Surfer-H Meets Holo1: Cost-Efficient Web Agent Powered by Open Weights
hamza-hcompany
Abstract
Surfer-H, paired with Holo1, an open-weight collection of Vision-Language Models, achieves top performance in web navigation tasks with high cost-efficiency.
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.
Community
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.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- DPO Learning with LLMs-Judge Signal for Computer Use Agents (2025)
- GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents (2025)
- AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025)
- Web-Shepherd: Advancing PRMs for Reinforcing Web Agents (2025)
- UIShift: Enhancing VLM-based GUI Agents through Self-supervised Reinforcement Learning (2025)
- WebThinker: Empowering Large Reasoning Models with Deep Research Capability (2025)
- Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
