HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915719288979456 |
|---|---|
| author | Tian, Zihang Li, Rui Zhang, Jingsen Bo, Xiaohe Huo, Wei Chen, Xu |
| author_facet | Tian, Zihang Li, Rui Zhang, Jingsen Bo, Xiaohe Huo, Wei Chen, Xu |
| contents | Large language model (LLM) routing aims to exploit the specialized strengths of different LLMs for diverse tasks. However, existing approaches typically focus on selecting LLM architectures while overlooking parameter settings, which are critical for task performance. In this paper, we introduce HAPS, a hierarchical LLM routing framework that jointly searches over model architectures and parameters. Specifically, we use a high-level router to select among candidate LLM architectures, and then search for the optimal parameters for the selected architectures based on a low-level router. We design a parameter generation network to share parameters between the two routers to mutually enhance their capabilities. In the training process, we design a reward-augmented objective to effectively optimize our framework. Experiments on two commonly used benchmarks show that HAPS consistently outperforms strong routing baselines. We have released our code at https://github.com/zihangtian/HAPS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05903 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search Tian, Zihang Li, Rui Zhang, Jingsen Bo, Xiaohe Huo, Wei Chen, Xu Computation and Language Large language model (LLM) routing aims to exploit the specialized strengths of different LLMs for diverse tasks. However, existing approaches typically focus on selecting LLM architectures while overlooking parameter settings, which are critical for task performance. In this paper, we introduce HAPS, a hierarchical LLM routing framework that jointly searches over model architectures and parameters. Specifically, we use a high-level router to select among candidate LLM architectures, and then search for the optimal parameters for the selected architectures based on a low-level router. We design a parameter generation network to share parameters between the two routers to mutually enhance their capabilities. In the training process, we design a reward-augmented objective to effectively optimize our framework. Experiments on two commonly used benchmarks show that HAPS consistently outperforms strong routing baselines. We have released our code at https://github.com/zihangtian/HAPS. |
| title | HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.05903 |