InfoResearchPeer-reviewedLLM-specific
From model trust to software topology: a Perspective on structurally governed agentic AI systems
- Published
- Record updated
Summary
This Perspective, published in Frontiers in Computer Science on 2026-10-08, argues that agentic AI safety should be treated as a software-architecture problem alongside model alignment and prompt-level defenses. It proposes a five-plane reference topology (intent, orchestration, execution, oversight, adaptation) with the invariant that deciding components should not directly act, and acting components should not act without supervision. The topology is realized in Polos, an open reference specification.