Skip to content

Agent-native applications: a new application paradigm

Agent-Native Applications: A New Application Paradigm

arXiv: 其他 AI 安全论文· arXiv:2611.23243· David Luo, Alberto Leon-Garcia·Indexed by this site · 13 hr ago· Originally publishedDefenses· Its place in the scan record →
AI summary

The paper proposes a new paradigm, "agent-native applications": LLM agents take on the application's core logic and, after authorization, can adjust the application graph at runtime. The architecture represents the application as a portable graph of agents, tools, data sources, and human-in-the-loop checkpoints, and constrains authorized behavior with a behavioral envelope in a declarative specification. At runtime, the application orchestrator serves as the control plane and the agent mesh as the data plane and generates audit events; an executable ANR prototype demonstrates some of the core mechanisms.

Read originalarxiv.org