用大模型做问答代理，能更好理解问题并获取外部信息。
A Survey of Large Language Model Agents for Question Answering
- 以大模型为核心引擎，动态规划回答步骤
- 相比传统方法，问答准确率显著提升
- 适合研究智能对话系统与自主推理的学者
本文综述了基于大语言模型（LLM）的问答代理的发展。传统代理存在数据需求高、泛化能力差等问题，而基于LLM的代理通过将大模型作为核心推理引擎，克服了这些挑战。这类代理在问答任务中表现优于传统流水线和直接使用大模型的简单方法，关键在于能够与外部环境交互。本文系统梳理了问答场景下LLM代理的设计，涵盖规划、问题理解、信息检索和答案生成等关键阶段。同时，文章指出了当前面临的挑战，并探讨了未来提升性能的研究方向。
原文摘要 · Abstract (English)
This paper surveys the development of large language model (LLM)-based agents for question answering (QA). Traditional agents face significant limitations, including substantial data requirements and difficulty in generalizing to new environments. LLM-based agents address these challenges by leveraging LLMs as their core reasoning engine. These agents achieve superior QA results compared to traditional QA pipelines and naive LLM QA systems by enabling interaction with external environments. We systematically review the design of LLM agents in the context of QA tasks, organizing our discussion across key stages: planning, question understanding, information retrieval, and answer generation. Additionally, this paper identifies ongoing challenges and explores future research directions to enhance the performance of LLM agent QA systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。