# Behavioral Governance for Autonomous AI Agents: The AgentBound Framework

arXiv: https://arxiv.org/abs/2606.30970 · HTML: https://mlsanity.com/paper/2606.30970/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 16 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 12 of 12)

- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [Cedar: A New Language for Expressive, Fast, Safe, and Analyzable Authorization (Extended Version)](https://mlsanity.com/paper/2403.04651/) (2024)
- [Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents](https://mlsanity.com/paper/2602.22302/) (2026)
- [Agent Contracts: A Formal Framework for Resource-Bounded Autonomous AI Systems](https://mlsanity.com/paper/2601.08815/) (2026)
- [Auditable Agents](https://mlsanity.com/paper/2604.05485/) (2026)
- [Right to History: A Sovereignty Kernel for Verifiable AI Agent Execution](https://mlsanity.com/paper/2602.20214/) (2026)
- [HDP: A Lightweight Cryptographic Protocol for Human Delegation Provenance in Agentic AI Systems](https://mlsanity.com/paper/2604.04522/) (2026)
- [Governance of Autonomous Agents on the Web: Challenges and Opportunities](https://mlsanity.com/paper/2202.02574/) (2022)
- [MAC: Multi-Agent Constitution Learning](https://mlsanity.com/paper/2603.15968/) (2026)
- [Aegon: Auditable AI Content Access with Ledger-Bound Tokens and Hardware-Attested Mobile Receipts](https://mlsanity.com/paper/2604.06693/) (2026)
- [Building the Web for Agents: A Declarative Framework for Agent-Web Interaction](https://mlsanity.com/paper/2511.11287/) (2025)

## Built on by (most cited first, 1 of 1)

- [Fault-Tolerant Budget Conservation in Distributed Multi-Agent Delegation](https://mlsanity.com/paper/2610.00349/) (2026)

## Abstract (arXiv)

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.