收藏切换
Multi-Agent Scientific Hypothesis Generation Based on Human-Machine Collaboration
收藏切换
Ziyang Chen1, Xiang Zhao1, *, Runhao Zhao1, Ziqi Ni2, Yicong Ye2
Journal of Computer Research and Development | 2025, 62(7) : 1639 - 1652
Less
收藏切换
Journal of Computer Research and Development | 2025, 62(7): 1639-1652
• Special Issue on Generative AI-driven Information Systems •
Multi-Agent Scientific Hypothesis Generation Based on Human-Machine Collaboration
Full
Ziyang Chen1, Xiang Zhao1, *, Runhao Zhao1, Ziqi Ni2, Yicong Ye2
Affiliations
  • 1Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410003
  • 2College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410003
  • born in 1999. PhD candidate. Member of CCF. His main research interests include natural language processing, knowledge graph, and large language models

    born in 1986. PhD, professor. Distinguished member of CCF. His main research areas include graph data management and analysis, knowledge graphs, and big data knowledge engineering

    born in 2002. Master candidate. His main research interests include natural language processing, knowledge graph question answering, and data fusion

    born in 2000. PhD candidate. Her main research interests include materials informatics and energy storage ceramics

    born in 1985. PhD, professor. His main research interests include materials informatics and special metal materials

About Author:

born in 1999. PhD candidate. Member of CCF. His main research interests include natural language processing, knowledge graph, and large language models

born in 1986. PhD, professor. Distinguished member of CCF. His main research areas include graph data management and analysis, knowledge graphs, and big data knowledge engineering

born in 2002. Master candidate. His main research interests include natural language processing, knowledge graph question answering, and data fusion

born in 2000. PhD candidate. Her main research interests include materials informatics and energy storage ceramics

born in 1985. PhD, professor. His main research interests include materials informatics and special metal materials

Published: 2025-07-01 doi: 10.7544/issn1000-1239.202440552
Outline
收藏切换

With the explosive growth of scientific literature and the continuous deepening of research fields, researchers face significant information processing challenges when attempting to formulate novel scientific hypotheses. Although large language models (LLMs) possess considerable potential for data processing and knowledge integration, they remain limited in their ability to generate original and insightful scientific hypotheses. Existing research predominantly emphasizes utilizing LLMs to expedite and refine established theories and technologies, often overlooking the initial stages of scientific inquiry where novel hypotheses are proposed and new theories are developed—a stage vital to scientific advancement. This study, grounded in the principles of divergent and convergent thinking from the theory of structured intelligence, proposes an innovative human-in-the-loop multi-agent framework (HILMA) for the reliable generation of scientific hypotheses. HILMA framework incorporates a real-time, systematic knowledge retrieval enhancement mechanism, dynamically integrating the latest research advancements to construct citation network subgraphs, providing LLMs with comprehensive and up-to-date scientific knowledge surveys. Additionally, the framework enhances hypothesis generation through a multi-agent argumentation approach that simulates the scientific peer review process, while also leveraging the intuition and expertise of human experts to further refine and diversify the generated hypotheses. A series of human-machine evaluations has shown that this method demonstrates significant advantages over existing baselines in generating high-quality scientific hypotheses and holds promise as a key facilitator for driving technological innovation.

large language models (LLMs)  /  scientific hypothesis generation  /  multi-agent  /  human-machine collaboration  /  theory of structural intelligence
陈子阳, 赵翔, 赵润豪, 倪子淇, 叶益聪. 基于人机协作的多智能体科学假设生成. 计算机研究与发展, 2025 , 62 (7) : 1639 -1652 . DOI: 10.7544/issn1000-1239.202440552
Ziyang Chen, Xiang Zhao, Runhao Zhao, Ziqi Ni, Yicong Ye. Multi-Agent Scientific Hypothesis Generation Based on Human-Machine Collaboration[J]. Journal of Computer Research and Development, 2025 , 62 (7) : 1639 -1652 . DOI: 10.7544/issn1000-1239.202440552
Year 2025 volume 62 Issue 7
122
59
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202440552
  • Receive Date:2024-06-20
  • Online Date:2026-11-10
  • Published:2025-07-01
Article Data
Affiliations
History
  • Received:2024-06-20
  • Revised:2024-12-31
Affiliations
    1Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410003
    2College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410003
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440552
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT