A Multi-Agent Human-LLM Collaborative Framework for Closed-Loop Scientific Literature Summarization

TL;DR

Elhuyar is a multi-agent, human-in-the-loop framework that leverages LLMs and structured AI to systematically analyze scientific literature, producing detailed insights and visualizations to accelerate discovery.

Contribution

The paper introduces Elhuyar, a novel multi-agent system integrating LLMs, structured AI, and human oversight for comprehensive literature analysis and insight extraction.

Findings

Analyzed tungsten literature revealing helium bubble growth correlates with irradiation dose and temperature.

Demonstrated AI-assisted review can uncover scientific patterns in materials science.

System produces structured reports with data, visualizations, and summaries.

Abstract

Scientific discovery is slowed by fragmented literature that requires excessive human effort to gather, analyze, and understand. AI tools, including autonomous summarization and question answering, have been developed to aid in understanding scientific literature. However, these tools lack the structured, multi-step approach necessary for extracting deep insights from scientific literature. Large Language Models (LLMs) offer new possibilities for literature analysis, but remain unreliable due to hallucinations and incomplete extraction. We introduce Elhuyar, a multi-agent, human-in-the-loop system that integrates LLMs, structured AI, and human scientists to extract, analyze, and iteratively refine insights from scientific literature. The framework distributes tasks among specialized agents for filtering papers, extracting data, fitting models, and summarizing findings, with human oversight ensuring reliability. The system generates structured reports with extracted data, visualizations, model equations, and text summaries, enabling deeper inquiry through iterative refinement. Deployed in materials science, it analyzed literature on tungsten under helium-ion irradiation, showing experimentally correlated exponential helium bubble growth with irradiation dose and temperature, offering insight for plasma-facing materials (PFMs) in fusion reactors. This demonstrates how AI-assisted literature review can uncover scientific patterns and accelerate discovery.