NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning

• URL: http://arxiv.org/abs/2605.16757v1
• Date: Sat, 16 May 2026 02:11:34 GMT
• Title: NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning
• Abstract summary: We propose NeuroMAS as a trainable and scalable neural-network-like architecture for multi-agent language systems.<n>We show that NeuroMAS improves significantly over both inference-time and trained multi-agent baselines.<n>Larger systems can be challenging to train from scratch, but become feasible when grown progressively from smaller trained systems.
• Score: 7.167256048138654
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• NeuroClaw Technical Report [54.14941057366186]
  NeuroClaw is a domain-specialized multi-agent research assistant for neuroimaging research.<n>NeuroClaw operates directly on raw neuroimaging data across formats and modalities.<n>A three-tier skill/agent hierarchy separates user-facing interaction, high-level orchestration, and low-level tool skills.
  arXiv  Detail & Related papers  (2026-04-27T16:57:14Z)
• Rethinking Multi-Agent Intelligence Through the Lens of Small-World Networks [14.233668486426795]
  Large language models (LLMs) have enabled multi-agent systems (MAS) in which multiple agents argue, critique, and coordinate to solve complex tasks.<n>Most existing LLM-based MAS either adopt fully connected graphs, simple sparse rings, or ad-hoc dynamic selection, with little structural guidance.<n>We first bridge insights from neuroscience and complex networks to MAS, highlighting how SW structures balance local clustering and long-range integration.<n>Experiment results show that SW connectivity yields nearly the same accuracy and token cost, while substantially stabilizing consensus trajectories.
  arXiv  Detail & Related papers  (2025-12-19T22:05:43Z)
• AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs [8.912989700822127]
  We propose AgentsNet, a new benchmark for multi-agent reasoning.<n>We evaluate a variety of baseline methods on AgentsNet including homogeneous networks of agents.<n>We find that some frontier LLMs are already demonstrating strong performance for small networks but begin to fall off once the size of the network scales.
  arXiv  Detail & Related papers  (2025-07-11T14:13:22Z)
• Agentic Neural Networks: Self-Evolving Multi-Agent Systems via Textual Backpropagation [29.45297422127962]
  We present a framework that conceptualizes multi-agent collaboration as a layered neural network architecture.<n>In this design, each agent operates as a node, and each layer forms a cooperative "team" focused on a specific subtask.<n>Our findings indicate that ANN provides a scalable, data-driven framework for multi-agent systems.
  arXiv  Detail & Related papers  (2025-06-10T17:59:21Z)
• The Spike Gating Flow: A Hierarchical Structure Based Spiking Neural Network for Online Gesture Recognition [12.866549161582412]
  We develop a novel brain-inspired Spiking Neural Network (SNN) based system titled Spiking Gating Flow (SGF) for online action learning. To the best of our knowledge, this is the highest accuracy among the non-backpropagation algorithm based SNNs.
  arXiv  Detail & Related papers  (2022-06-04T04:37:56Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
  We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
  arXiv  Detail & Related papers  (2021-07-08T18:01:02Z)
• A multi-agent model for growing spiking neural networks [0.0]
  This project has explored rules for growing the connections between the neurons in Spiking Neural Networks as a learning mechanism. Results in a simulation environment showed that for a given set of parameters it is possible to reach topologies that reproduce the tested functions. This project also opens the door to the usage of techniques like genetic algorithms for obtaining the best suited values for the model parameters.
  arXiv  Detail & Related papers  (2020-09-21T15:11:29Z)
• Automated Search for Resource-Efficient Branched Multi-Task Networks [81.48051635183916]
  We propose a principled approach, rooted in differentiable neural architecture search, to automatically define branching structures in a multi-task neural network. We show that our approach consistently finds high-performing branching structures within limited resource budgets.
  arXiv  Detail & Related papers  (2020-08-24T09:49:19Z)
• Deep Multi-Task Learning for Cooperative NOMA: System Design and Principles [52.79089414630366]
  We develop a novel deep cooperative NOMA scheme, drawing upon the recent advances in deep learning (DL) We develop a novel hybrid-cascaded deep neural network (DNN) architecture such that the entire system can be optimized in a holistic manner.
  arXiv  Detail & Related papers  (2020-07-27T12:38:37Z)
• Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment [84.57874289554839]
  Training deep neural networks on large-scale datasets requires significant hardware resources. Backpropagation, the workhorse for training these networks, is an inherently sequential process that is difficult to parallelize. We propose a neuro-biologically-plausible alternative to backprop that can be used to train deep networks.
  arXiv  Detail & Related papers  (2020-02-10T16:20:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.