Search papers, labs, and topics across Lattice.
TRN-R1-Zero is introduced as a post-training framework for zero-shot reasoning on text-rich networks (TRNs) that directly optimizes base LLMs using reinforcement learning. The method employs a Neighbour-aware Group Relative Policy Optimisation objective, dynamically adjusting rewards based on a margin gain metric for neighboring signal informativeness. Experiments on citation, hyperlink, social, and co-purchase TRNs demonstrate TRN-R1-Zero's superiority and robustness without supervised fine-tuning or chain-of-thought data.
LLMs can learn to reason over complex text-rich networks in a zero-shot manner using reinforcement learning alone, outperforming methods relying on supervised fine-tuning or distillation.
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 edge- and graph-level tasks, extending beyond cross-domain transfer. The codebase is publicly available at https://github.com/superallen13/TRN-R1-Zero.
