# A New Query Expansion Approach via Agent-Mediated Dialogic Inquiry

arXiv: https://arxiv.org/abs/2502.08557 · HTML: https://mlsanity.com/paper/2502.08557/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 48 references that are in the map.
- First posted on arXiv 12 Feb 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 23 of 23)

- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Overview of the TREC 2019 deep learning track](https://mlsanity.com/paper/2003.07820/) (2020)
- [Query2doc: Query Expansion with Large Language Models](https://mlsanity.com/paper/2303.07678/) (2023)
- [BM25S: Orders of magnitude faster lexical search via eager sparse scoring](https://mlsanity.com/paper/2407.03618/) (2024)
- [Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting](https://mlsanity.com/paper/2310.09716/) (2023)
- [Query Expansion by Prompting Large Language Models](https://mlsanity.com/paper/2305.03653/) (2023)
- [MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion](https://mlsanity.com/paper/2310.19056/) (2023)
- [The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models](https://mlsanity.com/paper/2305.14999/) (2023)
- [Corpus-Steered Query Expansion with Large Language Models](https://mlsanity.com/paper/2402.18031/) (2024)
- [Using Word Embeddings for Automatic Query Expansion](https://mlsanity.com/paper/1606.07608/) (2016)
- [GenRewrite: Query Rewriting via Large Language Models](https://mlsanity.com/paper/2403.09060/) (2024)
- [Generative and Pseudo-Relevant Feedback for Sparse, Dense and Learned Sparse Retrieval](https://mlsanity.com/paper/2305.07477/) (2023)
- [Socratic Reasoning Improves Positive Text Rewriting](https://mlsanity.com/paper/2403.03029/) (2024)
- [Query expansion with artificially generated texts](https://mlsanity.com/paper/2012.08787/) (2020)
- [Generative Query Reformulation Using Ensemble Prompting, Document Fusion, and Relevance Feedback](https://mlsanity.com/paper/2405.17658/) (2024)
- [A novel model for query expansion using pseudo-relevant web knowledge](https://mlsanity.com/paper/1908.10193/) (2019)
- [GenCRF: Generative Clustering and Reformulation Framework for Enhanced Intent-Driven Information Retrieval](https://mlsanity.com/paper/2409.10909/) (2024)
- [Exploiting LLMs' Reasoning Capability to Infer Implicit Concepts in Legal Information Retrieval](https://mlsanity.com/paper/2410.12154/) (2024)

## Built on by (most cited first, 2 of 2)

- [Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines](https://mlsanity.com/paper/2604.22661/) (2026)
- [VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies](https://mlsanity.com/paper/2608.12282/) (2026)

## Abstract (arXiv)

Query expansion is widely used in Information Retrieval (IR) to improve search outcomes by supplementing initial queries with richer information. While recent Large Language Model (LLM) based methods generate pseudo-relevant content and expanded terms via multiple prompts, they often yield homogeneous, narrow expansions that lack the diverse context needed to retrieve relevant information. In this paper, we propose AMD: a new Agent-Mediated Dialogic Framework that engages in a dialogic inquiry involving three specialized roles: (1) a Socratic Questioning Agent reformulates the initial query into three sub-questions, with each question inspired by a specific Socratic questioning dimension, including clarification, assumption probing, and implication probing, (2) a Dialogic Answering Agent generates pseudo-answers, enriching the query representation with multiple perspectives aligned to the user's intent, and (3) a Reflective Feedback Agent evaluates and refines these pseudo-answers, ensuring that only the most relevant and informative content is retained. By leveraging a multi-agent process, AMD effectively crafts richer query representations through inquiry and feedback refinement. Extensive experiments on benchmarks including BEIR and TREC demonstrate that our framework outperforms previous methods, offering a robust solution for retrieval tasks.