A Survey of Large Language Model Agents for Question Answering
This is a survey paper that organizes and reviews existing work on LLM agents for QA, identifying challenges and future directions for researchers in this domain.
This paper surveys the development of large language model (LLM)-based agents for question answering, which address limitations of traditional agents by using LLMs as reasoning engines and achieve superior results compared to existing QA systems.
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.