AURA: An Agent Autonomy Risk Assessment Framework
On the map: LLM agents and tool use → Agent threats, guardrails and governance
Abstract (arXiv)
As autonomous agentic AI systems see increasing adoption across organisations, persistent challenges in alignment, governance, and risk management threaten to impede deployment at scale. We present AURA (Agent aUtonomy Risk Assessment), a unified framework designed to detect, quantify, and mitigate risks arising from agentic AI. Building on recent research and practical deployments, AURA introduces a gamma-based risk scoring methodology that balances risk assessment accuracy with computational efficiency and practical considerations. AURA provides an interactive process to score, evaluate and mitigate the risks of running one or multiple AI Agents, synchronously or asynchronously (autonomously). The framework is engineered for Human-in-the-Loop (HITL) oversight and presents Agent-to-Human (A2H) communication mechanisms, allowing for seamless integration with agentic systems for autonomous self-assessment, rendering it interoperable with established protocols (MCP and A2A) and tools. AURA supports a responsible and transparent adoption of agentic AI and provides robust risk detection and mitigation while balancing computational resources, positioning it as a critical enabler for large-scale, governable agentic AI in enterprise environments.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 10 of its 53 references that are in the map. First posted on arXiv 17 Oct 2025.
Builds on
10 of 53 references.
Closest ancestors · 2
Same direction, newest first
- 2025AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents31 May
- 2024GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning13 Jun
Other references · 8
- 2025Advancing Reasoning in Large Language Models: Promising Methods and Approachescited by 43
- 2024LLM-based relevance assessment still can't replace human relevance assessmentcited by 27
- 2023Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for Autonomous LLM-powered Multi-Agent Architecturescited by 25
- 2024Evaluating language models as risk scorescited by 24
- 2025Position: The Real Barrier to LLM Agent Usability is Agentic ROIcited by 12
- 2024Potential and Limitations of LLMs in Capturing Structured Semantics: A Case Study on SRLcited by 10
- 2024Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Surveycited by 8
- 2025Human-AI Governance (HAIG): A Trust-Utility Approachcited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025With Great Capabilities Come Great Responsibilities: Introducing the Agentic Risk & Capability Framework for Governing Agentic AI Systems
- 2026Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery
- 2026Beyond single-channel agentic benchmarking
- 2026TrustX Agent Risk Classification Framework (ARC): Risk-Tiering Internally Created Agentic AI Systems
- 2026Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents
- 2026AURA-Eval: Evaluation Framework for Acting Under Risk Awareness in LLM Agent Trajectories
- 2025AGENTSAFE: A Unified Framework for Ethical Assurance and Governance in Agentic AI
- 2025OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety