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. Third, we examine collaborative and evolutionary multi-agent systems, investigating the collective intelligence emerging from agent interactions, cooperation, and societal structures, highlighting parallels to human social dynamics. Finally, we address the critical imperative of building safe, secure, and beneficial AI systems, emphasizing intrinsic and extrinsic security threats, ethical alignment, robustness, and practical mitigation strategies necessary for trustworthy real-world deployment.

@article{liu2025_2504.01990,
  title={ Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems },
  author={ Bang Liu and Xinfeng Li and Jiayi Zhang and Jinlin Wang and Tanjin He and Sirui Hong and Hongzhang Liu and Shaokun Zhang and Kaitao Song and Kunlun Zhu and Yuheng Cheng and Suyuchen Wang and Xiaoqiang Wang and Yuyu Luo and Haibo Jin and Peiyan Zhang and Ollie Liu and Jiaqi Chen and Huan Zhang and Zhaoyang Yu and Haochen Shi and Boyan Li and Dekun Wu and Fengwei Teng and Xiaojun Jia and Jiawei Xu and Jinyu Xiang and Yizhang Lin and Tianming Liu and Tongliang Liu and Yu Su and Huan Sun and Glen Berseth and Jianyun Nie and Ian Foster and Logan Ward and Qingyun Wu and Yu Gu and Mingchen Zhuge and Xiangru Tang and Haohan Wang and Jiaxuan You and Chi Wang and Jian Pei and Qiang Yang and Xiaoliang Qi and Chenglin Wu },
  journal={arXiv preprint arXiv:2504.01990},
  year={ 2025 }
}