As the strength of Large Language Models (LLMs) has grown over recent years, so too has interest in their use as the underlying models for autonomous agents. Although LLMs demonstrate emergent abilities and broad expertise across natural language domains, their inherent unpredictability makes the implementation of LLM agents challenging, resulting in a gap between related research and the real-world implementation of such systems. To bridge this gap, this paper frames actionable insights and considerations from the research community in the context of established application paradigms to enable the construction and facilitate the informed deployment of robust LLM agents. Namely, we position relevant research findings into four broad categories--Planning, Memory, Tools, and Control Flow--based on common practices in application-focused literature and highlight practical considerations to make when designing agentic LLMs for real-world applications, such as handling stochasticity and managing resources efficiently. While we do not conduct empirical evaluations, we do provide the necessary background for discussing critical aspects of agentic LLM designs, both in academia and industry.

本研究针对大型语言模型（LLM）在自主代理应用中的不确定性与实际部署之间的差距进行探讨。提出了从研究界获得的可操作性见解，重点围绕规划、记忆、工具和控制流程四个方面，帮助设计和部署更具稳健性的LLM代理。研究的关键在于强调在真实世界应用中设计自主LLM模型时需考虑的实际问题，如随机性处理和资源管理。 

自主代理大型语言模型系统的实际考虑