Agent-R^2: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis

Teng Pan, wangzixuan, Yuchen Yan, Qifei Wu, Yao Chen, Yingqi Qu, Ruiqing Zhang, Yongliang Shen

Agent-R^2: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis: 8 upvotes on Hugging Face Daily Papers, #18 of 34 papers on 2026-11-13. Day-by-day upvote history.

Upvotes over time

It had 3 upvotes by its first day, 4 upvotes by the next day, 8 upvotes by day 3, 8 upvotes by day 7, and has 8 now. It ranked #82 of 167 papers in its week and #264 of 520 in its month. Its code repository has 12 GitHub stars.

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. However, current agents still struggle to finish such tasks, where success requires following long-horizon professional workflows, understanding heterogeneous file contexts, and producing usable deliverables under fine-grained requirements. A key bottleneck is the lack of scalable post-training data that reflects real work intent, authentic file environments, and deliverable-level evaluation. To close this gap, we introduce Agent-R^2, a real-source data synthesis framework that scales training data for realistic productivity work. Instead of relying on manually specified workflows or LLM-generated files, Agent-R^2 grounds synthesis throughout the pipeline in real occupational seeds, corpus-derived workflow evidence, and authentic web-sourced files. From 10k web-corpus candidates, Agent-R^2 distills 4k task instances that pair real multi-format attachments with fine-grained, deliverable-level rubrics. On this data, we train Agent-R^2-4B via supervised fine-tuning and rubric-based reinforcement learning, improving both end-to-end productivity performance and file-grounded reasoning. Trained on only 4k instances, Agent-R^2-4B surpasses Qwen3-235B-A22B-Thinking-2507 on both GDPval (51.0% vs. 48.0%) and OfficeQA (14.8% vs. 13.8%). Further analysis shows that Agent-R^2 mitigates shortcut behavior, where agents produce superficially plausible deliverables before sufficiently grounding, constructing, or verifying them, while promoting sustained exploration.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.