6 papers
Constraint-Aware Corrective Memory for Language-Based Drug Discovery Agents
Maochen Sun, Youzhi Zhang, Gaofeng Meng
Large language models are making autonomous drug discovery agents increasingly feasible, but reliable success in this setting is not determined by any single action or molecule. It…
Auditing Cascading Risks in Multi-Agent Systems via Semantic-Geometric Co-evolution
Zixun Luo, Yuhang Fan, Hengyu Lin +2
Large Language model (LLM)-based Multi-Agent Systems (MAS) are prone to cascading risks, where early-stage interactions remain semantically fluent and policy-compliant, yet the und…
Considering the Difference in Utility Functions of Team Players in Adversarial Team Games
Youzhi Zhang
The United Nations' 2030 Agenda for Sustainable Development requires that all countries collaborate to fight adversarial factors to achieve peace and prosperity for humans and the…
AIAuditTrack: A Framework for AI Security system
Zixun Luo, Yuhang Fan, Yufei Li +3
The rapid expansion of AI-driven applications powered by large language models has led to a surge in AI interaction data, raising urgent challenges in security, accountability, and…
Siren: A Learning-Based Multi-Turn Attack Framework for Simulating Real-World Human Jailbreak Behaviors
Yi Zhao, Youzhi Zhang
Large language models (LLMs) are widely used in real-world applications, raising concerns about their safety and trustworthiness. While red-teaming with jailbreak prompts exposes t…
The Docking Game: Loop Self-Play for Fast, Dynamic, and Accurate Prediction of Flexible Protein-Ligand Binding
Youzhi Zhang, Yufei Li, Gaofeng Meng +2
Molecular docking is a crucial aspect of drug discovery, as it predicts the binding interactions between small-molecule ligands and protein pockets. However, current multi-task lea…