NeuroMAS：将多智能体系统视为神经网络并进行联合强化学习训练
NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning
AI 导读
NeuroMAS 提出把多智能体语言系统当作可训练、可扩展的神经网络式架构，LLM 智能体作为节点、中间文本信号作为边，节点无固定角色但具备结构感知，由强化学习决定通信、专业化与协调方式。实验显示该方法显著优于推理时和训练型多智能体基线；组织化扩展具有路径依赖性，从较小已训练系统渐进生长比从头训练更可行。
正文 · 原文
Abstract:Multi-agent language systems are often built as hand-designed workflows, where agents are assigned semantic roles and communication protocols are specified in advance. We propose NeuroMAS, a method that first treats a multi-agent language system as a trainable and scalable neural-network-like architecture with LLM agents as nodes and intermediate textual signals as edges. In NeuroMAS, agent nodes are role-free but structure-aware: the topology only determines how information can flow in general, while reinforcement learning training determines how nodes communicate, specialize, and coordinate. This formulation shifts multi-agent design from workflow engineering toward architecture design, where depth, width, connectivity, and growth protocol become scalable sources of capability. Further, we provide a theoretical perspective showing why such modular textual computation is more parameter-efficient when tasks admit hierarchical decompositions. Experiments show that NeuroMAS improves significantly over both inference-time and trained multi-agent baselines. We further find that organizational scaling is path-dependent: larger systems can be challenging to train from scratch, but become feasible when grown progressively from smaller trained systems. These results suggest that learned neural multi-agent systems are a promising scaling axis for LLMs.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Methodology (stat.ME); Machine Learning (stat.ML) |
| Cite as: | arXiv:2605.16757 [cs.AI] |
| (or arXiv:2605.16757v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.16757 arXiv-issued DOI via DataCite |
|
| Journal reference: | The First Conference on Statistics and Trustworthy AI for Cross (X)-Domain Acceleration (2026) |
Submission history
From: Haoran Lu [view email]
[v1]
Sat, 16 May 2026 02:11:34 UTC (752 KB)
[v2]
Fri, 23 Oct 2026 01:38:57 UTC (761 KB)
来源：arXiv cs.AI · arxiv.org