Large language models (LLMs) offer strong capabilities but raise cost and privacy concerns, whereas small language models (SLMs) facilitate efficient and private local inference yet suffer from limited capacity. To synergize the complementary strengths, we introduce a dynamic collaboration framework, where an SLM learns to proactively decide how to request an LLM during multi-step reasoning, while the LLM provides adaptive feedback instead of acting as a passive tool. We further systematically investigate how collaboration strategies are shaped by SLM and LLM capabilities as well as efficiency and privacy constraints. Evaluation results reveal a distinct scaling effect: stronger SLMs become more self-reliant, while stronger LLMs enable fewer and more informative interactions. In addition, the learned dynamic collaboration strategies significantly outperform static pipelines and standalone inference, and transfer robustly to unseen LLMs.
@article{arxiv.2604.17827,
title = {Learning to Seek Help: Dynamic Collaboration Between Small and Large Language Models},
author = {Hang Zeng and Xiangyu Liu and Yong Hu and Chaoyue Niu and Jiarui Zhang and Shaojie Tang and Fan Wu and Guihai Chen},
journal= {arXiv preprint arXiv:2604.17827},
year = {2026}
}