2 papers
cs.CR2026
EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents
Shiyi Kuang, Xuemei Luo, Kun Liu +7
Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resources. Existing benchmarks leave ga…
cs.AI2026
Agent-Native Immune System: Architecture, Taxonomy, and Engineering
Bo Shen, Lifeng Chang, Tianyuan Wei +7
The transition from static chat bots to autonomous agents--equipped with persistent memory, tool-use protocols, and multi-agent collaboration--has fundamentally expanded the AI thr…