Beyond Autonomy: A Dynamic Tiered AgentRunner Framework for Governable and Resilient Enterprise AI Execution
On the map: LLM agents and tool use → Agent threats, guardrails and governance
Abstract (arXiv)
Current large language model agent frameworks prioritize autonomy but lack the governability mechanisms required for enterprise deployment. High-risk write operations proceed without independent review, complex tasks lack acceptance verification, and computational resources are allocated uniformly regardless of risk level. We propose the Dynamic Tiered AgentRunner, a controlled execution protocol distilled from a production-grade multi-tenant SaaS platform. The framework introduces three core mechanisms: (1) Risk-Adaptive Tiering that dynamically allocates computational resources and review intensity based on task risk profiles, achieving Pareto-optimal trade-offs between safety and efficiency; (2) Separation of Powers architecture where proposal, review, execution, and verification are performed by independent agents with physically isolated boundaries; and (3) Resilience-by-Design through a Verifier-Recovery closed loop that treats failure as a first-class system state. We formalize the tier selectio
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 18 of its 29 references that are in the map. First posted on arXiv 11 May 2026.
Builds on
18 of 29 references.
Closest ancestors · 2
Same direction, newest first
- 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agents18 Jan
- 2023Identifying the Risks of LM Agents with an LM-Emulated Sandbox25 Sep
Other references · 16
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
- 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
- 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
- 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
- 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
- 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
- 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
4 more
- 2023AgentBench: Evaluating LLMs as Agentscited by 1,267
- 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
- 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 574
- 2023TaskWeaver: A Code-First Agent Frameworkcited by 86
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026A Policy Algebra for Trust-Preserving Agentic AI Execution
- 2026The CASE Framework: A Multi-Disciplinary Control Architecture for Governing Enterprise Agentic AI
- 2026Governing the Agentic Enterprise: A Governance Maturity Model for Managing AI Agent Sprawl in Business Operations
- 2026Separating Capability from Permission: A Governance Framework for Agentic AI Autonomy Levels
- 2025Beyond Accuracy: A Multi-Dimensional Framework for Evaluating Enterprise Agentic AI Systems
- 2026A Contract-Centered Architecture for Scalable and Manageable Agentic Runtimes
- 2026Governed Memory: A Production Architecture for Multi-Agent Workflows
- 2026POLARIS: Typed Planning and Governed Execution for Agentic AI in Back-Office Automation