GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design

2026-02-07

AI Summary

This work addresses the challenges of cross-domain knowledge integration in materials science and the issues of information overload and model hallucination in the development of PFAS alternatives. We propose a knowledge graph–guided multi-agent collaborative framework that synergistically integrates large language models, domain-specific prompt engineering, and graph traversal algorithms. Specialized agents—tasked with problem decomposition, evidence retrieval, and parameter extraction—dynamically coordinate to balance exploratory and exploitative search strategies, enabling cross-domain relational reasoning and hypothesis generation. By deeply embedding a knowledge graph into the multi-agent system for the first time, our approach uncovers latent connections across disparate knowledge domains and successfully designs multiple PFAS-free candidate materials that meet stringent requirements for tribological performance, thermal stability, chemical resistance, and biocompatibility, thereby significantly expanding the design space for sustainable materials.

Technology Category

• Multiagent Systems: Other Foundations of Multi Agent Systems
• Search and Optimization: Metareasoning and Metaheuristics
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Large Language Models (LLMs) promise to accelerate discovery by reasoning across the expanding scientific landscape. Yet, the challenge is no longer access to information but connecting it in meaningful, domain-spanning ways. In materials science, where innovation demands integrating concepts from molecular chemistry to mechanical performance, this is especially acute. Neither humans nor single-agent LLMs can fully contend with this torrent of information, with the latter often prone to hallucinations. To address this bottleneck, we introduce a multi-agent framework guided by large-scale knowledge graphs to find sustainable substitutes for per- and polyfluoroalkyl substances (PFAS)-chemicals currently under intense regulatory scrutiny. Agents in the framework specialize in problem decomposition, evidence retrieval, design parameter extraction, and graph traversal, uncovering latent connections across distinct knowledge pockets to support hypothesis generation. Ablation studies show that the full multi-agent pipeline outperforms single-shot prompting, underscoring the value of distributed specialization and relational reasoning. We demonstrate that by tailoring graph traversal strategies, the system alternates between exploitative searches focusing on domain-critical outcomes and exploratory searches surfacing emergent cross-connections. Illustrated through the exemplar of biomedical tubing, the framework generates sustainable PFAS-free alternatives that balance tribological performance, thermal stability, chemical resistance, and biocompatibility. This work establishes a framework combining knowledge graphs with multi-agent reasoning to expand the materials design space, showcasing several initial design candidates to demonstrate the approach.

Problem

• cross-domain materials design
• PFAS alternatives
• knowledge integration
• sustainable materials
• multi-domain reasoning

Innovation

• multi-agent framework
• knowledge graph
• cross-domain reasoning
• materials design
• graph traversal