StackRAG Agent: Improving Developer Answers with Retrieval-Augmented Generation
This addresses the issue of unreliable or time-consuming information retrieval for developers, but it appears incremental as it builds on existing RAG and multiagent approaches.
The paper tackles the problem of developers spending time finding reliable information by proposing StackRAG, a retrieval-augmented multiagent tool that combines Stack Overflow knowledge with LLMs to improve answer reliability, with initial evaluations showing correct, accurate, relevant, and useful generated answers.
Developers spend much time finding information that is relevant to their questions. Stack Overflow has been the leading resource, and with the advent of Large Language Models (LLMs), generative models such as ChatGPT are used frequently. However, there is a catch in using each one separately. Searching for answers is time-consuming and tedious, as shown by the many tools developed by researchers to address this issue. On the other, using LLMs is not reliable, as they might produce irrelevant or unreliable answers (i.e., hallucination). In this work, we present StackRAG, a retrieval-augmented Multiagent generation tool based on LLMs that combines the two worlds: aggregating the knowledge from SO to enhance the reliability of the generated answers. Initial evaluations show that the generated answers are correct, accurate, relevant, and useful.