# Throttling Web Agents Using Reasoning Gates arXiv: https://arxiv.org/abs/2509.01619 ยท HTML: https://mlsanity.com/paper/2509.01619/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. - Builds on 46 of its 111 references that are in the map. - First posted on arXiv 1 Sep 2025. ## Placed in - LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/) - LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/) ## Builds on (most cited first, 30 of 46) - [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021) - [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021) - [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023) - [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025) - [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024) - [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025) - [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023) - [Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models](https://mlsanity.com/paper/2410.07985/) (2024) - [Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions](https://mlsanity.com/paper/2503.23278/) (2025) - [Survey on Evaluation of LLM-based Agents](https://mlsanity.com/paper/2503.16416/) (2025) - [MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning](https://mlsanity.com/paper/2310.16049/) (2023) - [AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges](https://mlsanity.com/paper/2505.10468/) (2025) - [On Memorization of Large Language Models in Logical Reasoning](https://mlsanity.com/paper/2410.23123/) (2024) - [Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space](https://mlsanity.com/paper/2505.15778/) (2025) - [OverThink: Slowdown Attacks on Reasoning LLMs](https://mlsanity.com/paper/2502.02542/) (2025) - [LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models](https://mlsanity.com/paper/2309.14393/) (2023) - [Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models](https://mlsanity.com/paper/2503.21380/) (2025) - [Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images](https://mlsanity.com/paper/2401.11170/) (2024) - [Authenticated Delegation and Authorized AI Agents](https://mlsanity.com/paper/2501.09674/) (2025) - [Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers](https://mlsanity.com/paper/2506.13538/) (2025) - [SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories](https://mlsanity.com/paper/2409.07440/) (2024) - [Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks](https://mlsanity.com/paper/2502.08586/) (2025) - [VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks](https://mlsanity.com/paper/2401.13649/) (2024) - [Agentic Web: Weaving the Next Web with AI Agents](https://mlsanity.com/paper/2507.21206/) (2025) - [Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models](https://mlsanity.com/paper/2406.17169/) (2024) - [Quizbowl: The Case for Incremental Question Answering](https://mlsanity.com/paper/1904.04792/) (2019) - [Denial-of-Service Poisoning Attacks against Large Language Models](https://mlsanity.com/paper/2410.10760/) (2024) - [SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas](https://mlsanity.com/paper/2505.14615/) (2025) - [Benchmarking Reasoning Robustness in Large Language Models](https://mlsanity.com/paper/2503.04550/) (2025) - [Language Models can be Logical Solvers](https://mlsanity.com/paper/2311.06158/) (2023) ## Built on by (most cited first, 2 of 2) - [A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypes](https://mlsanity.com/paper/2601.05293/) (2026) - [From Question Answering to Task Completion: A Survey on Agent System and Harness Design](https://mlsanity.com/paper/2606.20683/) (2026) ## Abstract (arXiv) AI web agents use Internet resources at far greater speed, scale, and complexity -- changing how users and services interact. Deployed maliciously or erroneously, these agents could overload content providers. At the same time, web agents can bypass CAPTCHAs and other defenses by mimicking user behavior or flood authentication systems with fake accounts. Yet providers must protect their services and content from denial-of-service attacks and scraping by web agents. In this paper, we design a framework that imposes tunable costs on agents before providing access to resources; we call this Web Agent Throttling. We start by formalizing Throttling Gates as challenges issued to an agent that are asymmetric, scalable, robust, and compatible with any agent. Focusing on a common component -- the language model -- we require the agent to solve reasoning puzzles, thereby incurring excessive token-generation costs. However, we find that using existing puzzles, e.g., coding or math, as throttling gates fails to satisfy our properties. To address this, we introduce rebus-based Reasoning Gates, synthetic text puzzles that require multi-hop reasoning over world knowledge (thereby throttling an agent's model). We design a scalable generation and verification protocol for such reasoning gates. Our framework achieves computational asymmetry, i.e., the response-generation cost is 9.2x higher than the generation cost for SOTA models. We further deploy reasoning gates on a custom website and Model Context Protocol (MCP) servers and evaluate with real-world web agents. Finally, we discuss the limitations and environmental impact of real-world deployment of our framework.