Heterogeneous Scientific Foundation Model Collaboration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Zihao, Zou, Jiaru, Fang, Feihao, Ning, Xuying, Ai, Mengting, Wei, Tianxin, Chen, Sirui, Yang, Xiyuan, He, Jingrui
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915970474311680
author Li, Zihao
Zou, Jiaru
Fang, Feihao
Ning, Xuying
Ai, Mengting
Wei, Tianxin
Chen, Sirui
Yang, Xiyuan
He, Jingrui
author_facet Li, Zihao
Zou, Jiaru
Fang, Feihao
Ning, Xuying
Ai, Mengting
Wei, Tianxin
Chen, Sirui
Yang, Xiyuan
He, Jingrui
contents Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally limits their applicability to many real-world problems, especially in scientific domains where domain-specific foundation models have been developed to address specialized tasks beyond natural language. In this work, we introduce Eywa, a heterogeneous agentic framework designed to extend language-centric systems to a broader class of scientific foundation models. The key idea of Eywa is to augment domain-specific foundation models with a language-model-based reasoning interface, enabling language models to guide inference over non-linguistic data modalities. This design allows predictive foundation models, which are typically optimized for specialized data and tasks, to participate in higher-level reasoning and decision-making processes within agentic systems. Eywa can serve as a drop-in replacement for a single-agent pipeline (EywaAgent) or be integrated into existing multi-agent systems by replacing traditional agents with specialized agents (EywaMAS). We further investigate a planning-based orchestration framework in which a planner dynamically coordinates traditional agents and Eywa agents to solve complex tasks across heterogeneous data modalities (EywaOrchestra). We evaluate Eywa across a diverse set of scientific domains spanning physical, life, and social sciences. Experimental results demonstrate that Eywa improves performance on tasks involving structured and domain-specific data, while reducing reliance on language-based reasoning through effective collaboration with specialized foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2604_27351
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Heterogeneous Scientific Foundation Model Collaboration
Li, Zihao
Zou, Jiaru
Fang, Feihao
Ning, Xuying
Ai, Mengting
Wei, Tianxin
Chen, Sirui
Yang, Xiyuan
He, Jingrui
Artificial Intelligence
Computation and Language
Machine Learning
Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally limits their applicability to many real-world problems, especially in scientific domains where domain-specific foundation models have been developed to address specialized tasks beyond natural language. In this work, we introduce Eywa, a heterogeneous agentic framework designed to extend language-centric systems to a broader class of scientific foundation models. The key idea of Eywa is to augment domain-specific foundation models with a language-model-based reasoning interface, enabling language models to guide inference over non-linguistic data modalities. This design allows predictive foundation models, which are typically optimized for specialized data and tasks, to participate in higher-level reasoning and decision-making processes within agentic systems. Eywa can serve as a drop-in replacement for a single-agent pipeline (EywaAgent) or be integrated into existing multi-agent systems by replacing traditional agents with specialized agents (EywaMAS). We further investigate a planning-based orchestration framework in which a planner dynamically coordinates traditional agents and Eywa agents to solve complex tasks across heterogeneous data modalities (EywaOrchestra). We evaluate Eywa across a diverse set of scientific domains spanning physical, life, and social sciences. Experimental results demonstrate that Eywa improves performance on tasks involving structured and domain-specific data, while reducing reliance on language-based reasoning through effective collaboration with specialized foundation models.
title Heterogeneous Scientific Foundation Model Collaboration
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2604.27351