Kexin Chu
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Research Timeline
2026
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
The paper proposes the Layered Attack Surface Model (LASM), a structural taxonomy that maps security threats and defenses across the complex, multi-layered architecture of AI agents, revealing significant gaps in current research.
CoWeaver: A Bi-directional, Learnable and Explainable Matching Engine for Mixed Human-Agent Science Collaboration
The paper proposes COWEAVER, a bidirectional, learnable and explainable algorithm for matching scientists and forming collaborations within a human-agent network.
Highlighted terms show continued research focus across papers
Papers
cs.MAcs.AIcs.CLEmpiricalRecentJul 17, 2026
CoWeaver: A Bi-directional, Learnable and Explainable Matching Engine for Mixed Human-Agent Science Collaboration
Jiayao Gu, Kexin Chu, Peidong Liu, Yue Yang +4 more
The paper proposes COWEAVER, a bidirectional, learnable and explainable algorithm for matching scientists and forming collaborations within a human-agent network.
View →
cs.CRcs.LGRecent