CoLM: Collaborative Large Models via a Client-Server Paradigm
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (26) · 22039-22047
DOI: 10.1609/aaai.v40i26.39358 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Siqi Huang und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Large models have achieved remarkable performance across a range of reasoning and understanding tasks. Prior work often utilizes model ensembles or multi-agent systems to collaboratively generate responses, effectively operating in a server-to-server paradigm. However, such approaches do not align well with practical deployment settings, where a limited number of server-side models are shared by many clients under modern internet architectures. In this paper, we introduce CoLM (Collaboration in Large-Models), a novel framework for collaborative reasoning that redefines cooperation among large models from a client-server perspective. Unlike traditional ensemble methods that rely on simultaneous inference from multiple models to produce a single output, CoLM allows the outputs of multiple models to be aggregated or shared, enabling each client model to independently refine and update its own generation based on these high-quality outputs. This design enables collaborative benefits by fully leveraging both client-side and shared server-side models. We further extend CoLM to vision-language models (VLMs), demonstrating its applicability beyond language tasks. Experimental results across multiple benchmarks show that CoLM consistently improves model performance on previously failed queries, highlighting the effectiveness of collaborative guidance in enhancing single-model capabilities.
Zitieren
APA
Huang, S., Huang, S., & Zhang, H. (2026). CoLM: Collaborative Large Models via a Client-Server Paradigm. Proceedings of the AAAI Conference on Artificial Intelligence, 40(26), 22039-22047. https://doi.org/10.1609/aaai.v40i26.39358
Vancouver
Huang S, Huang S, Zhang H. CoLM: Collaborative Large Models via a Client-Server Paradigm. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(26):22039-22047. doi:10.1609/aaai.v40i26.39358
BibTeX
@article{Huang2026,
author = {Huang, Siqi and Huang, Sida and Zhang, Hongyuan},
title = {CoLM: Collaborative Large Models via a Client-Server Paradigm},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {26},
pages = {22039--22047},
doi = {10.1609/aaai.v40i26.39358}
}
EUVIMED