Large language models (LLMs) often exhibit complementary strengths. Model routing harnesses these strengths by dynamically directing each query to the most suitable model, given a candidate model pool. However, routing performance relies on accurate model representations, and adding new models typically requires retraining, limiting scalability. To address these challenges, we propose a novel routing method using in-context vectors to represent model capabilities. The method proceeds in two stages. First, queries are embedded and projected into vectors, with a projector and LLM-based router trained to reconstruct the original queries, aligning vector representations with the router's semantic space. Second, each candidate model is profiled on a query set, and the router learns -- based on in-context vectors of query and model performance -- to predict whether each model can correctly answer new queries. Extensive experiments demonstrate that our method achieves state-of-the-art routing performance in both in-distribution and out-of-distribution tasks. Moreover, our method allows for seamless integration of new models without retraining the router. The code is available at https://github.com/lalalamdbf/ICL-Router.
@article{arxiv.2510.09719,
title = {ICL-Router: In-Context Learned Model Representations for LLM Routing},
author = {Chenxu Wang and Hao Li and Yiqun Zhang and Linyao Chen and Jianhao Chen and Ping Jian and Peng Ye and Qiaosheng Zhang and Shuyue Hu},
journal= {arXiv preprint arXiv:2510.09719},
year = {2025}
}