Heterogeneous Scientific Foundation Model Collaboration

• URL: http://arxiv.org/abs/2604.27351v1
• Date: Thu, 30 Apr 2026 03:02:27 GMT
• Title: Heterogeneous Scientific Foundation Model Collaboration
• Abstract summary: We introduce Eywa, a heterogeneous agentic framework designed to extend language-centric systems to a broader class of scientific foundation models.<n>Key idea of Eywa is to augment domain-specific foundation models with a language-model-based reasoning interface.<n>Eywa can serve as a drop-in replacement for a single-agent pipeline or be integrated into existing multi-agent systems.
• Score: 48.442331461141926
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• The Emerging Paradigm of Geospatial Foundation Models: From Pre-Training to Agentic Reasoning [0.0]
  The analysis of satellite and aerial imagery has entered a new era with the advent of foundation models.<n>This paper describes the concept of Geospatial Foundation Models (GeoFMs), which are artificial intelligence/machine learning (AI/ML) models pre-trained on massive geospatial datasets.
  arXiv  Detail & Related papers  (2026-07-13T21:50:50Z)
• Rethinking Foundation Model Collaboration: Enhancing Specialized Models through Proxy Task Reasoning [14.610059982650426]
  We propose FAT, a foundation-model-augmented task-specific reasoning framework.<n> FAT decomposes structured prediction into specialist prediction, information-space reconstruction, and foundation-model proxy reasoning.<n>We instantiate this principle as ProxySelect with a vision-language model.
  arXiv  Detail & Related papers  (2026-06-30T05:35:18Z)
• Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences [89.71422932447423]
  LOGOS is a scientific generative language model that unifies heterogeneous tasks across the natural sciences.<n>By representing spatial contact and constraint patterns as discrete tokens, the model captures complex structural interactions in a purely sequential manner.<n>Across diverse tasks, LOGOS consistently matches or outperforms domain-specific baselines.
  arXiv  Detail & Related papers  (2026-06-15T16:14:53Z)
• OrchMAS: Orchestrated Reasoning with Multi Collaborative Heterogeneous Scientific Expert Structured Agents [40.6404203725551]
  We propose a scientific domain oriented interactive two tier multi model orchestration framework.<n>A dedicated orchestration model analyzes each task, dynamically constructs a domain aware reasoning pipeline, and instantiates specialized expert agents with tailored prompts.<n>The orchestrator iteratively updates the pipeline based on intermediate feedback, enabling dynamic replanning, role reallocation, and prompt refinement across multi turn interactions.
  arXiv  Detail & Related papers  (2026-03-03T13:57:43Z)
• HELP: Hierarchical Embodied Language Planner for Household Tasks [75.38606213726906]
  Embodied agents tasked with complex scenarios rely heavily on robust planning capabilities.<n>Large language models equipped with extensive linguistic knowledge can play this role.<n>We propose a Hierarchical Embodied Language Planner, called HELP, consisting of a set of LLM-based agents.
  arXiv  Detail & Related papers  (2025-12-25T15:54:08Z)
• Grounding Natural Language for Multi-agent Decision-Making with Multi-agentic LLMs [10.186029242664931]
  We extend the capabilities of large language models (LLMs) by integrating them with advancements in multi-agent decision-making algorithms.<n>We propose a systematic framework for the design of multi-agentic large language models (LLMs), focusing on key integration practices.
  arXiv  Detail & Related papers  (2025-08-10T19:53:23Z)
• ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges [72.19809898215857]
  We introduce ModelingBench, a novel benchmark featuring real-world-inspired, open-ended problems from math modeling competitions across diverse domains.<n>These tasks require translating natural language into formal mathematical formulations, applying appropriate tools, and producing structured, defensible reports.<n>We also present ModelingAgent, a multi-agent framework that coordinates tool use, supports structured, creative solutions, and generates well-grounded, creative solutions.
  arXiv  Detail & Related papers  (2025-05-21T03:33:23Z)
• Large Language Model Agent: A Survey on Methodology, Applications and Challenges [88.3032929492409]
  Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical pathway toward artificial general intelligence.<n>This survey systematically deconstructs LLM agent systems through a methodology-centered taxonomy.<n>Our work provides a unified architectural perspective, examining how agents are constructed, how they collaborate, and how they evolve over time.
  arXiv  Detail & Related papers  (2025-03-27T12:50:17Z)
• A Survey of Model Architectures in Information Retrieval [59.61734783818073]
  The period from 2019 to the present has represented one of the biggest paradigm shifts in information retrieval (IR) and natural language processing (NLP)<n>We trace the development from traditional term-based methods to modern neural approaches, particularly highlighting the impact of transformer-based models and subsequent large language models (LLMs)<n>We conclude with a forward-looking discussion of emerging challenges and future directions.
  arXiv  Detail & Related papers  (2025-02-20T18:42:58Z)
• Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations [0.0]
  This article explores the influence of computational entities based on multi-agent systems theory (SMA) and large language models (LLM) on human user interaction. In our approach we employ agents developed from large language models (LLM), each with distinct prototyping that considers behavioral elements. We demonstrate the potential of developing agents useful for organizational strategies, based on multi-agent system theories (SMA) and innovative uses based on large language models (LLM based)
  arXiv  Detail & Related papers  (2024-03-12T15:56:10Z)
• PROMISE: A Framework for Developing Complex Conversational Interactions (Technical Report) [33.7054351451505]
  We present PROMISE, a framework that facilitates the development of complex language-based interactions with information systems. We show the benefits of PROMISE in the context of application scenarios within health information systems and demonstrate its ability to handle complex interactions.
  arXiv  Detail & Related papers  (2023-12-06T18:59:11Z)
• Foundation Models for Decision Making: Problems, Methods, and Opportunities [124.79381732197649]
  Foundation models pretrained on diverse data at scale have demonstrated extraordinary capabilities in a wide range of vision and language tasks. New paradigms are emerging for training foundation models to interact with other agents and perform long-term reasoning. Research at the intersection of foundation models and decision making holds tremendous promise for creating powerful new systems.
  arXiv  Detail & Related papers  (2023-03-07T18:44:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.