# RAILS: Retrieval-Augmented Incremental LLM Clustering at Scale

arXiv: https://arxiv.org/abs/2609.24464 · HTML: https://mlsanity.com/paper/2609.24464/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 12 of 12)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark](https://mlsanity.com/paper/2008.09335/) (2020)
- [Few-NERD: A Few-Shot Named Entity Recognition Dataset](https://mlsanity.com/paper/2105.07464/) (2021)
- [ClusterLLM: Large Language Models as a Guide for Text Clustering](https://mlsanity.com/paper/2305.14871/) (2023)
- [Goal-Driven Explainable Clustering via Language Descriptions](https://mlsanity.com/paper/2305.13749/) (2023)
- [Text Clustering as Classification with LLMs](https://mlsanity.com/paper/2410.00927/) (2024)
- [Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues](https://mlsanity.com/paper/2412.09049/) (2024)
- [LLMs Enable Bag-of-Texts Representations for Short-Text Clustering](https://mlsanity.com/paper/2510.06747/) (2025)
- [LLM-Guided Lifecycle-Aware Clustering of Multi-Turn Customer Support Conversations](https://mlsanity.com/paper/2601.04388/) (2026)
- [Optimized Algorithms for Text Clustering with LLM-Generated Constraints](https://mlsanity.com/paper/2601.11118/) (2026)
- [PRISM: LLM-Guided Semantic Clustering for High-Precision Topics](https://mlsanity.com/paper/2604.03180/) (2026)

## Abstract (arXiv)

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.