Query Suggestion for Retrieval-Augmented Generation via Dynamic In-Context Learning

TL;DR

This paper proposes a dynamic few-shot learning approach for query suggestion in retrieval-augmented generation systems, aiming to improve answerability and relevance of suggested queries in multi-step workflows.

Contribution

It introduces a robust dynamic few-shot learning method that retrieves relevant workflow examples, enhancing query suggestion answerability in agentic RAG systems.

Findings

Outperforms few-shot and retrieval-only baselines in relevance and answerability.

Effective on three benchmark datasets and real-world user queries.

Enables safer, more effective user interaction with RAG systems.

Abstract

Retrieval-augmented generation with tool-calling agents (agentic RAG) has become increasingly powerful in understanding, processing, and responding to user queries. However, the scope of the grounding knowledge is limited and asking questions that exceed this scope may lead to issues like hallucination. While guardrail frameworks aim to block out-of-scope questions (Rodriguez et al., 2024), no research has investigated the question of suggesting answerable queries in order to complete the user interaction. In this paper, we initiate the study of query suggestion for agentic RAG. We consider the setting where user questions are not answerable, and the suggested queries should be similar to aid the user interaction. Such scenarios are frequent for tool-calling LLMs as communicating the restrictions of the tools or the underlying datasets to the user is difficult, and adding query suggestions enhances the interaction with the RAG agent. As opposed to traditional settings for query recommendations such as in search engines, ensuring that the suggested queries are answerable is a major challenge due to the RAG's multi-step workflow that demands a nuanced understanding of the RAG as a whole, which the executing LLM lacks. As such, we introduce robust dynamic few-shot learning which retrieves examples from relevant workflows. We show that our system can be self-learned, for instance on prior user queries, and is therefore easily applicable in practice. We evaluate our approach on three benchmark datasets based on two unlabeled question datasets collected from real-world user queries. Experiments on real-world datasets confirm that our method produces more relevant and answerable suggestions, outperforming few-shot and retrieval-only baselines, and thus enable safer, more effective user interaction with agentic RAG.