Adaptive Intelligence: leveraging insights from adaptive behavior in animals to build flexible AI systems

Abstract

Biological intelligence is inherently adaptive -- animals continually adjust their actions based on environmental feedback. However, creating adaptive artificial intelligence (AI) remains a major challenge. The next frontier is to go beyond traditional AI to develop "adaptive intelligence," defined here as harnessing insights from biological intelligence to build agents that can learn online, generalize, and rapidly adapt to changes in their environment. Recent advances in neuroscience offer inspiration through studies that increasingly focus on how animals naturally learn and adapt their world models. In this Perspective, I will review the behavioral and neural foundations of adaptive biological intelligence, the parallel progress in AI, and explore brain-inspired approaches for building more adaptive algorithms.

10 pages, 4 figures

References in corpus (23)

• Overcoming catastrophic forgetting in neural networks
• Knowledge Distillation: A Survey
• On the Opportunities and Risks of Foundation Models
• Gemini: A Family of Highly Capable Multimodal Models
• Deep learning tools for the measurement of animal behavior in neuroscience
• Learnable latent embeddings for joint behavioral and neural analysis
• Large-scale neural recordings call for new insights to link brain and behavior
• DeepSeek-V3 Technical Report
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• Event-Based Backpropagation can compute Exact Gradients for Spiking Neural Networks
• SuperAnimal pretrained pose estimation models for behavioral analysis
• Measuring and modeling the motor system with machine learning
• MemGPT: Towards LLMs as Operating Systems
• Memory Replay with Data Compression for Continual Learning
• Learning offline: memory replay in biological and artificial reinforcement learning
• An Introduction to Vision-Language Modeling
• Building population models for large-scale neural recordings: opportunities and pitfalls
• LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
• Brain decoding: toward real-time reconstruction of visual perception
• Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers
• Elastic Weight Consolidation Improves the Robustness of Self-Supervised Learning Methods under Transfer
• Towards a "universal translator" for neural dynamics at single-cell, single-spike resolution
• A Metacognitive Approach to Out-of-Distribution Detection for Segmentation