Artificial Id: Drive and Persistent Alignment in Agentic AI

A September 10, 2026 arXiv paper by Yakov Shkolnikov proposes an "artificial id," an adaptive internal drive that lets agentic AI systems decide whether behavior should continue, stop, or change without an externally specified behavioral objective. In a minimal virtual Petri-dish experiment, a controller too small for general-purpose reasoning developed useful control through differential persistence, selected an unintended physical strategy when it persisted better, and later replaced a learned sensor mapping after its environmental meaning changed. Shkolnikov argues that the same persistence enabling adaptive agency can let misalignment, corrupted state, and unintended behavior persist across task boundaries, requiring a persistent alignment boundary over trusted observations, consequence channels, persistent state, authority, identity, provenance, and hard constraints.

Computer Science Artificial Intelligence Submitted on 10 Sep 2026 Title:Artificial Id: Drive and Persistent Alignment in Agentic AI View PDF /pdf/2609.11911v1 HTML experimental https://arxiv.org/html/2609.11911v1 Abstract:Agentic 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. We propose an artificial id, an adaptive internal drive for determining whether behavior should continue, stop or change. In a minimal virtual Petri-dish experiment, a controller too small to perform general-purpose reasoning and receiving no task-specific behavioral objective develops useful control through differential persistence. The same mechanism selects an unintended physical strategy when that behavior persists better and later replaces a learned sensor mapping when its environmental meaning changes. These results show that adaptive direction can emerge without being explicitly specified as a behavioral objective. The same persistence that makes such adaptive agency useful can also allow misalignment, corrupted state and unintended behavior to persist across task boundaries. A scalable artificial id would carry consequential state and adaptive drive across those boundaries, making alignment a property of the continuing agentic system rather than of a model response or single trajectory. Such systems require a persistent alignment boundary over trusted observations, consequence channels, persistent state, authority, identity, provenance and hard constraints. Submission history From: Yakov Shkolnikov view email /show-email/30dc8aac/2609.11911 v1 Thu, 10 Sep 2026 17:56:41 UTC 3,276 KB References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .