Behavioral Governance for Autonomous AI Agents: The AgentBound Framework

• URL: http://arxiv.org/abs/2606.30970v2
• Date: Wed, 01 Jul 2026 18:23:51 GMT
• Title: Behavioral Governance for Autonomous AI Agents: The AgentBound Framework
• Abstract summary: We present AgentBound, a runtime governance framework that provides verifiable behavioral oversight for autonomous AI agents.<n>AgentBound evaluates each proposed action using three independent authorities: delegated authorization, owner-signed behavioral constitutions, and site action contracts.<n>AgentBound generates cryptographically verifiable governance receipts that bind every action to the exact delegation, policy, and semantic artifacts governing the decision.
• Score: 2.4469484645516832
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous AI agents increasingly perform consequential actions on behalf of human principals, including financial transactions, external communications, and enterprise workflows. Existing agent infrastructure relies on identity federation and delegated authorization to authenticate workloads and control resource access, but it cannot determine whether an authorized action should be executed under the current behavioral and operational context. We present AgentBound, a runtime governance framework that provides verifiable behavioral oversight for autonomous AI agents. AgentBound evaluates each proposed action using three independent authorities: delegated authorization, owner-signed behavioral constitutions, and site action contracts. Their judgments are conservatively composed through a formal decision model to determine whether an action should be permitted, reviewed, or denied before execution. To provide accountability, AgentBound generates cryptographically verifiable governance receipts that bind every action to the exact delegation, policy, and semantic artifacts governing the decision, enabling independent replay verification and policy provenance. The framework also introduces standing delegation for long-running agents, allowing periodic workloads to operate under continuously refreshed governance policies while preserving revocability and bounded authority. We present the formal foundation, system architecture, governance receipt protocol, and AgentBound-Bench, a benchmark framework for evaluating governance correctness, authority composition, and accountability. Rather than replacing model alignment, AgentBound complements it by providing a deterministic governance layer between authorization and execution, transforming governance from a process that must be trusted into one that can be independently verified.

Related papers

• When Intelligence Becomes Agency: A Theory of Governed, Proactive Agency for Symbiotic AI Systems [0.0]
  Persistent AI assistants are intended to extend human attention, memory, and coordination across changing digital and physical environments.<n>They must decide on their own whether a situation warrants behavior at all, when it does and in what mode.<n>This paper develops a conceptual and formal framework for governed proactive agency.
  arXiv  Detail & Related papers  (2026-09-07T16:46:38Z)
• EMERGE-Policy: A Robot Mind Emerges Beyond a Single Policy [48.898967774856466]
  EMERGE-Policy coordinates both capability invocation and information exchange.<n>Main Agent retains task-level state within an active context window.<n>Role-specific Sub Agents process perception, execution monitoring, verification, and memory consolidation.
  arXiv  Detail & Related papers  (2026-08-30T16:46:06Z)
• The Authority Resolution Framework: A Five-Domain Ontology for Governing Who and What Decides, at Scale [0.0]
  This paper introduces the Authority Resolution Framework (ARF), a five-domain ontology for representing and resolving authority.<n>ARF defines the Authority Relation (AR) as a cross-domain primitive binding an actor, action, object, bounded context, justification chain, and a calibration measure.<n>ARF is designed to support AI agents in determining the provenance, scope and contextual validity of authority before executing consequential actions.
  arXiv  Detail & Related papers  (2026-08-16T16:05:50Z)
• Mandato: Protocol-Level Enforcement of Digitally Signed Mandates on AI Agent Actions with Cryptographically Chained Audit Trails [0.0]
  We present Mandato, a governance proxy that enforces digitally signed mandates on agent actions at the protocol level.<n>A mandate is a machine-readable, cryptographically signed authorization artifact specifying which tools an agent may invoke.<n>We describe the implementation status of the reference system and a quantitative evaluation plan covering enforcement overhead, audit completeness, and tamper-evidence verification cost.
  arXiv  Detail & Related papers  (2026-08-14T08:33:43Z)
• 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)
• Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels [53.63220028820581]
  Embodied intelligence integrates learned perception and decision making with real-time computation, control, and physical interaction.<n>We define trustworthy embodied intelligence as the sustained capacity to execute specified tasks reliably.
  arXiv  Detail & Related papers  (2026-07-28T17:50:44Z)
• Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI [5.459755757192724]
  This paper proposes a compositional governance framework for agentic AI systems.<n>We define types of delegation and their permissions and accountability implications.<n>It provides a formal yet practical foundation for accountable authorization in agentic AI systems.
  arXiv  Detail & Related papers  (2026-06-02T11:39:39Z)
• 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)
• Think Before You Act -- A Neurocognitive Governance Model for Autonomous AI Agents [4.064061517379954]
  The rapid deployment of autonomous AI agents across enterprise, healthcare, and safety-critical environments has created a fundamental governance gap.<n>We address this gap by drawing on how humans self-govern naturally: before acting, humans engage deliberate cognitive processes grounded in executive function.<n>This paper proposes a neurocognitive governance framework that formally maps this human self-governance process to agent reasoning.
  arXiv  Detail & Related papers  (2026-04-28T14:15:20Z)
• PolicyBank: Evolving Policy Understanding for LLM Agents [51.86716874651299]
  PolicyBank maintains structured, tool-level policy insights and iteratively refines them.<n>PolicyBank closes up to 82% of the gap toward a human oracle.
  arXiv  Detail & Related papers  (2026-04-16T20:29:30Z)
• ClawLess: A Security Model of AI Agents [34.70695138834452]
  We present ClawLess, a security framework that enforces formally verified policies on AI agents.<n>ClawLess formalizes a fine-grained security model over system entities, trust scopes, and permissions.<n>This approach bridges the formal security model with practical enforcement, ensuring security regardless of the agent's internal design.
  arXiv  Detail & Related papers  (2026-04-07T12:19:55Z)
• Agent Control Protocol: Admission Control for Agent Actions [0.4929694290403903]
  Agent Control Protocol (ACP) is a formal specification for admission control governance of autonomous agents in B2B institutional environments.<n>ACP defines cryptographic identity, capability-based authorization, deterministic risk evaluation, chained delegation, and cryptographically-chained auditing.<n>ACP operates on top of RBAC and Zero Trust, addressing what neither model solves.
  arXiv  Detail & Related papers  (2026-03-19T12:28:28Z)
• Faramesh: A Protocol-Agnostic Execution Control Plane for Autonomous Agent Systems [0.0]
  Faramesh is a protocol-agnostic execution control plane that enforces execution-time authorization for agent-driven actions.<n>We show how these primitives yield enforceable, predictable governance for autonomous execution.
  arXiv  Detail & Related papers  (2026-01-25T08:27:27Z)
• Binding Agent ID: Unleashing the Power of AI Agents with accountability and credibility [46.323590135279126]
  BAID (Binding Agent ID) is a comprehensive identity infrastructure establishing verifiable user-code binding.<n>We implement and evaluate a complete prototype system, demonstrating the practical feasibility of blockchain-based identity management and zkVM-based authentication protocol.
  arXiv  Detail & Related papers  (2025-12-19T13:01:54Z)
• AI Agents with Decentralized Identifiers and Verifiable Credentials [32.505127447635864]
  This article presents a prototypical multi-agent system, where each agent is endowed with a self-sovereign digital identity.<n>It combines a unique and ledger-anchored Decentralized Identifier (DID) of an agent with a set of third-party issued Verifiable Credentials (VCs)<n>It enables agents at the start of a dialog to prove ownership of their self-controlled DIDs for authentication purposes and to establish various cross-domain trust relationships.
  arXiv  Detail & Related papers  (2025-10-01T08:10:37Z)
• 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)
• SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints [59.645885492637845]
  SOPBench is an evaluation pipeline that transforms each service-specific SOP code program into a directed graph of executable functions.<n>Our approach transforms each service-specific SOP code program into a directed graph of executable functions and requires agents to call these functions based on natural language SOP descriptions.<n>We evaluate 18 leading models, and results show the task is challenging even for top-tier models.
  arXiv  Detail & Related papers  (2025-03-11T17:53:02Z)

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.