Skip to main content
Search

Teng Pan

1 related articles

Subscribe to updates
  1. arXiv

    A 4B agent trained on 4,000 real-source office tasks edges past a 235B model on GDPval, 51.0% to 48.0%

    Zhejiang University and Baidu introduce Agent-R2, a pipeline that synthesizes productivity-work training data from real sources: it distills 4,000 task instances from 10,000 web-corpus candidates, each pairing authentic multi-format attachments with fine-grained rubrics. Trained on this data with supervised fine-tuning and rubric-based reinforcement learning, Agent-R2-4B reaches 51.0% Pass@1 on GDPval versus 48.0% for Qwen3-235B-A22B-Thinking-2507, and 14.8% versus 13.8% on OfficeQA.

You’re all caught up