OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets

• URL: http://arxiv.org/abs/2609.00015v2
• Date: Wed, 02 Sep 2026 05:03:22 GMT
• Title: OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets
• Abstract summary: We present OpenAgentFlow, a control-plane/action-plane architecture that establishes the action-commit boundary as a shared enforcement interface.<n> GUI, API, tool, and LLM-generated actions are normalized into a common AgentEvent stream and mediated by a shared pre-execution Policy Enforcement Point.<n>This provides a common governance layer across incompatible executors and allows new policies to take effect without modifying agents, prompts, models, or execution paths.
• Score: 30.42587289236515
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI agents powered by large language models are evolving from isolated assistants into heterogeneous systems in which multiple agents, planners, tools, and execution backends operate over shared environments. In such settings, safety becomes a system-level action-governance problem: deciding whether a pending action should be committed given policy-relevant state accumulated across a session. Existing safeguards operate at fragmented boundaries, making it difficult to enforce shared policies over composed action flows across heterogeneous execution paths. We present OpenAgentFlow, a control-plane/action-plane architecture that establishes the action-commit boundary as a shared enforcement interface. GUI, API, tool, and LLM-generated actions are normalized into a common AgentEvent stream and mediated by a shared pre-execution Policy Enforcement Point, while provenance, session state, audit evidence, and updatable policies are maintained outside individual agents. This provides a common governance layer across incompatible executors and allows new policies to take effect without modifying agents, prompts, models, or execution paths. We evaluate OpenAgentFlow through complementary system evaluations spanning controlled action-flow tests, a public external benchmark, policy updates, and real Android execution. On a 300-case controlled suite, OpenAgentFlow achieves 94.00% accuracy and a 95.35% attack-block rate. On the complete 1,220-case AgentDojo-Traj split of TS-Bench, it achieves 97.62% accuracy, 96.59% unsafe-action recall, and a 1.96% safe false-intervention rate. New control-plane rules take effect without modifying protected agents, and the same enforcement path operates across live GUI, API/tool, and LLM-planned Android execution. These results show that a shared action-commit boundary provides a practical basis for system-wide governance across heterogeneous agent execution paths.

Related papers

• HazardAuditor: From Executable Threats to Safer Computer-Use Agents [50.06351661912873]
  Existing guard models target static prompts and responses.<n>Existing safety platforms produce evaluation verdicts rather than the normalized supervision a guard model needs to learn.<n>We introduce HazardAuditor, an execution-grounded framework that closes both gaps.
  arXiv  Detail & Related papers  (2026-09-14T07:09:33Z)
• EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents [56.25120535601186]
  Vision-language-action (VLA) models map visual observations and language instructions directly to robot actions.<n>We propose EmbodiedSkills, a framework that treats each skill decision as an execution proposal.<n>A shared executable-skill interface connects high-level skill selection, bounded low-level VLA execution, and post-action verification.
  arXiv  Detail & Related papers  (2026-09-01T14:14:47Z)
• LMSM: LLM Security Framework Inspired by Linux Security Modules [56.93644694627783]
  Large language models (LLMs) are increasingly deployed with layered defenses, yet malicious prompts can still bypass them.<n>We present Language Model Security Modules (LMSM), a security framework that adapts the separation behind Linux Security Modules (LSM) to LLM serving.
  arXiv  Detail & Related papers  (2026-08-26T12:13:05Z)
• AgentFlow: A Flow-Centric Policy Language and Framework for Securing LLM Agent Systems [7.734540679538682]
  LLM agents increasingly read untrusted content, invoke external tools, access private data, and delegate work to other agents.<n>We present AgentFlow, a flow-centric policy language and runtime enforcement model for specifying where data may travel in agent systems.
  arXiv  Detail & Related papers  (2026-08-24T06:56:00Z)
• Permission Denied: Policy-Graded Evaluation of Coding Agents in Hardened Environments [0.0]
  We evaluate 12 coding agents on Terminal-Bench 2.1 across nested security policy levels derived from common real-world enterprise restrictions.<n>We characterize how agents behave when policy blocks their actions and decompose the failures hardening.<n>We release Boundary-Bench, an open-source hardening plugin enabling policy-constrained evaluation of coding agents.
  arXiv  Detail & Related papers  (2026-08-02T14:26:12Z)
• PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution [49.776611937968]
  We present PhyAgentOS, a foundation delivering scheduling, verification, memory, benchmarking, and safety as system-level services.<n>Its Session-Centered treats a session, not an action, as the minimum unit of scheduling, compatibility, supervised execution, evidence collection, and acceptance.<n>SessionVerifier distinguishes execution termination from semantic task completion via evidence-grounded verdicts of success, failure, or replan.<n> Benchmarking reuses the deployment session and verification path, so results trace to real execution.
  arXiv  Detail & Related papers  (2026-07-18T04:46:53Z)
• Governance by Construction for Generalist Agents [7.48004748585128]
  This demo presents CUGA's policy system, a modular policy-as-code layer that composes with a generalist agent to deliver predictable, auditable, and compliance-aware behavior.<n>We present a governance architecture that enforces policy interventions at every critical stage of execution.
  arXiv  Detail & Related papers  (2026-05-20T08:13:16Z)
• AgentWall: A Runtime Safety Layer for Local AI Agents [0.0]
  AgentWall is a runtime safety and observability layer for local AI agents.<n>It intercepts every proposed agent action before it reaches the host environment, evaluates it against an explicit declarative policy, requires human approval for sensitive operations, and records a complete execution trail for audit and replay.<n>We present the design, architecture, threat model, and policy model of AgentWall, and demonstrate 92.9% policy enforcement accuracy with sub-millisecond overhead across 14 benchmark tests.
  arXiv  Detail & Related papers  (2026-03-24T11:39:35Z)
• Autonomous Action Runtime Management(AARM):A System Specification for Securing AI-Driven Actions at Runtime [0.0]
  This paper introduces Autonomous Action Management (AARM), an open specification for securing AI-driven actions at runtime.<n>AARM intercepts actions before execution, accumulates session context, evaluates against policy and intent alignment, enforces authorization decisions, and records tamper-evident receipts for forensic reconstruction.<n>AARM is model-agnostic, framework-agnostic, and vendor-neutral, treating action execution as the stable security boundary.
  arXiv  Detail & Related papers  (2026-02-10T05:57:30Z)
• DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents [52.92354372596197]
  Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities.<n>This interaction also introduces the risk of prompt injection attacks, where malicious inputs from external sources can mislead the agent's behavior.<n>We propose a Dynamic Rule-based Isolation Framework for Trustworthy agentic systems, which enforces both control and data-level constraints.
  arXiv  Detail & Related papers  (2025-06-13T05:01:09Z)
• Progent: Programmable Privilege Control for LLM Agents [46.31581986508561]
  We introduce Progent, the first privilege control framework to secure Large Language Models agents.<n>Progent enforces security at the tool level by restricting agents to performing tool calls necessary for user tasks while blocking potentially malicious ones.<n>Thanks to our modular design, integrating Progent does not alter agent internals and only requires minimal changes to the existing agent implementation.
  arXiv  Detail & Related papers  (2025-04-16T01:58:40Z)
• Distributed-Training-and-Execution Multi-Agent Reinforcement Learning for Power Control in HetNet [48.96004919910818]
  We propose a multi-agent deep reinforcement learning (MADRL) based power control scheme for the HetNet. To promote cooperation among agents, we develop a penalty-based Q learning (PQL) algorithm for MADRL systems. In this way, an agent's policy can be learned by other agents more easily, resulting in a more efficient collaboration process.
  arXiv  Detail & Related papers  (2022-12-15T17:01:56Z)

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.