# LLM Agents Are the Antidote to Walled Gardens

arXiv: https://arxiv.org/abs/2506.23978 · HTML: https://mlsanity.com/paper/2506.23978/

## Key facts

- Cited by 3 papers in the map (data through 14 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.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 39)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [Poisoning Web-Scale Training Datasets is Practical](https://mlsanity.com/paper/2302.10149/) (2023)
- [Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents](https://mlsanity.com/paper/2403.02502/) (2024)
- [Large Language Model-Brained GUI Agents: A Survey](https://mlsanity.com/paper/2411.18279/) (2024)
- [WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks](https://mlsanity.com/paper/2504.18575/) (2025)
- [RestGPT: Connecting Large Language Models with Real-World RESTful APIs](https://mlsanity.com/paper/2306.06624/) (2023)
- [Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL](https://mlsanity.com/paper/2406.08426/) (2024)
- [Attacking Vision-Language Computer Agents via Pop-ups](https://mlsanity.com/paper/2411.02391/) (2024)
- [Reducing hallucination in structured outputs via Retrieval-Augmented Generation](https://mlsanity.com/paper/2404.08189/) (2024)
- [AgentSims: An Open-Source Sandbox for Large Language Model Evaluation](https://mlsanity.com/paper/2308.04026/) (2023)
- [Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents](https://mlsanity.com/paper/2503.15547/) (2025)
- [Authenticated Delegation and Authorized AI Agents](https://mlsanity.com/paper/2501.09674/) (2025)
- [Benchmarking Prompt Sensitivity in Large Language Models](https://mlsanity.com/paper/2502.06065/) (2025)
- [Exploring the Sensitivity of LLMs' Decision-Making Capabilities: Insights from Prompt Variation and Hyperparameters](https://mlsanity.com/paper/2312.17476/) (2023)
- [API Agents vs. GUI Agents: Divergence and Convergence](https://mlsanity.com/paper/2503.11069/) (2025)
- [Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis](https://mlsanity.com/paper/2502.20383/) (2025)
- [IDs for AI Systems](https://mlsanity.com/paper/2406.12137/) (2024)
- [ReMatch: Retrieval Enhanced Schema Matching with LLMs](https://mlsanity.com/paper/2403.01567/) (2024)
- [From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems](https://mlsanity.com/paper/2410.01066/) (2024)
- [Breaking reCAPTCHAv2](https://mlsanity.com/paper/2409.08831/) (2024)
- [SandboxEval: Towards Securing Test Environment for Untrusted Code](https://mlsanity.com/paper/2504.00018/) (2025)
- [A Framework for Testing and Adapting REST APIs as LLM Tools](https://mlsanity.com/paper/2504.15546/) (2025)
- [From Robotic Process Automation to Intelligent Process Automation: Emerging Trends](https://mlsanity.com/paper/2007.13257/) (2020)
- [Microservice API Evolution in Practice: A Study on Strategies and Challenges](https://mlsanity.com/paper/2311.08175/) (2023)
- [Ontology Development is Consensus Creation, Not (Merely) Representation](https://mlsanity.com/paper/2210.12026/) (2022)

## Built on by (most cited first, 3 of 3)

- [Architecting Trust in Artificial Epistemic Agents](https://mlsanity.com/paper/2603.02960/) (2026)
- [EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprises](https://mlsanity.com/paper/2603.21630/) (2026)
- [The Agentic Web Requires New Normative Infrastructure](https://mlsanity.com/paper/2606.10711/) (2026)

## 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.