Arch-Router: Aligning LLM Routing with Human Preferences
Co Tran, Salman Paracha, Adil Hafeez, and Shuguang Chen

TL;DR
Arch-Router is a compact model that aligns large language model routing with human preferences by matching queries to user-defined domains and actions, improving subjective satisfaction and flexibility.
Contribution
We introduce Arch-Router, a novel preference-aligned routing framework that supports adding new models without retraining and captures subjective human preferences.
Findings
Achieves state-of-the-art matching of queries with human preferences
Outperforms top proprietary models in experiments
Supports seamless addition of new models without retraining
Abstract
With the rapid proliferation of large language models (LLMs) -- each optimized for different strengths, style, or latency/cost profile -- routing has become an essential technique to operationalize the use of different models. However, existing LLM routing approaches are limited in two key ways: they evaluate performance using benchmarks that often fail to capture human preferences driven by subjective evaluation criteria, and they typically select from a limited pool of models. In this work, we propose a preference-aligned routing framework that guides model selection by matching queries to user-defined domains (e.g., travel) or action types (e.g., image editing) -- offering a practical mechanism to encode preferences in routing decisions. Specifically, we introduce \textbf{Arch-Router}, a compact 1.5B model that learns to map queries to domain-action preferences for model routing…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
- 🤗katanemo/Arch-Router-1.5Bmodel· 3.5k dl· ♡ 2483.5k dl♡ 248
- 🤗katanemo/Arch-Router-1.5B.ggufmodel· 219 dl· ♡ 13219 dl♡ 13
- 🤗mradermacher/Arch-Router-1.5B-GGUFmodel· 136 dl· ♡ 3136 dl♡ 3
- 🤗Mungert/Arch-Router-1.5B-GGUFmodel· 127 dl127 dl
- 🤗ThomasTheMaker/Arch-Router-1.5B-rkllmmodel· 2 dl2 dl
- 🤗jedisct1/Arch-Router-1.5Bmodel· 12 dl· ♡ 112 dl♡ 1
- 🤗huangang/Arch-Router-1.5B-mlx-4Bitmodel· 4 dl4 dl
- 🤗huangang/Arch-Router-1.5B-mlx-fp16model· 3 dl3 dl
- 🤗N19hty/Arch-Router-1.5B-IQ3_XXS-GGUFmodel· 1 dl1 dl
- 🤗tensorblock/katanemo_Arch-Router-1.5B-GGUFmodel· 11 dl· ♡ 111 dl♡ 1
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMultimodal Machine Learning Applications · Topic Modeling · Natural Language Processing Techniques
