1
Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression
把图上万条邻居文本压成精华提示，让大模型在图推理上更准更省。
arXiv:2601.08187v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TA…