 of 24)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems](https://mlsanity.com/paper/1705.04146/) (2017)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Complexity-Based Prompting for Multi-Step Reasoning](https://mlsanity.com/paper/2210.00720/) (2022)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023)
- [Progressive-Hint Prompting Improves Reasoning in Large Language Models](https://mlsanity.com/paper/2304.09797/) (2023)
- [Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2410.02506/) (2024)
- [CF-VLM:CounterFactual Vision-Language Fine-tuning](https://mlsanity.com/paper/2506.17267/) (2025)
- [GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning](https://mlsanity.com/paper/2505.23399/) (2025)
- [MAT-Agent: Adaptive Multi-Agent Training Optimization](https://mlsanity.com/paper/2510.17845/) (2025)
- [Failure-Driven Workflow Refinement](https://mlsanity.com/paper/2510.10035/) (2025)
- [Learning Dynamics of VLM Finetuning](https://mlsanity.com/paper/2510.11978/) (2025)

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

- [Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classification](https://mlsanity.com/paper/2512.00812/) (2025)

## Abstract (arXiv)

To combat the prohibitive communication costs of ``free-for-all" multi-agent systems (MAS), we introduce 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.