基础智能体的进展与挑战：从类脑智能到进化、协作与安全系统

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

March 31, 2025

作者: Bang Liu, Xinfeng Li, Jiayi Zhang, Jinlin Wang, Tanjin He, Sirui Hong, Hongzhang Liu, Shaokun Zhang, Kaitao Song, Kunlun Zhu, Yuheng Cheng, Suyuchen Wang, Xiaoqiang Wang, Yuyu Luo, Haibo Jin, Peiyan Zhang, Ollie Liu, Jiaqi Chen, Huan Zhang, Zhaoyang Yu, Haochen Shi, Boyan Li, Dekun Wu, Fengwei Teng, Xiaojun Jia, Jiawei Xu, Jinyu Xiang, Yizhang Lin, Tianming Liu, Tongliang Liu, Yu Su, Huan Sun, Glen Berseth, Jianyun Nie, Ian Foster, Logan Ward, Qingyun Wu, Yu Gu, Mingchen Zhuge, Xiangru Tang, Haohan Wang, Jiaxuan You, Chi Wang, Jian Pei, Qiang Yang, Xiaoliang Qi, Chenglin Wu

cs.AI

摘要

大型语言模型（LLMs）的出现催化了人工智能领域的变革性转变，为能够在多样化领域中实现复杂推理、强大感知和多功能行动的先进智能体铺平了道路。随着这些智能体日益推动AI研究和实际应用，其设计、评估与持续改进带来了错综复杂、多层面的挑战。本综述提供了一个全面的概览，将智能体置于一个模块化、受大脑启发的架构中，该架构整合了认知科学、神经科学和计算研究的原理。我们将探索分为四个相互关联的部分。首先，深入探讨智能体的模块化基础，系统性地将其认知、感知和操作模块映射到类似的人类大脑功能上，并阐明诸如记忆、世界建模、奖励处理及类情感系统等核心组件。其次，讨论自我增强与适应性进化机制，探索智能体如何自主优化其能力、适应动态环境，并通过包括新兴的AutoML和LLM驱动优化策略在内的自动化优化范式实现持续学习。第三，考察协作与进化的多智能体系统，研究智能体互动、合作及社会结构中涌现的集体智能，强调其与人类社会动态的相似之处。最后，探讨构建安全、可靠且有益的AI系统的关键必要性，着重于内在与外在的安全威胁、伦理对齐、鲁棒性以及实现可信赖实际部署所需的实用缓解策略。

English

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.