基于大语言模型代理的终身学习：路线图
Lifelong Learning of Large Language Model based Agents: A Roadmap
AI总结：
本文提出了一种基于大语言模型代理的终身学习框架，通过三个模块整合多模态输入、知识存储与动态环境交互，以实现持续适应和长期性能提升。
摘要：
终身学习，也称为持续或增量学习，是通过使系统能够在动态环境中持续适应，从而推动人工通用智能（AGI）发展的重要组成部分。尽管大语言模型（LLMs）在自然语言处理方面展示了出色的性能，但现有的LLM代理通常针对静态系统设计，缺乏在面对新挑战时随时间推移进行适应的能力。本文是首次系统总结将终身学习整合到LLM代理中的潜在技术。我们将这些代理的核心组件分为三个模块：感知模块用于多模态输入整合，记忆模块用于存储和检索不断演变的知识，以及行动模块用于与动态环境进行基础交互。我们强调这些支柱如何共同实现持续适应，缓解灾难性遗忘，并提高长期性能。本文为致力于开发LLM代理终身学习能力的研究人员和实践者提供了路线图，提供了关于新兴趋势、评估指标和应用场景的见解。相关文献和资源可在https://github.com/qianlima-lab/awesome-lifelong-llm-agent获取。
英文摘要：
Lifelong learning, also known as continual or incremental learning, is a crucial component for advancing Artificial General Intelligence (AGI) by enabling systems to continuously adapt in dynamic environments. While large language models (LLMs) have demonstrated impressive capabilities in natural language processing, existing LLM agents are typically designed for static systems and lack the ability to adapt over time in response to new challenges. This survey is the first to systematically summarize the potential techniques for incorporating lifelong learning into LLM-based agents. We categorize the core components of these agents into three modules: the perception module for multimodal input integration, the memory module for storing and retrieving evolving knowledge, and the action module for grounded interactions with the dynamic environment. We highlight how these pillars collectively enable continuous adaptation, mitigate catastrophic forgetting, and improve long-term performance. This survey provides a roadmap for researchers and practitioners working to develop lifelong learning capabilities in LLM agents, offering insights into emerging trends, evaluation metrics, and application scenarios. Relevant literature and resources are available at \href{this url}{https://github.com/qianlima-lab/awesome-lifelong-llm-agent}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
