# DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval

arXiv: https://arxiv.org/abs/2508.07995 · HTML: https://mlsanity.com/paper/2508.07995/

## Key facts

- Cited by 37 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 22 of its 36 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 22 of 22)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity](https://mlsanity.com/paper/2310.07521/) (2023)
- [Gecko: Versatile Text Embeddings Distilled from Large Language Models](https://mlsanity.com/paper/2403.20327/) (2024)
- [ReasonIR: Training Retrievers for Reasoning Tasks](https://mlsanity.com/paper/2504.20595/) (2025)
- [Rank1: Test-Time Compute for Reranking in Information Retrieval](https://mlsanity.com/paper/2502.18418/) (2025)
- [Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning](https://mlsanity.com/paper/2503.06034/) (2025)
- [ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability](https://mlsanity.com/paper/2508.07050/) (2025)
- [InfoNCE: Identifying the Gap Between Theory and Practice](https://mlsanity.com/paper/2407.00143/) (2024)
- [Rank-K: Test-Time Reasoning for Listwise Reranking](https://mlsanity.com/paper/2505.14432/) (2025)
- [RaDeR: Reasoning-aware Dense Retrieval Models](https://mlsanity.com/paper/2505.18405/) (2025)
- [REARANK: Reasoning Re-ranking Agent via Reinforcement Learning](https://mlsanity.com/paper/2505.20046/) (2025)
- [ThinkQE: Query Expansion via an Evolving Thinking Process](https://mlsanity.com/paper/2506.09260/) (2025)
- [TongSearch-QR: Reinforced Query Reasoning for Retrieval](https://mlsanity.com/paper/2506.11603/) (2025)
- [Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking](https://mlsanity.com/paper/2504.03947/) (2025)
- [HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.05714/) (2025)
- [BRIGHT+: Upgrading the BRIGHT Benchmark with MARCUS, a Multi-Agent RAG Clean-Up Suite](https://mlsanity.com/paper/2506.07116/) (2025)
- [Leveraging Reference Documents for Zero-Shot Ranking via Large Language Models](https://mlsanity.com/paper/2506.11452/) (2025)
- [PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.22927/) (2025)
- [POLYRAG: Integrating Polyviews into Retrieval-Augmented Generation for Medical Applications](https://mlsanity.com/paper/2504.14917/) (2025)

## Built on by (most cited first, 30 of 37)

- [τ-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge](https://mlsanity.com/paper/2603.04370/) (2026)
- [ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval](https://mlsanity.com/paper/2510.08252/) (2025)
- [MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrieval](https://mlsanity.com/paper/2510.09510/) (2025)
- [LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving](https://mlsanity.com/paper/2605.13137/) (2026)
- [Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm](https://mlsanity.com/paper/2510.14321/) (2025)
- [Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval](https://mlsanity.com/paper/2602.19961/) (2026)
- [OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries](https://mlsanity.com/paper/2605.06235/) (2026)
- [MR2-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval](https://mlsanity.com/paper/2509.26378/) (2025)
- [TEMPO: A Realistic Multi-Domain Benchmark for Temporal Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2601.09523/) (2026)
- [Query-focused and Memory-aware Reranker for Long Context Processing](https://mlsanity.com/paper/2602.12192/) (2026)
- [LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval](https://mlsanity.com/paper/2510.13217/) (2025)
- [Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms](https://mlsanity.com/paper/2601.20131/) (2026)
- [Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead](https://mlsanity.com/paper/2604.03676/) (2026)
- [LimRank: Less is More for Reasoning-Intensive Information Reranking](https://mlsanity.com/paper/2510.23544/) (2025)
- [GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs](https://mlsanity.com/paper/2511.11653/) (2025)
- [ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge](https://mlsanity.com/paper/2602.09839/) (2026)
- [Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems](https://mlsanity.com/paper/2605.04018/) (2026)
- [Very Efficient Listwise Multimodal Reranking for Long Documents](https://mlsanity.com/paper/2605.11864/) (2026)
- [RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents](https://mlsanity.com/paper/2605.26352/) (2026)
- [Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM](https://mlsanity.com/paper/2509.02558/) (2025)
- [A Survey of Reasoning-Intensive Retrieval: Progress and Challenges](https://mlsanity.com/paper/2605.00063/) (2026)
- [SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG](https://mlsanity.com/paper/2606.16661/) (2026)
- [SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematics](https://mlsanity.com/paper/2606.29894/) (2026)
- [The Magnitude Mirage: Rethinking Confidence for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2609.15578/) (2026)
- [Inferential Question Answering](https://mlsanity.com/paper/2602.01239/) (2026)
- [RAG without Forgetting: Continual Query-Infused Key Memory](https://mlsanity.com/paper/2602.05152/) (2026)
- [MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL](https://mlsanity.com/paper/2604.07079/) (2026)
- [BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment](https://mlsanity.com/paper/2604.07201/) (2026)
- [HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2604.07220/) (2026)
- [Context Convergence Improves Answering Inferential Questions](https://mlsanity.com/paper/2605.12370/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation has achieved strong performance on knowledge-intensive tasks where query-document relevance can be identified through direct lexical or semantic matches. However, many real-world queries involve abstract reasoning, analogical thinking, or multi-step inference, which existing retrievers often struggle to capture. To address this challenge, we present DIVER, a retrieval pipeline designed for reasoning-intensive information retrieval. It consists of four components. The document preprocessing stage enhances readability and preserves content by cleaning noisy texts and segmenting long documents. The query expansion stage leverages large language models to iteratively refine user queries with explicit reasoning and evidence from retrieved documents. The retrieval stage employs a model fine-tuned on synthetic data spanning medical and mathematical domains, along with hard negatives, enabling effective handling of reasoning-intensive queries. Finally, the reranking stage combines pointwise and listwise strategies to produce both fine-grained and globally consistent rankings. On the BRIGHT benchmark, DIVER achieves state-of-the-art nDCG@10 scores of 46.8 overall and 31.9 on original queries, consistently outperforming competitive reasoning-aware models. These results demonstrate the effectiveness of reasoning-aware retrieval strategies in complex real-world tasks.