mlsanityData to 7 Oct 2026

LLM Agents Are the Antidote to Walled Gardens

arXiv 2506.23978 ↗First posted 30 Jun 2025cs.LG cs.CL cs.CYcited by 3

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

While the Internet's core infrastructure was designed to be open and universal, today's application layer is dominated by closed, proprietary platforms. Open and interoperable APIs require significant investment, and market leaders have little incentive to enable data exchange that could erode their user lock-in. We argue that LLM-based agents fundamentally disrupt this status quo. Agents can automatically translate between data formats and interact with interfaces designed for humans: this makes interoperability dramatically cheaper and effectively unavoidable. We name this shift universal interoperability: the ability for any two digital services to exchange data seamlessly using AI-mediated adapters. Universal interoperability undermines monopolistic behaviours and promotes data portability. However, it can also lead to new security risks, technical debt, and legal frictions. Our position is that the ML community should embrace this development while building the appropriate frameworks to mitigate the downsides. By acting now, we can harness AI to restore user freedom and competitive markets without sacrificing security.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 39 of its 108 references that are in the map. First posted on arXiv 30 Jun 2025.

Builds on

39 of 108 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep

Other references · 38

  1. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  2. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  3. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  4. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandboxcited by 514
  5. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  6. 2023Poisoning Web-Scale Training Datasets is Practicalcited by 276
  7. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 194
  8. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
  9. 2025WASP: Benchmarking Web Agent Security Against Prompt Injection Attackscited by 140
  10. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 129
  11. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  12. 2024Attacking Vision-Language Computer Agents via Pop-upscited by 112
26 more
  1. 2024Reducing hallucination in structured outputs via Retrieval-Augmented Generationcited by 92
  2. 2023AgentSims: An Open-Source Sandbox for Large Language Model Evaluationcited by 86
  3. 2025Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agentscited by 81
  4. 2025Authenticated Delegation and Authorized AI Agentscited by 63
  5. 2025Benchmarking Prompt Sensitivity in Large Language Modelscited by 38
  6. 2023Exploring the Sensitivity of LLMs' Decision-Making Capabilities: Insights from Prompt Variation and Hyperparameterscited by 32
  7. 2025API Agents vs. GUI Agents: Divergence and Convergencecited by 28
  8. 2025Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysiscited by 27
  9. 2024IDs for AI Systemscited by 18
  10. 2024ReMatch: Retrieval Enhanced Schema Matching with LLMscited by 16
  11. 2024From Natural Language to SQL: Review of LLM-based Text-to-SQL Systemscited by 15
  12. 2024Breaking reCAPTCHAv2cited by 12
  13. 2025SandboxEval: Towards Securing Test Environment for Untrusted Codecited by 10
  14. 2025A Framework for Testing and Adapting REST APIs as LLM Toolscited by 9
  15. 2020From Robotic Process Automation to Intelligent Process Automation: Emerging Trendscited by 8
  16. 2023Microservice API Evolution in Practice: A Study on Strategies and Challengescited by 7
  17. 2022Ontology Development is Consensus Creation, Not (Merely) Representationcited by 5
  18. 2023CAPTCHA Types and Breaking Techniques: Design Issues, Challenges, and Future Research Directionscited by 3
  19. 2017Domain Specific Semantic Validation of Schema.org Annotationscited by 2
  20. 2018Semantic Interoperability Middleware Architecture for Heterogeneous Environmental Data Sourcescited by 2
  21. 2023Dazed & Confused: A Large-Scale Real-World User Study of reCAPTCHAv2cited by 2
  22. 2014A Brief History of Web Crawlerscited by 1
  23. 2015Web Content Extraction - a Meta-Analysis of its Past and Thoughts on its Futurecited by 1
  24. 2018Business Rules in e-Government Applicationscited by 1
  25. 2021Continuous API Evolution in Heterogenous Enterprise Software Systemscited by 1
  26. 2025Putting GenAI on Notice: GenAI Exceptionalism and Contract Lawcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Architecting Trust in Artificial Epistemic Agentscited by 3
  2. 2026EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprisescited by 1
  3. 2026The Agentic Web Requires New Normative Infrastructurecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Beyond the Sum: Unlocking AI Agents Potential Through Market Forces
  2. 2026Bridging LLM Agents and Data Spaces: An Architectural Mediation Approach using the Model Context Protocol
  3. 2026Reframing LLM Agent Security as an Agent-Human Interaction Problem
  4. 2025Regulating the Agency of LLM-based Agents
  5. 2025The Agentic Economy
  6. 2026The Next Paradigm Is User-Centric Agent, Not Platform-Centric Service
  7. 2025A Survey of AI Agent Protocols
  8. 2025The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Markets