Problem
Research questions and friction points this paper is trying to address.
scientific literature summarization
fragmented literature
deep insight extraction
LLM hallucinations
reliable knowledge synthesis
A Multi-Agent Human-LLM Collaborative Framework for Closed-Loop Scientific Literature Summarization
🤖 AI Summary
This study addresses the severe fragmentation of scientific literature, which significantly hinders research efficiency and limits the ability of existing AI tools to reliably extract deep insights. To overcome this challenge, the authors propose the first literature review framework that enables closed-loop collaboration between human experts and a multi-agent large language model. The framework employs phased document screening, structured data extraction, modeling, and summarization, iteratively refined through human–AI interaction to produce high-confidence, structured reports. Applied to helium ion irradiation studies of tungsten materials, the approach successfully uncovers an exponential relationship between bubble growth and both irradiation dose and temperature, offering novel insights for plasma-facing material design in fusion reactors and substantially enhancing both the efficiency and depth of scientific discovery.
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
multi-agent system
human-in-the-loop
scientific literature summarization
large language models
structured AI
🔎 Similar Papers
No similar papers found.
