NeuroAI and Beyond: Bridging Between Advances in Neuroscience and ArtificialIntelligence

TL;DR

This paper discusses how integrating neuroscience principles into AI can address current limitations in physical interaction, learning robustness, and efficiency, proposing a research roadmap and institutional changes.

Contribution

It identifies key neuroscience-inspired principles to enhance AI capabilities and outlines a comprehensive research roadmap for NeuroAI development across different time horizons.

Findings

Neuroscience principles can improve AI interaction with the physical world.

Hierarchical and sparse computation models can enhance AI efficiency.

A multidisciplinary approach is essential for advancing NeuroAI.

Abstract

Neuroscience and Artificial Intelligence (AI) have made impressive progress in recent years but remain only loosely interconnected. Based on a workshop convened by the National Science Foundation in August 2025, we identify three fundamental capability gaps in current AI: the inability to interact with the physical world, inadequate learning that produces brittle systems, and unsustainable energy and data inefficiency. We describe the neuroscience principles that address each: co-design of body and controller, prediction through interaction, multi-scale learning with neuromodulatory control, hierarchical distributed architectures, and sparse event-driven computation. We present a research roadmap organized around these principles at near, mid, and long-term horizons. We argue that realizing this program requires a new generation of researchers trained across the boundary between neuroscience and engineering, and describe the institutional conditions: interdisciplinary training, hardware access, community standards, and ethics, needed to support them. We conclude that NeuroAI, neuroscience-informed artificial intelligence, has the potential to overcome limitations of current AI while deepening our understanding of biological neural computation.