Why Self Modifying or Self Extending Agents Are CG Inadmissible
Abstract
This paper demonstrates that self-modifying or self-extending agents are categorically inadmissible (CG-inadmissible) under standing conservation and fail-closed evaluation. By exhaustion, any agent that attempts to alter its own constraint structure, extend its scope, or recursively generate new capacities necessarily performs illicit scope transport and incurs terminal standing failure. The argument is purely negative and structural: it does not propose agent designs, control strategies, or containment mechanisms. The treatment is declarative and non-procedural, placing on record that admissible agency is necessarily bounded and that self-modification claims are incompatible with legitimacy.
Fields of Study & Subjects
Ethics and Social Impacts of AI
Psychiatry
Mental Health
Neuroscience
Multi-Agent Systems and Negotiation
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 8 February 2026