Large‐Language‐Model‐Based AI Agent for Organic Semiconductor Device Research

ИИ-агент на основе большой языковой модели для исследования органических полупроводниковых приборов
Jiaxin Yan, Wenping Hu, Xinyi Xie, Yajing Sun, Qian Zhang, Yongxu Hu, Hengyue Zhang, Jie Zhu, Huchao Li, Xinxin Niu, Liqiang Li, Wenping Hu, Xinxin Niu
2024-05-30

AI agentExtreme Gradient BoostingGPT-4experimental parameter extractionorganic field-effect transistors
Large language models (LLMs) have attracted widespread attention recently, however, their application in specialized scientific fields still requires deep adaptation. Here, an artificial intelligence (AI) agent for organic field-effect transistors (OFETs) is designed by integrating the generative pre-trained transformer 4 (GPT-4) model with well-trained machine learning (ML) algorithms. It can efficiently extract the experimental parameters of OFETs from scientific literature and reshape them into a structured database, achieving precision and recall rates both exceeding 92%. Combined with well-trained ML models, this AI agent can further provide targeted guidance and suggestions for device design. With prompt engineering and human-in-loop strategies, the agent extracts sufficient information of 709 OFETs from 277 research articles across different publishers and gathers them into a standardized database containing more than 10 000 device parameters. Using this database, a ML model based on Extreme Gradient Boosting is trained for device performance judgment. Combined with the interpretation of the high-precision model, the agent has provided a feasible optimization scheme that has tripled the charge transport properties of 2,6-diphenyldithieno[3,2-b:2',3'-d]thiophene OFETs. This work is an effective practice of LLMs in the field of organic optoelectronic devices and expands the research paradigm of organic optoelectronic materials and devices.
1
An AI agent integrating GPT-4 with trained machine-learning algorithms extracts OFET experimental parameters from literature with precision and recall both exceeding 92%.
2
An Extreme Gradient Boosting model trained on the database supports OFET performance judgment and interpretable device optimization.
3
Prompt engineering and human-in-the-loop strategies enabled extraction of information on 709 OFETs from 277 articles into a standardized database containing over 10,000 device parameters.
4
The agent provides targeted organic field-effect transistor design guidance by combining structured literature data with trained machine-learning models.
5
The agent-derived optimization scheme tripled the charge-transport properties of 2,6-diphenyldithieno[3,2-b:2′,3′-d]thiophene OFETs.

organic field-effect transistors (OFETs)

experimental parameter extraction, structured-data construction, performance prediction, and design optimization of OFETs using an LLM-based AI agent and machine-learning models

Publication Details
Publication Date
2024-05-30
Journal
Publisher
ISSN
Cited by
52
Access Type
Author Information
Authors
Jiaxin Yan
Wenping Hu
Xinyi Xie
Yajing Sun
Qian Zhang
Yongxu Hu
Hengyue Zhang
Jie Zhu
Huchao Li
Xinxin Niu
Liqiang Li
Wenping Hu
Xinxin Niu
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%