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.
@article{arxiv.2603.23518,
title = {Cluster-R1: Large Reasoning Models Are Instruction-following Clustering Agents},
author = {Peijun Qing and Puneet Mathur and Nedim Lipka and Varun Manjunatha and Ryan Rossi and Franck Dernoncourt and Saeed Hassanpour and Soroush Vosoughi},
journal= {arXiv preprint arXiv:2603.23518},
year = {2026}
}