However, the existing method heavily relies on human-annotated agent profiles (e.g., name, age, personality, relationships with others,

Among all MLLMs, proprietary models consistently perform well.

To perform systematic evaluations, we set up 32 various tasks, including improvements to existing multimodal tasks, extension of text-only tasks to multimodal scenarios, and novel methods for risk assessment, which focus on models' basic performance with practical significance.

Graph Neural Networks (GNNs) excel across various applications but remain vulnerable to adversarial attacks, particularly Graph Injection Attacks (GIAs), which inject malicious nodes into the original graph and pose realistic threats.

Intelligent education stands as a prominent application of machine learning.

The emergence of large language models (LLMs) has revolutionized the way we interact with graphs, leading to a new paradigm called GraphLLM.