WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models — HN submission

Thu, 16 Jan 2025 13:07:44 GMT

Show HN: Skyvern 2.0 – open-source AI Browser Agent scoring 85.8% on WebVoyager

Hey HN, We’re Suchintan and Shu from Skyvern (https://www.skyvern.com). We’re building an open source AI Agent that can browse the web and take actions. Our open source repo can be found at https://github.com/Skyvern-AI/Skyvern. We’ve re-built Skyvern with a Planner-Actor-Validator agent architecture and achieved 85.8% state of the art (SOTA) on the WebVoyager Benchmark. You can see the results for yourself here: https://eval.skyvern.com/ For reference, here were the previous SOTA results: 83.5% - Google Mariner (https://deepmind.google/technologies/project-mariner/) 73.1% - AgentE…

9 points; 3 discussion replies on HN. Paper and source history. A submission is not an endorsement.

WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models — mentioned by hypoxia

Mon, 23 Dec 2024 11:18:15 GMT

Yeah, +1. Looking back to the WebVoyager [1] and GPT4V generalist agent [2] papers from last January, it feels like we haven't come that far. But there are now several major technical unlocks - fine tuning for cursor locations (in Claude), better reasoning with o3, and RL fine-tuning so we can learn based on task success. That gives me significant hope. [1] https://arxiv.org/abs/2401.13919 [2] https://arxiv.org/abs/2401.01614

Paper and discussion history. A mention is not an endorsement.

WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models · HackerPapers discussions

WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models — HN submission

WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models — mentioned by hypoxia