Reproduce “Discovering hierarchical governing equations for community-structured complex network dynamics with LLM agents” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jinlei Zhang, Zixuan Zhang, Hao Qiu, Feng Chen, Jiateng Yin, Xiaoyong Yan, Xiaolei Ma, Hao Sun and 3 more
SAGE infers network dynamics as community-shared rules plus node-specific deviations. Numerical solvers fit equations, while an LLM guides revisions to a predefined function catalog when reviews find unexplained patterns. In a synthetic test, SAGE recovered one withheld term family in all 20 runs and the full equation in 90%; the family remained in the broader catalog.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.