mlsanityData to 14 Oct 2026

Cluster-R1: Large Reasoning Models Are Instruction-following Clustering Agents

arXiv 2603.23518 ↗First posted 6 Mar 2026cs.CL cs.AIcited by 2

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

General-purpose embedding models excel at recognizing semantic similarities but fail to capture the characteristics of texts specified by user instructions. In contrast, instruction-tuned embedders can align embeddings with textual instructions yet cannot autonomously infer latent corpus structures, such as determining the optimal number of clusters. To address both limitations, we reframe instruction-following clustering as a generative task and train large reasoning models (LRMs) as autonomous clustering agents. Our reasoning-driven training pipeline enables LRMs to interpret high-level clustering instructions and then infer the corresponding latent groupings. To evaluate this paradigm, we introduce ReasonCluster, a comprehensive benchmark comprising 28 diverse tasks spanning daily dialogue, legal cases, and financial reports. Experiments across diverse datasets and clustering scenarios show that our approach consistently outperforms strong embedding-based methods and LRM baselines, demonstrating that explicit reasoning fosters more faithful and interpretable instruction-based clustering.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 12 of its 53 references that are in the map. First posted on arXiv 6 Mar 2026.

Builds on

12 of 53 references.

References · 12

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  5. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  6. 2022MTEB: Massive Text Embedding Benchmarkcited by 640
  7. 2025RM-R1: Reward Modeling as Reasoningcited by 154
  8. 2021Supporting Clustering with Contrastive Learningcited by 90
  9. 2023Goal-Driven Explainable Clustering via Language Descriptionscited by 58
  10. 2023IDAS: Intent Discovery with Abstractive Summarizationcited by 22
  11. 2024Context-Aware Clustering using Large Language Modelscited by 9
  12. 2019An end-to-end Neural Network Framework for Text Clusteringcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026AudioLens: Multi-Perspective Speech Clustering with Reasoning Audio-Language Modelscited by 0
  2. 2026UTILMEM: Benchmarking Evidence Utilization in Long-Term Conversational Memorycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Reasoning-Based Refinement of Unsupervised Text Clusters with LLMs
  2. 2025Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs
  3. 2025ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation
  4. 2025MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
  5. 2025Latent Reasoning via Sentence Embedding Prediction
  6. 2025A Tale of LLMs and Induced Small Proxies: Scalable Small Language Models for Knowledge Mining
  7. 2025Big Reasoning with Small Models: Instruction Retrieval at Inference Time
  8. 2026RA-MoWE: Workflow-Affinity Embeddings for Query Clustering and Agentic Workflow Generation