Agentic deep graph reasoning yields self-organizing knowledge networks
Name
43578_2025_Article_1652.pdf
Size
5.63 MB
Format
Adobe PDF
Checksum (MD5)
3fef9b776faaf2afc1be621a66c40459
Author(s)
Buehler, Markus J.
Date Issued
July 31, 2025
Journal
Journal of Materials Research
Publisher
Springer International Publishing
Citation
Buehler, M.J. Agentic deep graph reasoning yields self-organizing knowledge networks. J. Mater. Res. 40, 2204–2242 (2025).
Version
Final published version
Abstract
We present an agentic, autonomous graph expansion framework that iteratively structures and refines knowledge in situ. Unlike conventional knowledge graph construction methods relying on static extraction or single-pass learning, our approach couples a reasoning-native large language model with a continually updated graph representation. At each step, the system actively generates new concepts and relationships, merges them into a global graph, and formulates subsequent prompts based on its evolving structure. Through this feedback-driven loop, the model organizes information into a scale-free network characterized by hub formation, stable modularity, and bridging nodes that link disparate knowledge clusters. Over hundreds of iterations, new nodes and edges continue to appear without saturating, while centrality measures and shortest path distributions evolve to yield increasingly distributed connectivity. Applied to materials design problems, we present compositional reasoning experiments to foster knowledge synthesis, yielding cross-domain ideas that transcend rote summarization.
MIT Department
Massachusetts Institute of Technology. Laboratory for Atomistic and Molecular Mechanics
Massachusetts Institute of Technology. Center for Computational Science and Engineering
MIT Schwarzmann College of Computing
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1557/s43578-025-01652-1
