SasAgent: Multi-Agent AI System for Small-Angle Scattering Data Analysis

2025-09-03

AI Summary

To address the labor-intensive, expert-dependent nature of small-angle scattering (SAS) data analysis, this paper proposes a large language model (LLM)-based multi-agent system enabling end-to-end automated analysis and natural-language interaction. The system employs a retrieval-augmented generation (RAG)-enhanced multi-agent architecture that integrates core SasView functionalities—including scattering length density (SLD) calculation, parametric model fitting, and synthetic data generation—and delivers an intuitive text-based interface via Gradio. Key contributions include: (1) the first application of LLM-driven multi-agent paradigms to SAS analysis; (2) RAG-enabled precise alignment between physical model documentation and tool APIs, substantially improving instruction comprehension and task execution accuracy; and (3) experimental validation demonstrating high-fidelity performance on complex fitting and parameter inversion tasks, significantly lowering technical barriers for non-expert users.

Technology Category

• Multiagent Systems: Modeling other Agents
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

We introduce SasAgent, a multi-agent AI system powered by large language models (LLMs) that automates small-angle scattering (SAS) data analysis by leveraging tools from the SasView software and enables user interaction via text input. SasAgent features a coordinator agent that interprets user prompts and delegates tasks to three specialized agents for scattering length density (SLD) calculation, synthetic data generation, and experimental data fitting. These agents utilize LLM-friendly tools to execute tasks efficiently. These tools, including the model data tool, Retrieval-Augmented Generation (RAG) documentation tool, bump fitting tool, and SLD calculator tool, are derived from the SasView Python library. A user-friendly Gradio-based interface enhances user accessibility. Through diverse examples, we demonstrate SasAgent's ability to interpret complex prompts, calculate SLDs, generate accurate scattering data, and fit experimental datasets with high precision. This work showcases the potential of LLM-driven AI systems to streamline scientific workflows and enhance automation in SAS research.

Problem

• Automates small-angle scattering data analysis workflow
• Enables user interaction via text input interpretation
• Fits experimental datasets with high precision accuracy

Innovation

• Multi-agent AI system automates SAS data analysis
• LLM-powered coordinator delegates tasks to specialized agents
• Integrates SasView tools for SLD calculation and fitting