September 2026Unreviewed
Stored Is Not Supported: Typed Provenance and Assertion Guardrails for Persistent AI Agents
Jun He, Deying Yu
Abstract
Persistent AI agents construct autobiographical state through reflection, retrieval, and consolidation. Persistence changes availability, not epistemic standing: stored or retrieved material is not thereby supported. Untrusted inputs, prompt injections, and model inferences can therefore enter persistent state and later be presented as agent history or user commitments. We specify typed provenance and assertion guardrails for autobiographical assertion boundedness, a system-relative release prop
Categories
Framework mappings
OWASP Top 10 for LLM Applications
- LLM01Prompt Injection
MITRE ATLAS
- AML.T0051LLM Prompt Injection
Suggested from the entry's categories.
Cite
@misc{he2026stored,
title = {{Stored Is Not Supported: Typed Provenance and Assertion Guardrails for Persistent AI Agents}},
author = {Jun He and Deying Yu},
year = {2026},
month = sep,
eprint = {2609.02127},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.02127}
}