Brain-inspired AI Agent: The Way Towards AGI

TL;DR

This work advocates a brain-inspired agent design that maps mesoscale cortical regions and their functional connectivity onto modular agent components to move toward AGI. It grounds the architecture in cortical parcellation frameworks (Brodmann Areas and HCP) and differentiates structural versus functional connectivity, emphasizing networks like the DMN and ECN. The proposed agent uses cortical-area-like modules across perception, planning, memory, and action within a perception-planning-action framework, contrasting with current LLM-centric agents and arguing for a general, brain-like cognitive architecture. The paper discusses limitations—such as incomplete brain understanding, the need for broader architectural definitions, high computational costs, and integration challenges—and outlines future directions for expanding mesoscale coverage and developing specialized, integrated frameworks to advance brain-inspired AGI.

Abstract

Artificial General Intelligence (AGI), widely regarded as the fundamental goal of artificial intelligence, represents the realization of cognitive capabilities that enable the handling of general tasks with human-like proficiency. Researchers in brain-inspired AI seek inspiration from the operational mechanisms of the human brain, aiming to replicate its functional rules in intelligent models. Moreover, with the rapid development of large-scale models in recent years, the concept of agents has garnered increasing attention, with researchers widely recognizing it as a necessary pathway toward achieving AGI. In this article, we propose the concept of a brain-inspired AI agent and analyze how to extract relatively feasible and agent-compatible cortical region functionalities and their associated functional connectivity networks from the complex mechanisms of the human brain. Implementing these structures within an agent enables it to achieve basic cognitive intelligence akin to human capabilities. Finally, we explore the limitations and challenges for realizing brain-inspired agents and discuss their future development.

Figures (1)

• Figure 1: Schematic Diagram of Brain Regions in a Brain-Inspired Agent.