mlsanityData to 7 Oct 2026

ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval

arXiv 2510.08252 ↗First posted 9 Oct 2025cs.IR cs.CLcited by 15

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce ReasonEmbed, a novel text embedding model developed for reasoning-intensive document retrieval. Our work includes three key technical contributions. First, we propose ReMixer, a new data synthesis method that overcomes the triviality problem prevalent in previous synthetic datasets, enabling large-scale production of 82K high-quality training samples. Second, we design Redapter, a self-adaptive learning algorithm that dynamically adjusts training each sample's weight based on its reasoning intensity. This allows the model to effectively capture the complex semantic relationships between queries and documents. Third, we implement ReasonEmbed across multiple backbones of varying sizes, all of which achieve superior performance on reasoning-intensive retrieval tasks. Notably, our ReasonEmbed-Qwen3-8B model offers a record-high nDCG@10 score of 38.1 on the BRIGHT benchmark, which significantly outperforms existing text embedding models. We will fully open-source our created resources in ReasonEmbed to push forward the research advancement in this field.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 30 of its 39 references that are in the map. First posted on arXiv 9 Oct 2025.

Builds on

30 of 39 references.

References · 30

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2017Billion-scale similarity search with GPUscited by 2,477
  3. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  4. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  5. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  6. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  7. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  8. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
  9. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  10. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  11. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  12. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 466
18 more
  1. 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 271
  2. 2024BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrievalcited by 153
  3. 2025EmbeddingGemma: Powerful and Lightweight Text Representationscited by 128
  4. 2025MMTEB: Massive Multilingual Text Embedding Benchmarkcited by 120
  5. 2024Jasper and Stella: distillation of SOTA embedding modelscited by 109
  6. 2024NV-Retriever: Improving text embedding models with effective hard-negative miningcited by 83
  7. 2024Making Text Embedders Few-Shot Learnerscited by 78
  8. 2025Rank1: Test-Time Compute for Reranking in Information Retrievalcited by 68
  9. 2025Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learningcited by 58
  10. 2025ReasonRank: Empowering Passage Ranking with Strong Reasoning Abilitycited by 39
  11. 2025DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrievalcited by 35
  12. 2024JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Rerankingcited by 34
  13. 2025Rank-K: Test-Time Reasoning for Listwise Rerankingcited by 28
  14. 2025RaDeR: Reasoning-aware Dense Retrieval Modelscited by 27
  15. 2025R2MED: A Benchmark for Reasoning-Driven Medical Retrievalcited by 21
  16. 2025Towards A Generalist Code Embedding Model Based On Massive Data Synthesiscited by 8
  17. 2025Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrievalcited by 7
  18. 2025HotelMatch-LLM: Joint Multi-Task Training of Small and Large Language Models for Efficient Multimodal Hotel Retrievalcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 14.

15 papers.

Sort:

By area:

  1. 2026AgentIR: Reasoning-Aware Retrieval for Deep Research Agentscited by 13
  2. 2026Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrievalcited by 8
  3. 2026LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrievalcited by 8
  4. 2025LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrievalcited by 4
  5. 2026Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systemscited by 2
  6. 2026With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spotscited by 1
  7. 2026A Survey of Reasoning-Intensive Retrieval: Progress and Challengescited by 1
  8. 2026CRE-T1 Preview Technical Report: Beyond Contrastive Learning for Reasoning-Intensive Retrievalcited by 0
  9. 2026On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stabilitycited by 0
  10. 2026GRC: Unifying Reasoning-Driven Generation, Retrieval and Compressioncited by 0
  11. 2026SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematicscited by 0
  12. 2026SHIFT: Self-reconstruction Harnesses Implicit Fine-grained Thinking for Retrievalcited by 0
3 more
  1. 2026InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrievalcited by 0
  2. 2026Retrieval Grounding Latent Reasoning for Dense Retrievalcited by 0
  3. 2026Madeleine: Learning Involuntary Recall for Conversational Memory from Simulated Livescited by 0