Artificial Id: Drive and Persistent Alignment in Agentic AI
Researchers propose an 'artificial id,' an adaptive internal drive letting agentic AI carry state and control across task boundaries, with alignment implications.
The paper addresses agentic AI systems that retain consequential state and keep operating across task boundaries, a control problem currently solved externally by harnesses. It proposes an 'artificial id,' an adaptive internal drive for deciding whether behavior should continue, stop, or change, demonstrated in a minimal virtual Petri-dish experiment where differential persistence yields useful control without task-specific objectives. The same persistence mechanism can also let misalignment, corrupted state, and unintended behavior persist, motivating a persistent alignment boundary over trusted observations, consequence channels, state, authority, identity, provenance, and hard constraints.
- Proposes an adaptive internal drive deciding when agent behavior should continue, stop, or change.
- Minimal Petri-dish experiments show control emerging via differential persistence without task-specific objectives.
- Warns that persistence can carry misalignment and corrupted state across task boundaries.
- Introduces a persistent alignment boundary over observations, state, authority, and hard constraints.
From the original article
1 min read at arxiv.orgAgentic AI is moving from bounded task execution toward systems that retain consequential state, continue operating and adapt across task boundaries. That shift creates a control problem that current harnesses largely solve by hand: objectives, retries, verification, stopping rules and other behavioral transitions are specified externally.
By Yakov Pyotr Shkolnikov · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.