AgentGuard: An Attribute-Based Access Control Framework for Tool-Use LLM-Based Agent

Jiaqi Luo^*, Songyang Peng^*, Jiarun Dai, Zhile Chen, Zhuoxiang Shen, Geng Hong, Xudong Pan, Yuan Zhang, Min Yang.

Stay tunned.

Amour: A Latent Dynamical System for Controllable and Stateful Social Interaction in LLMs

Songyang Peng, Ruoyu Fang, Xinfeng Yuan, Haidong Zheng, Zesong Yang, Ruijie Wang, Hongze Mi, Yilan Guo, Linxiao Zhou.

KDD 2026 Workshop on SciSoc Agents & LLMs (Oral); manuscript under review.

Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution

Hongze Mi, Yibo Feng, WenJie Lu, Song Cao, Jinyuan Li, Yanming Li, Xuelin Zhang, Haotian Luo, Songyang Peng, He Cui, Tengfei Tian, Jun Fang, Hua Chai, Naiqiang Tan.

In Proceedings of the International Conference on Machine Learning (ICML), 2026.

Autonomy Comes with Costs: Detecting Denial-of-Service Vulnerabilities Caused by Resource Abusing in LLM-based Agents

Jiaqi Luo, Jiarun Dai, Fengyu Liu, Songyang Peng, Youkun Shi, Tong Bu, Geng Hong, Xudong Pan, Yuan Zhang.

In Proceedings of the 35th USENIX Security Symposium (USENIX Security), Baltimore, MD, USA, August 12-14, 2026.

APSFUZZ: Simulation-Based Fuzzing Testing for Automated Parking Systems

Tong Bu, Jiarun Dai, Jiaqi Luo, Songyang Peng, Zongan Huang, Min Yang.

In Proceedings of the 3rd USENIX Symposium on Vehicle Security and Privacy (VehicleSec), 2025, pages 289-296.

BHUNTER: Generating Blind-Spot Driving Scenarios for Robustness Testing of Perception Systems

Songyang Peng, Jiarun Dai, Yanghao Lv, Jiaqi Luo, Zongan Huang, Yuan Zhang, Min Yang.

ACM Transactions on Software Engineering and Methodology (TOSEM), major revision.

Facilitating Logical Flaw Detection for Autonomous Driving Systems through LLM-Empowered Oracle Generation

Zongan Huang, Jiarun Dai, Jiaqi Luo, Qifan Xiao, Songyang Peng, Xudong Pan, Yuan Zhang, Min Yang.

IEEE Transactions on Information Forensics and Security (TIFS), major revision.