pith. sign in

arxiv: 2506.02865 · v2 · pith:PQ7EZE5Dnew · submitted 2025-06-03 · 💻 cs.AI

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

Mathieu Andreux , Breno Baldas Skuk , Hamza Benchekroun , Emilien Bir\'e , Antoine Bonnet , Riaz Bordie , Nathan Bout , Matthias Brunel
show 36 more authors
Pierre-Louis Cedoz Antoine Chassang Micka\"el Chen Alexandra D. Constantinou Antoine d'Andign\'e Hubert de La Jonqui\`ere Aur\'elien Delfosse Ludovic Denoyer Alexis Deprez Augustin Derupti Michael Eickenberg Math\"is Federico Charles Kantor Xavier Koegler Yann Labb\'e Matthew C. H. Lee Erwan Le Jumeau de Kergaradec Amir Mahla Avshalom Manevich Adrien Maret Charles Masson Rafa\"el Maurin Arturo Mena Philippe Modard Axel Moyal Axel Nguyen Kerbel Julien Revelle Mats L. Richter Mar\'ia Santos Laurent Sifre Maxime Theillard Marc Thibault Louis Thiry L\'eo Tronchon Nicolas Usunier Tony Wu
This is my paper
classification 💻 cs.AI
keywords holo1surfer-hagentagenticcost-efficientdatapoweredwebclick
0
0 comments X
read the original abstract

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 paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Weblica: Scalable and Reproducible Training Environments for Visual Web Agents

    cs.AI 2026-05 unverdicted novelty 7.0

    Weblica scales RL training for visual web agents by building thousands of reproducible environments through HTTP caching for stable replays and LLM synthesis from real sites, yielding an 8B model that beats similar op...

  2. MolmoWeb: Open Visual Web Agent and Open Data for the Open Web

    cs.CV 2026-04 unverdicted novelty 7.0

    Open 4B and 8B visual web agents achieve state-of-the-art results on browser benchmarks by predicting actions from screenshots and instructions, outperforming similar open models and some closed larger-model agents, w...

  3. OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

    cs.LG 2026-06 unverdicted novelty 6.0

    OpenWebRL trains a 4B visual web agent with online RL on live sites using 0.4K init trajectories and 2.2K RL tasks to reach 67% success on Online-Mind2Web and 64% on DeepShop, outperforming prior open agents.

  4. "I Strongly Suspect This Website Is a Scam": Benchmarking PII Leakage and Detection without Defense in Autonomous Web Agents

    cs.CR 2026-05 unverdicted novelty 6.0

    New benchmark Scammer4U finds 54-93% critical PII leakage from frontier web agents on scam sites versus 0% on benign twins, plus a 30-point gap between verbalized suspicion and actual submission.