Saved in:
Bibliographic Details
Main Authors: Hao, Guangfu, Dai, Yuming, Qin, Xianzhe, Yu, Shan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.15371
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915867187478528
author Hao, Guangfu
Dai, Yuming
Qin, Xianzhe
Yu, Shan
author_facet Hao, Guangfu
Dai, Yuming
Qin, Xianzhe
Yu, Shan
contents Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of language tasks, yet complex multi-step reasoning remains a fundamental challenge. While Large Reasoning Models (LRMs) equipped with extended chain-of-thought mechanisms demonstrate improved performance over standard LLMs, both model types still suffer from accuracy collapse on sufficiently complex tasks, suggesting that scaling model-level reasoning alone is insufficient. Inspired by the global workspace theory of human cognition, we propose Brain-Inspired Graph Multi-Agent Systems (BIGMAS), in which specialized LLM agents are organized as nodes in a dynamically constructed directed graph and coordinate exclusively through a centralized shared workspace. A problem-adaptive GraphDesigner constructs task-specific agent topologies, while a global Orchestrator leverages the complete shared state for routing decisions, overcoming the local-view bottleneck of reactive approaches. Experiments on Game24, Six Fives, and Tower of London across six frontier LLMs demonstrate that BIGMAS consistently improves reasoning performance for both standard LLMs and LRMs, outperforming existing multi-agent baselines including ReAct and Tree of Thoughts, showing that multi-agent architectural design provides complementary gains orthogonal to model-level reasoning enhancements.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15371
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Brain-Inspired Graph Multi-Agent Systems for LLM Reasoning
Hao, Guangfu
Dai, Yuming
Qin, Xianzhe
Yu, Shan
Artificial Intelligence
Networking and Internet Architecture
Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of language tasks, yet complex multi-step reasoning remains a fundamental challenge. While Large Reasoning Models (LRMs) equipped with extended chain-of-thought mechanisms demonstrate improved performance over standard LLMs, both model types still suffer from accuracy collapse on sufficiently complex tasks, suggesting that scaling model-level reasoning alone is insufficient. Inspired by the global workspace theory of human cognition, we propose Brain-Inspired Graph Multi-Agent Systems (BIGMAS), in which specialized LLM agents are organized as nodes in a dynamically constructed directed graph and coordinate exclusively through a centralized shared workspace. A problem-adaptive GraphDesigner constructs task-specific agent topologies, while a global Orchestrator leverages the complete shared state for routing decisions, overcoming the local-view bottleneck of reactive approaches. Experiments on Game24, Six Fives, and Tower of London across six frontier LLMs demonstrate that BIGMAS consistently improves reasoning performance for both standard LLMs and LRMs, outperforming existing multi-agent baselines including ReAct and Tree of Thoughts, showing that multi-agent architectural design provides complementary gains orthogonal to model-level reasoning enhancements.
title Brain-Inspired Graph Multi-Agent Systems for LLM Reasoning
topic Artificial Intelligence
Networking and Internet Architecture
url https://arxiv.org/abs/2603.15371