Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems
This paper proposes a governance model for autonomous AI agents that does not monitor their reasoning but requires independently attested evidence at the point of high-risk actions. The agent retains autonomy over planning and reasoning, but execution of designated high-risk actions is conditional on preconditions attested by separate authoritative sources, cryptographically bound to a declared intent, and evaluated by a deterministic policy. Decisions are recorded in a tamper-evident log. A proof-of-concept implementation is presented with examples from software deployment and clinical prescribing.
[2606.26298] Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems
[Submitted on 24 Jun 2026]
Title:Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems
View a PDF of the paper titled Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems, by Jakob Salfeld-Nebgen
View PDF HTML (experimental)
Abstract:Autonomous AI agents may begin to perform consequential, irreversible actions such as clinical prescribing and production software deployment. This paper observes that human institutions have governed powerful autonomous actors not by monitoring their reasoning but by requiring independently attested evidence at the point of consequential action. We formalise this institutional pattern as a computational governance model for AI agent systems. Under the proposed model, an agent retains full autonomy over planning and reasoning but holds no execution authority over designated high-risk actions. Execution is conditional on preconditions that are each independently attested by a separate authoritative source, cryptographically bound to a declared intent, and evaluated by a deterministic policy. Decisions are recorded in a tamper-evident log amenable to independent re-verification. We present a proof-of-concept implementation and illustrate the model with examples from software deployment and clinical prescribing.
Subjects:
Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
Cite as: arXiv:2606.26298 [cs.AI]
(or arXiv:2606.26298v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.26298
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Jakob Salfeld-Nebgen [view email] [v1] Wed, 24 Jun 2026 18:43:00 UTC (63 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems, by Jakob Salfeld-Nebgen
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-06
Change to browse by:
cs cs.CR
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
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.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)