Hugging Face Papers ↗ · 2026-11-05
Agent-R^2: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis
Media reports Hugging Face Papers Source language: Chinese
论文摘要(作者报告,未经本站复测):Large language models have made rapid progress in agentic reasoning and tool use, raising expectations for agents that can take over realistic productivity work from humans.
Full text
A real-source data synthesis framework trains a 4B agent on 4k task instances with supervised fine-tuning and rubric-based reinforcement learning, improving realistic productivity work and file-grounded reasoning over larger models.