Year: 2026
Type: conference-paper
Abstract: Zero-shot reasoning on text-rich networks (TRNs) remains a challenging frontier, as models must integrate textual semantics with relational structure without task-specific supervision.While graph neural networks rely on fixed label spaces and supervised objectives, recent large language model (LLM)-based approaches often overlook graph context or depend on distillation from larger models, limiting generalisation.We propose TRN-R1-Zero, a post-training framework for TRN reasoning trained solely via reinforcement learning.TRN-R1-Zero directly optimises base LLMs using a Neighbour-aware Group Relative Policy Optimisation objective that dynamically adjusts rewards based on a novel margin gain metric for the informativeness of neighbouring signals, effectively guiding the model toward relational reasoning.Unlike prior methods, TRN-R1-Zero requires no supervised fine-tuning or chain-of-thought data generated from large reasoning models.Extensive experiments across citation, hyperlink, social and co-purchase TRN benchmarks demonstrate the superiority and robustness of TRN-R1-Zero.Moreover, relying strictly on node-level training, TRN-R1-Zero achieves zero-shot inference on edgeand graph-level tasks, extending beyond crossdomain transfer.
Authors: Yilun Liu, Ruihong Qiu, Zi Huang
Institution: The University of Queensland
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166880989