# Query-aware Routing for Filtered Approximate Nearest Neighbors Search

arXiv: https://arxiv.org/abs/2606.19898 · HTML: https://mlsanity.com/paper/2606.19898/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Vector search and ANN indexes, one of 15 directions in Retrieval-augmented generation.
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Placed in

- Retrieval-augmented generation / [Vector search and ANN indexes](https://mlsanity.com/rag/vector-search-and-ann-indexes/)

## Builds on (most cited first, 8 of 8)

- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithms](https://mlsanity.com/paper/1807.05614/) (2018)
- [Approximate Nearest Neighbor Search with Window Filters](https://mlsanity.com/paper/2402.00943/) (2024)
- [UNIFY: Unified Index for Range Filtered Approximate Nearest Neighbors Search](https://mlsanity.com/paper/2412.02448/) (2024)
- [HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints](https://mlsanity.com/paper/2207.07940/) (2022)
- [SIEVE: Effective Filtered Vector Search with Collection of Indexes](https://mlsanity.com/paper/2507.11907/) (2025)
- [Efficient Filtered-ANN via Learning-based Query Planning](https://mlsanity.com/paper/2602.17914/) (2026)

## Abstract (arXiv)

Filtered ANN search, which combines vector similarity with attribute predicates, is a core primitive in modern vector databases and retrieval-augmented generation. We benchmark all major categorical filtered ANN methods across multiple datasets under three predicates and find that no single method dominates. Moreover, even within a single dataset and predicate type, the best method for a query can vary. Therefore, we propose a query-aware routing framework. A lightweight ML model predicts each candidate method's recall on the query, and the router consults an offline benchmark table that maps every method and parameter setting to its measured recall and QPS, then selects the method with the best recall--QPS trade-off. Our ablation study narrows 22 candidate features to a minimal set of three and we adopt regression rather than classification as the prediction target to sharpen accuracy. Our model is trained on six real-world datasets and applied to five unseen validation datasets. The final result shows that our router achieves state-of-the-art recall and QPS balance across all five validation datasets compared to existing filtered ANN baselines, while incurring negligible latency overhead.