# Your Dense Retriever is Secretly an Expeditious Reasoner

arXiv: https://arxiv.org/abs/2510.21727 · HTML: https://mlsanity.com/paper/2510.21727/

## Key facts

- Cited by 6 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 0 of its 48 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Built on by (most cited first, 6 of 6)

- [LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval](https://mlsanity.com/paper/2603.01425/) (2026)
- [A Survey of Reasoning-Intensive Retrieval: Progress and Challenges](https://mlsanity.com/paper/2605.00063/) (2026)
- [SHIFT: Self-reconstruction Harnesses Implicit Fine-grained Thinking for Retrieval](https://mlsanity.com/paper/2607.21333/) (2026)
- [BLADE: Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning](https://mlsanity.com/paper/2607.28966/) (2026)
- [Retrieval Grounding Latent Reasoning for Dense Retrieval](https://mlsanity.com/paper/2608.14107/) (2026)
- [Mitigating Video Hallucinations via Attention-Guided Representation Perturbation](https://mlsanity.com/paper/2610.19728/) (2026)

## Abstract (arXiv)

Dense retrievers enhance retrieval by encoding queries and documents into continuous vectors, but they often struggle with reasoning-intensive queries. Although Large Language Models (LLMs) can reformulate queries to capture complex reasoning, applying them universally incurs significant computational cost. In this work, we propose Adaptive Query Reasoning (AdaQR), a hybrid query rewriting framework. Within this framework, a Reasoner Router dynamically directs each query to either fast dense reasoning or deep LLM reasoning. The dense reasoning is achieved by the Dense Reasoner, which performs LLM-style reasoning directly in the embedding space, enabling a controllable trade-off between efficiency and accuracy. Experiments on large-scale retrieval benchmarks BRIGHT show that AdaQR reduces reasoning cost by 28% while preserving-or even improving-retrieval performance by 7%.