Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

The advent of large language models (LLMs) has catalyzed a transformative shift in artificial intelligence, paving the way for advanced intelligent agents capable of sophisticated reasoning, robust perception, and versatile action across diverse domains. As these agents increasingly drive AI research and practical applications, their design, evaluation, and continuous improvement present intricate, multifaceted challenges. This survey provides a comprehensive overview, framing intelligent agents within a modular, brain-inspired architecture that integrates principles from cognitive science, neuroscience, and computational research. We structure our exploration into four interconnected parts. First, we delve into the modular foundation of intelligent agents, systematically mapping their cognitive, perceptual, and operational modules onto analogous human brain functionalities, and elucidating core components such as memory, world modeling, reward processing, and emotion-like systems. Second, we discuss self-enhancement and adaptive evolution mechanisms, exploring how agents autonomously refine their capabilities, adapt to dynamic environments, and achieve continual learning through automated optimization paradigms, including emerging AutoML and LLM-driven optimization strategies.

Introduction. Artificial Intelligence (AI) has long been driven by humanity’s ambition to create entities that mirror human intelligence, adaptability, and purpose-driven behavior. The roots of this fascination trace back to ancient myths and early engineering marvels, which illustrate humanity’s enduring dream of creating intelligent, autonomous beings. Stories like that of Talos, the bronze automaton of Crete, described a giant constructed by the gods to guard the island, capable of patrolling its shores and fending off intruders. Such myths symbolize the desire to imbue artificial creations with human-like agency and purpose. Similarly, the mechanical inventions of the Renaissance, including Leonardo da Vinci’s humanoid robot—designed to mimic human motion and anatomy—represent the first attempts to translate these myths into tangible, functional artifacts.

Discussion / Conclusion. We have explored in this survey the evolving landscape of foundation agents by drawing parallels between human cognitive processes and artificial intelligence. We began by outlining the core components of intelligent agents—detailing how modules such as memory, perception, emotion, reasoning, and action can be modeled in a framework inspired by the comparison with human brain. Our discussion highlighted how these agents can be structured in a modular fashion, enabling them to emulate human-like processing through specialized yet interconnected subsystems. We then delved into the dynamic aspects of agent evolution, examining self-improvement mechanisms that leverage optimization techniques, including both online and offline strategies. By investigating how large language models can act as both reasoning entities and autonomous optimizers, we illustrated the transformative potential of agents that continuously adapt to changing environments.