Visibility into AI Agents
Прозрачность в отношении ИИ-агентов
2024-06-03
SCID: 54.1/guqhbrpr
Discuss with AI
AI agent governanceAI agentsactivity loggingagent identifiersreal-time monitoring
Figures from the paper
Abstract (AI)
Increased delegation of commercial, scientific, governmental, and personal activities to AI agents—systems capable of pursuing complex goals with limited supervision—may exacerbate existing societal risks and introduce new risks. Understanding and mitigating these risks involves critically evaluating existing governance structures, revising and adapting these structures where needed, and ensuring accountability of key stakeholders. Information about where, why, how, and by whom certain AI agents are used, which we refer to as visibility, is critical to these objectives. In this paper, we assess three categories of measures to increase visibility into AI agents: agent identifiers, real-time monitoring, and activity logging. For each, we outline potential implementations that vary in intrusiveness and informativeness. We analyze how the measures apply across a spectrum of centralized through decentralized deployment contexts, accounting for various actors in the supply chain including hardware and software service providers. Finally, we discuss the implications of our measures for privacy and concentration of power. Further work into understanding the measures and mitigating their negative impacts can help to build a foundation for the governance of AI agents.
Key Findings
1
Each measure can be implemented with differing levels of intrusiveness and informativeness, creating distinct governance and privacy trade-offs.
2
Improving visibility may create privacy risks and concentrate power, requiring further research to mitigate these negative impacts.
3
The applicability of visibility measures varies across centralized and decentralized deployments and involves multiple hardware and software supply-chain actors.
4
The paper assesses three visibility measures for AI agents: agent identifiers, real-time monitoring, and activity logging.
5
Visibility into where, why, how, and by whom AI agents are used is critical for evaluating governance, accountability, and societal risks.
Research Object
AI agents (systems capable of pursuing complex goals with limited supervision)
Research Subject
Measures for increasing visibility into AI agents, including agent identifiers, real-time monitoring, and activity logging, and their implications for privacy and concentration of power
Publication Details
Publication Date
2024-06-03
Journal
Publisher
ISSN
Cited by
298
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai9
A survey on large language model based autonomous agents2024
Automation and New Tasks: How Technology Displaces and Reinstates Labor2019
Generative Agents: Interactive Simulacra of Human Behavior2023
GPT-4 Technical Report2023
Scaling Laws for Neural Language Models2020
Autonomous chemical research with large language models2023
Augmenting large language models with chemistry tools2024
Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction2023
Application of LLM Agents in Recruitment: A Novel Framework for Automated Resume Screening2024
Cited by11
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges2025
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges2025
Agentic AI: a comprehensive survey of architectures, applications, and future directions2025
AI Agents and Agentic Systems: A Multi-Expert Analysis2025
TRiSM for Agentic AI: A review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems2026
AgentAI: A comprehensive survey on autonomous agents in distributed AI for industry 4.02025
Agentic AI Frameworks in SMMEs: A Systematic Literature Review of Ecosystemic Interconnected Agents2025
Agentic AI in Healthcare: Opportunities, Challenges, and Future Directions2026
Toward Sustainable Agentic AI Systems: A Survey of Architectures and Methodologies2026
The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems2026
Orchestrating Autonomy: Patterns, Protocols, and Governance for Enterprise Agentic AI2025