RAILS: Retrieval-Augmented Incremental LLM Clustering at Scale

Armin Oliya, Aleksandra Sawczuk, Radosław Białobrzeski
9/21/2026
cs.LG

No confident code implementation found for this paper.

Abstract

Using a Large Language Model (LLM) as the clusterer at production scale is hard: prompts cannot hold the entire label space, and per-document serial processing does not deliver the throughput real workloads require. We present RAILS, a retrieval-augmented incremental LLM clusterer that turns clustering into a simple loop over a growing label pool and scales through document batching with bounded concurrency. On six public benchmarks RAILS exceeds the strongest prior LLM-clustering method on average, lifting accuracy from 51.2% to 59.3%, NMI from 67.2% to 74.8%, and ARI from 45.4% to 54.7%. We further report production-deployment evidence from a SaaS ticket-topic-discovery pipeline, where RAILS has replaced a traditional HDBSCAN stage with higher clustering quality, transparent prompt-driven control, and stateful incremental operation.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

TopicMerge: A Divide and Conquer Approach to Topic Modeling

85% match2026

Large Language Models Enable Few-Shot Clustering

84% match1 repo832023

Efficient Clustering with Provable Guardrails for LLM Inference at Scale

83% match2026

LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering

82% match2025

ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation

80% match2025

From Static to Dynamic: A Streaming RAG Approach to Real-time Knowledge Base

80% match2025

Cite this paper

@article{oliya2026rails,
  title  = {RAILS: Retrieval-Augmented Incremental LLM Clustering at Scale},
  author = {Armin Oliya and Aleksandra Sawczuk and Radosław Białobrzeski},
  year   = {2026},
  eprint = {2609.24464},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2609.24464v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2609.24464.svg)](https://codeofpaper.com/paper/2609.24464)

Discussion