Bridging Concepts: Multi-Agent Reasoning over Scientific Concept Graphs for High-Impact Research Prediction

arXiv:2610.25281v1 Announce Type: cross Abstract: Within a research community, new topics often emerge when previously unconnected concepts are first studied together. We construct scientific concept graphs (SCGs)--domain knowledge graphs whose nodes are fine-grained research concepts extracted from paper text by LLMs and whose edges capture their co-occurrence in papers--and study the task of forecasting high-impact concept pairs, i.e., discovering concept pairs that are currently unconnected but will have high impact when connected. To this end, we introduce new benchmark datasets constructed from CIKM, KDD, and SIGIR conference papers, with varied prediction settings, including impact forecasting for emerging concepts unseen during training. We propose MiroGraph, a Multi-agent reasoning framework with scientific concept Graphs, in which a feature designer agent designs predictive features for a given concept pair from structural, semantic, and trend perspectives, and then three LLM agents compute the actual feature values from the enclosing subgraph of the concept pair. Using these feature values, a classifier designer agent constructs a classifier that predicts the final impact labels. MiroGraph outperforms various impact forecasting and temporal link prediction methods.

Related

• Learning the Geometry of Admissible Hypotheses through Inductive Bias in Training Distributions
• Where and Why Search-Augmented LLMs Fail When Reasoning over Rapidly Evolving Knowledge
• SynCo: Synthetic Community-Aware Attributed Graph Generator for Graph Neural Network Benchmarking

Source: arXiv cs.LG | 2026-10-20