OpAgent achieves 71.6% success rate in web navigation tasks

Researchers have developed OpAgent, a novel web navigation agent that utilizes online reinforcement learning to overcome the limitations of static datasets. The agent employs a hierarchical multi-task fine-tuning approach with a Vision-Language Model and a specialized RL pipeline featuring a hybrid reward mechanism. OpAgent demonstrated a significant improvement in performance, achieving a 71.6% success rate on the WebArena benchmark, surpassing previous state-of-the-art results. AI

影响 OpAgent's SOTA performance on WebArena may accelerate research into more robust and adaptable web agents for complex online tasks.

排序理由 This is a research paper detailing a new agent architecture and benchmark performance.

在 arXiv cs.AI 阅读 →

• arXiv
• OpAgent
• Reinforcement Learning
• Vision-Language Model
• WebArena

• 论文
• 模型发布

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →