# Surfer-H Meets Holo1: Cost-Efficient Web Agent Powered by Open Weights

arXiv: https://arxiv.org/abs/2506.02865 · HTML: https://mlsanity.com/paper/2506.02865/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 17 of 17)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [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)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents](https://mlsanity.com/paper/2401.10935/) (2024)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents](https://mlsanity.com/paper/2410.05243/) (2024)
- [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://mlsanity.com/paper/2410.23218/) (2024)
- [What matters when building vision-language models?](https://mlsanity.com/paper/2405.02246/) (2024)
- [ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use](https://mlsanity.com/paper/2504.07981/) (2025)
- [On Hallucination and Predictive Uncertainty in Conditional Language Generation](https://mlsanity.com/paper/2103.15025/) (2021)
- [XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models](https://mlsanity.com/paper/2411.15100/) (2024)
- [Can Language Models Solve Olympiad Programming?](https://mlsanity.com/paper/2404.10952/) (2024)

## Built on by (most cited first, 8 of 8)

- [From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows](https://mlsanity.com/paper/2506.23260/) (2025)
- [How to Train Your LLM Web Agent: A Statistical Diagnosis](https://mlsanity.com/paper/2507.04103/) (2025)
- [OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents](https://mlsanity.com/paper/2606.02031/) (2026)
- [Surfer 2: The Next Generation of Cross-Platform Computer Use Agents](https://mlsanity.com/paper/2510.19949/) (2025)
- [Weblica: Scalable and Reproducible Training Environments for Visual Web Agents](https://mlsanity.com/paper/2605.06761/) (2026)
- [A Multimodal GUI Architecture for Interfacing with LLM-Based Conversational Assistants](https://mlsanity.com/paper/2510.06223/) (2025)
- [Best-of-Q: Improving VLM agents with Q-function Action Ranking at Inference](https://mlsanity.com/paper/2601.22701/) (2026)
- [CAPTCHAs in the Agentic Era: Solvers That Learn from Every Encounter](https://mlsanity.com/paper/2609.02393/) (2026)

## Abstract (arXiv)

We present Surfer-H, a cost-efficient web agent that integrates Vision-Language Models (VLM) to perform user-defined tasks on the web. We pair it with Holo1, a new open-weight collection of VLMs specialized in web navigation and information extraction. Holo1 was trained on carefully curated data sources, including open-access web content, synthetic examples, and self-produced agentic data. Holo1 tops generalist User Interface (UI) benchmarks as well as our new web UI localization benchmark, WebClick. When powered by Holo1, Surfer-H achieves a 92.2% state-of-the-art performance on WebVoyager, striking a Pareto-optimal balance between accuracy and cost-efficiency. To accelerate research advancement in agentic systems, we are open-sourcing both our WebClick evaluation dataset and the Holo1 model weights.