# DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation

arXiv: https://arxiv.org/abs/2508.16998 · HTML: https://mlsanity.com/paper/2508.16998/

## Key facts

- Cited by 11 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 28 of its 51 references that are in the map.
- First posted on arXiv 23 Aug 2025.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://mlsanity.com/paper/2003.06713/) (2020)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [Multi-Stage Document Ranking with BERT](https://mlsanity.com/paper/1910.14424/) (2019)
- [Improving Passage Retrieval with Zero-Shot Question Generation](https://mlsanity.com/paper/2204.07496/) (2022)
- [RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!](https://mlsanity.com/paper/2312.02724/) (2023)
- [Zero-Shot Listwise Document Reranking with a Large Language Model](https://mlsanity.com/paper/2305.02156/) (2023)
- [The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models](https://mlsanity.com/paper/2101.05667/) (2021)
- [RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models](https://mlsanity.com/paper/2309.15088/) (2023)
- [Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations](https://mlsanity.com/paper/2102.10073/) (2021)
- [Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers](https://mlsanity.com/paper/2410.02642/) (2024)
- [Scaling Down, LiTting Up: Efficient Zero-Shot Listwise Reranking with Seq2seq Encoder-Decoder Models](https://mlsanity.com/paper/2312.16098/) (2023)
- [TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions](https://mlsanity.com/paper/2502.21024/) (2025)
- [Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.02464/) (2025)
- [ReasoningRank: Teaching Student Models to Rank through Reasoning-Based Knowledge Distillation](https://mlsanity.com/paper/2410.05168/) (2024)
- [ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrieval](https://mlsanity.com/paper/2501.15245/) (2025)
- [InRanker: Distilled Rankers for Zero-shot Information Retrieval](https://mlsanity.com/paper/2401.06910/) (2024)
- [ComplexTempQA:A 100m Dataset for Complex Temporal Question Answering](https://mlsanity.com/paper/2406.04866/) (2024)
- [RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback](https://mlsanity.com/paper/2508.05512/) (2025)
- [EcoRank: Budget-Constrained Text Re-ranking Using Large Language Models](https://mlsanity.com/paper/2402.10866/) (2024)

## Built on by (most cited first, 11 of 11)

- [jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking](https://mlsanity.com/paper/2509.25085/) (2025)
- [LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation](https://mlsanity.com/paper/2601.05192/) (2026)
- [TEMPO: A Realistic Multi-Domain Benchmark for Temporal Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2601.09523/) (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)
- [Argus-Retriever: Vision-LLM Late-Interaction Retrieval with Region-Aware Query-Conditioned MoE for Visual Document Retrieval](https://mlsanity.com/paper/2606.04300/) (2026)
- [DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering](https://mlsanity.com/paper/2601.16478/) (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)
- [BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination](https://mlsanity.com/paper/2604.08834/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have transformed listwise document reranking by enabling global reasoning over candidate sets, yet single models often struggle to balance fine-grained relevance scoring with holistic cross-document analysis. We propose DeepAgentRank (DeAR), an open-source framework that decouples these tasks through a dual-stage approach, achieving superior accuracy and interpretability. In Stage 1, we distill token-level relevance signals from a frozen 13B LLaMA teacher into a compact 3, 8B student model using a hybrid of cross-entropy, RankNet, and KL divergence losses, ensuring robust pointwise scoring. In Stage 2, we attach a second LoRA adapter and fine-tune on 20K GPT-4o-generated chain-of-thought permutations, enabling listwise reasoning with natural-language justifications. Evaluated on TREC-DL19/20, eight BEIR datasets, and NovelEval-2306, DeAR surpasses open-source baselines by +5.1 nDCG@5 on DL20 and achieves 90.97 nDCG@10 on NovelEval, outperforming GPT-4 by +3.09. Without fine-tuning on Wikipedia, DeAR also excels in open-domain QA, achieving 54.29 Top-1 accuracy on Natural Questions, surpassing baselines like MonoT5, UPR, and RankGPT. Ablations confirm that dual-loss distillation ensures stable calibration, making DeAR a highly effective and interpretable solution for modern reranking systems.footnoteDataset and code available at https://github.com/DataScienceUIBK/DeAR-Reranking..