mlsanityData to 14 Oct 2026

The AI Agent Index

arXiv 2502.01635 ↗First posted 3 Feb 2025cs.SE cs.AIcited by 15

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

Leading AI developers and startups are increasingly deploying agentic AI systems that can plan and execute complex tasks with limited human involvement. However, there is currently no structured framework for documenting the technical components, intended uses, and safety features of agentic systems. To fill this gap, we introduce the AI Agent Index, the first public database to document information about currently deployed agentic AI systems. For each system that meets the criteria for inclusion in the index, we document the system's components (e.g., base model, reasoning implementation, tool use), application domains (e.g., computer use, software engineering), and risk management practices (e.g., evaluation results, guardrails), based on publicly available information and correspondence with developers. We find that while developers generally provide ample information regarding the capabilities and applications of agentic systems, they currently provide limited information regarding safety and risk management practices. The AI Agent Index is available online at https://aiagentindex.mit.edu/

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 62 of its 101 references that are in the map. First posted on arXiv 3 Feb 2025.

Builds on

62 of 101 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents11 Oct
  2. 2024AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents11 Oct
  3. 2024Teams of LLM Agents can Exploit Zero-Day Vulnerabilities2 Jun
  4. 2024LLM Agents can Autonomously Hack Websites6 Feb
  5. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandbox25 Sep

Other references · 57

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  6. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  8. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  9. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  10. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
  11. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  12. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
38 more
  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  2. 2018Datasheets for Datasetscited by 1,386
  3. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  4. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
  5. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,195
  6. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  7. 2018Model Cards for Model Reportingcited by 1,080
  8. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  9. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  10. 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineeringcited by 469
  11. 2023Cognitive Architectures for Language Agentscited by 429
  12. 2023Augmented Language Models: a Surveycited by 403
  13. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 392
  14. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentationcited by 366
  15. 2023A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesiscited by 353
  16. 2024TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Taskscited by 326
  17. 2024Magentic-One: A Generalist Multi-Agent System for Solving Complex Taskscited by 232
  18. 2024AI Agents That Mattercited by 219
  19. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 205
  20. 2024SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?cited by 203
  21. 2024Foundational Challenges in Assuring Alignment and Safety of Large Language Modelscited by 199
  22. 2024RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human expertscited by 175
  23. 2024Agent AI: Surveying the Horizons of Multimodal Interactioncited by 170
  24. 2024AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?cited by 158
  25. 2023Harms from Increasingly Agentic Algorithmic Systemscited by 135
  26. 2024Evaluating Frontier Models for Dangerous Capabilitiescited by 128
  27. 2024CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmarkcited by 123
  28. 2024The Ethics of Advanced AI Assistantscited by 107
  29. 2024DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agentscited by 100
  30. 2020Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Databasecited by 96
  31. 2023Evaluating the Social Impact of Generative AI Systems in Systems and Societycited by 92
  32. 2024Visibility into AI Agentscited by 79
  33. 2023The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AIcited by 73
  34. 2023The Foundation Model Transparency Indexcited by 66
  35. 2023PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documentscited by 61
  36. 2024HoneyComb: A Flexible LLM-Based Agent System for Materials Sciencecited by 57
  37. 2021Why AI is Harder Than We Thinkcited by 41
  38. 2025A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directionscited by 34

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 5.

15 papers.

Sort:

By area:

  1. 2025Characterizing AI Agents for Alignment and Governancecited by 30
  2. 2026The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systemscited by 30
  3. 2026How Well Does Agent Development Reflect Real-World Work?cited by 10
  4. 2025Build Agent Advocates, Not Platform Agentscited by 8
  5. 2025Position: Collaborative Agentic AI Needs Interoperability Across Ecosystemscited by 8
  6. 2025TableTalk: Scaffolding Spreadsheet Development with a Language Agentcited by 5
  7. 2025VET Your Agent: Towards Host-Independent Autonomy via Verifiable Execution Tracescited by 4
  8. 2025On the Regulatory Potential of User Interfaces for AI Agent Governancecited by 3
  9. 2026Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Modelscited by 3
  10. 2025The Problem of Algorithmic Collisions: Mitigating Unforeseen Risks in a Connected Worldcited by 2
  11. 2025Psychological and behavioural responses in human-agent vs. human-human interactions: a systematic review and meta-analysiscited by 2
  12. 2025Agentic AI for Mobile Network RAN Management and Optimizationcited by 2
3 more
  1. 2026ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperationcited by 1
  2. 2025Synchronization Dynamics of Heterogeneous, Collaborative Multi-Agent AI Systemscited by 0
  3. 2026The Agentic Web Requires New Normative Infrastructurecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety
  2. 2025Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
  3. 2026The Agentic Automation Canvas: a structured framework for agentic AI project design
  4. 2026Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents
  5. 2024Safeguarding AI Agents: Developing and Analyzing Safety Architectures
  6. 2025AgentHub: A Registry for Discoverable, Verifiable, and Reproducible AI Agents
  7. 2025Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems
  8. 2026TrustX Agent Risk Classification Framework (ARC): Risk-Tiering Internally Created Agentic AI Systems