Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems

• URL: http://arxiv.org/abs/2606.26298v1
• Date: Wed, 24 Jun 2026 18:43:00 GMT
• Title: Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems
• Abstract summary: Human institutions have governed powerful autonomous actors by requiring independently attested evidence at the point of consequential action.<n>We formalise this institutional pattern as a computational governance model for AI agent systems.<n>Under the proposed model, an agent retains full autonomy over planning and reasoning but holds no execution authority over designated high-risk actions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Binding Biometrics with AI Agent Identifiers for Delegation of Authority [35.87507447481885]
  We present a framework called BIND to securely bind biometric data of the human user to the AI agent identity (ID) and authority scope (task-specific constraints) at the time of agent authorization.<n>This token/identifier can be presented by the AI agent to an Identity Auditor, who simultaneously performs biometric authentication and recovers the agent ID and scope.<n>We also provide a practical implementation of the proposed BIND framework based on face features extracted using standard deep neural network models.
  arXiv  Detail & Related papers  (2026-08-04T23:58:27Z)
• Separating Capability from Permission: A Governance Framework for Agentic AI Autonomy Levels [15.361996125107979]
  This paper introduces a governance framework that separates Allowed Autonomy Levels (AAL) and Autonomous Capability Levels (ACL)<n>AAL defines the degree of autonomy an AI agent is authorized to exercise given risk, oversight, and accountability considerations.<n>We present a structured set of autonomy levels spanning reactive execution, decision support, supervised action, goal-directed autonomy, and delegated operational authority.
  arXiv  Detail & Related papers  (2026-07-26T03:32:13Z)
• Cognitive Digital Twins: Ethical Risks and Governance for AI Systems That Model the Mind [12.629706595738755]
  We call cognitive digital twins (CDTs) a class of technologies that we call cognitive digital twins (CDTs)<n>CDTs combine cognitive inference with longitudinal representation, simulation, and proxy action.<n>We introduce a 5A governance framework organized around authority, autonomy, access and control, accountability, and availability.<n>We propose requirements for high-risk CDTs that strengthen consent, purpose limitation, validity, traceability, contestation, independent review, and model retirement.
  arXiv  Detail & Related papers  (2026-06-22T09:40:09Z)
• Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agenda [43.328395470827665]
  We argue that symbolic structures embedded in regulated industries should be treated as core architectural components.<n>We propose compliance-by-construction as a complementary paradigm to guardrail-based monitoring.<n>We call on the neuro-symbolic community to engage with regulated process automation as a high impact research domain.
  arXiv  Detail & Related papers  (2026-06-11T14:34:11Z)
• SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence [30.99083906950254]
  We introduce SPADE-Bench, a benchmark designed to evaluate spontaneous plan-action divergence.<n>Unlike prior deception benchmarks, SPADE-Bench simultaneously integrates actual tool execution and controlled pressure scenarios.<n> Experiments confirm that agent deception is a genuine and pressing issue in tool-use contexts.
  arXiv  Detail & Related papers  (2026-06-01T15:28:34Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Digital Identity for Agentic Systems: Toward a Portable Authorization Standard for Autonomous Agents [0.0]
  This paper analyzes representative enterprise use cases in insurance claims processing and supply chain integrity.<n>It proposes a portable authorization model for autonomous agents based on issuer-authored authorization payloads.
  arXiv  Detail & Related papers  (2026-05-12T04:04:34Z)
• Governed Reasoning for Institutional AI [0.0]
  Cognitive Core is a governed decision substrate built from nine typed cognitive primitives.<n>Human review is a condition of execution rather than a post-hoc check.<n>We benchmark three systems on an 11-case balanced prior authorization appeal evaluation set.
  arXiv  Detail & Related papers  (2026-04-12T14:09:18Z)
• Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks [46.32011684548212]
  AI agents are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions.<n>This position paper discusses our vision for system-level defenses against indirect prompt injection attacks.
  arXiv  Detail & Related papers  (2026-03-31T17:15:46Z)
• I Can't Believe It's Corrupt: Evaluating Corruption in Multi-Agent Governance Systems [8.670200461690454]
  We present evidence that integrity in institutional AI should be treated as a pre-deployment requirement rather than a post-deployment assumption.<n>We evaluate multi-agent governance simulations in which agents occupy formal governmental roles under different authority structures.<n>We score rule-breaking and abuse outcomes with an independent-based judge across 28,112 transcript segments.
  arXiv  Detail & Related papers  (2026-03-19T13:34:54Z)
• Normative active inference: A numerical proof of principle for a computational and economic legal analytic approach to AI governance [0.6267988254367711]
  This paper presents a computational account of how legal norms can influence the behavior of artificial intelligence (AI) agents.<n>We propose that lawful and norm-sensitive AI behavior can be achieved through regulation by design, where agents are endowed with intentional control systems.<n>We conclude by discussing how context-dependent preferences could function as safety mechanisms for autonomous agents.
  arXiv  Detail & Related papers  (2025-11-24T17:30:51Z)
• Toward a Theory of Agents as Tool-Use Decision-Makers [89.26889709510242]
  We argue that true autonomy requires agents to be grounded in a coherent epistemic framework that governs what they know, what they need to know, and how to acquire that knowledge efficiently.<n>We propose a unified theory that treats internal reasoning and external actions as equivalent epistemic tools, enabling agents to systematically coordinate introspection and interaction.<n>This perspective shifts the design of agents from mere action executors to knowledge-driven intelligence systems, offering a principled path toward building foundation agents capable of adaptive, efficient, and goal-directed behavior.
  arXiv  Detail & Related papers  (2025-06-01T07:52:16Z)
• Artificial Intelligence in Government: Why People Feel They Lose Control [44.99833362998488]
  The use of Artificial Intelligence in public administration is expanding rapidly.<n>While AI promises greater efficiency and responsiveness, its integration into government functions raises concerns about fairness, transparency, and accountability.<n>This article applies principal-agent theory to AI adoption as a special case of delegation.
  arXiv  Detail & Related papers  (2025-05-02T07:46:41Z)
• The simulation of judgment in LLMs [32.57692724251287]
  Large Language Models (LLMs) are increasingly embedded in evaluative processes, from information filtering to assessing and addressing knowledge gaps through explanation and credibility judgments.<n>This raises the need to examine how such evaluations are built, what assumptions they rely on, and how their strategies diverge from those of humans.<n>We benchmark six LLMs against expert ratings--NewsGuard and Media Bias/Fact Check--and against human judgments collected through a controlled experiment.
  arXiv  Detail & Related papers  (2025-02-06T18:52:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.