As one of the most advanced techniques in AI, Retrieval-Augmented Generation (RAG) can
offer reliable and up-to-date external knowledge, providing huge convenience for numerous …

Existing agents based on large language models (LLMs) demonstrate robust problem-
solving capabilities by integrating LLMs' inherent knowledge, strong in-context learning and …

Graph Neural Networks (GNNs) are commonly used and have shown promising
performance in recommendation systems. A major branch, Heterogeneous GNNs, models …

The telecommunications industry is increasingly reliant on human agents to handle complex
customer support inquiries. With the rapid evolution of technologies like 5G and IoT …

As social media has become a predominant mode of communication globally, the rise of
abusive content threatens to undermine civil discourse. Recognizing the critical nature of …

Outline generation aims to reveal the internal structure of a document by identifying
underlying chapter relationships and generating corresponding chapter summaries …

The title of an academic paper encapsulates its core knowledge at a high level, while the
abstract provides a concise summary of the paper's content. Therefore, an automatic title …