mlsanityData to 14 Oct 2026

ThinkQE: Query Expansion via an Evolving Thinking Process

arXiv 2506.09260 ↗First posted 10 Jun 2025cs.IR cs.CLcited by 12

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Effective query expansion for web search benefits from promoting both exploration and result diversity to capture multiple interpretations and facets of a query. While recent LLM-based methods have improved retrieval performance and demonstrate strong domain generalization without additional training, they often generate narrowly focused expansions that overlook these desiderata. We propose ThinkQE, a test-time query expansion framework addressing this limitation through two key components: a thinking-based expansion process that encourages deeper and comprehensive semantic exploration, and a corpus-interaction strategy that iteratively refines expansions using retrieval feedback from the corpus. Experiments on diverse web search benchmarks (DL19, DL20, and BRIGHT) show ThinkQE consistently outperforms prior approaches, including training-intensive dense retrievers and rerankers.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 18 of its 38 references that are in the map. First posted on arXiv 10 Jun 2025.

Builds on

18 of 38 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Rank-K: Test-Time Reasoning for Listwise Reranking20 May
  2. 2025ReasonIR: Training Retrievers for Reasoning Tasks29 Apr
  3. 2025Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning8 Mar
  4. 2025Rank1: Test-Time Compute for Reranking in Information Retrieval25 Feb

Other references · 14

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  6. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  7. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  8. 2020Overview of the TREC 2019 deep learning trackcited by 286
  9. 2021Overview of the TREC 2020 deep learning trackcited by 196
  10. 2025Reasoning Models Can Be Effective Without Thinkingcited by 187
  11. 2023RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!cited by 155
  12. 2025Phi-4-reasoning Technical Reportcited by 151
2 more
  1. 2023Query Expansion by Prompting Large Language Modelscited by 57
  2. 2025Large Language Models are overconfident and amplify human biascited by 30

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 10.

12 papers.

  1. 2025DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrievalcited by 37
  2. 2025Reason to Retrieve: Enhancing Query Understanding through Decomposition and Interpretationcited by 4
  3. 2026RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agentscited by 2
  4. 2026RL-Index: Reinforcement Learning for Retrieval Index Reasoningcited by 2
  5. 2026ADORE: Iterative Query Expansion with Retrieval-Grounded Relevance Feedbackcited by 1
  6. 2026A Systematic Study of Pseudo-Relevance Feedback with LLMscited by 0
  7. 2026Ruling Out to Rule In: Contrastive Hypothesis Retrieval for Medical Question Answeringcited by 0
  8. 2026MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaLcited by 0
  9. 2026BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignmentcited by 0
  10. 2026HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrievalcited by 0
  11. 2026DualView: Adaptive Local-Global Fusion for Multi-Hop Document Rerankingcited by 0
  12. 2026Tracing and Taming Hallucinated Terms via Subsequence-Association Filtering and Breadth-Aware Selection for LLM Query Expansioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance
  2. 2025Enhancing Retrieval-Augmented Generation with Two-Stage Retrieval: FlashRank Reranking and Query Expansion
  3. 2026Query Expansion Should Be Coordinated: Dense Expands, Sparse Anchors
  4. 2025Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models
  5. 2025A New Query Expansion Approach via Agent-Mediated Dialogic Inquiry
  6. 2024A Survey of Query Optimization in Large Language Models
  7. 2026Better Together: Complementary Query Rewriting Under a Strong RAG Baseline
  8. 2026Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging Approach