Trendoday

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

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 st

  • Upvotes4
#22Rank now 3
#19Peak rank
3Days on list
90Score · 7d
Nov 14, 2026First seen
Rank · 7 days

About this paper

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.

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…

large language modelsagentic reasoningtool usepost-training datareal-source data synthesissupervised fine-tuningrubric-based reinforcement learningfile-grounded reasoningshortcut behaviorsustained exploration
Upvotes
4
Authors
8
Published
Nov 5, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

Agent-R^2: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis was first seen on Hugging Face · Daily papers on Nov 14, 2026. Since then it has appeared in 17 checks on 3 different days. Its best position was #19 of 30, reached on Nov 16, 03:28 UTC. It is #22 right now, climbing from #24 to #22 over the last 6 checks.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 13:2823:2809:2819:2805:28 Nov 14, 13:28 UTC · #28Nov 14, 15:28 UTC · #28Nov 14, 17:28 UTC · #28Nov 14, 19:28 UTC · #29Nov 14, 21:28 UTC · #29Nov 15, 07:28 UTC · #23Nov 15, 09:28 UTC · #25Nov 15, 11:28 UTC · #24Nov 15, 13:28 UTC · #24Nov 15, 15:28 UTC · #24Nov 15, 17:28 UTC · #24Nov 15, 19:28 UTC · #24Nov 15, 21:28 UTC · #24Nov 15, 23:28 UTC · #25Nov 16, 01:28 UTC · #25Nov 16, 03:28 UTC · #19Nov 16, 05:28 UTC · #22

Last 14 days

Best rank per day (UTC).

Nov 3today

Metric history

▲ as reported by Hugging Face.

0358 13:2823:2809:2819:2805:28 Nov 14, 13:28 UTC · 4Nov 14, 15:28 UTC · 4Nov 14, 17:28 UTC · 4Nov 14, 19:28 UTC · 4Nov 14, 21:28 UTC · 4Nov 15, 07:28 UTC · 6Nov 15, 09:28 UTC · 6Nov 15, 11:28 UTC · 7Nov 15, 13:28 UTC · 7Nov 15, 15:28 UTC · 7Nov 15, 17:28 UTC · 7Nov 15, 19:28 UTC · 7Nov 15, 21:28 UTC · 7Nov 15, 23:28 UTC · 7Nov 16, 01:28 UTC · 7Nov 16, 03:28 UTC · 8Nov 16, 05:28 UTC · 8

Questions

Is Agent-R^2: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis trending on HF Daily Papers right now?

Yes. As of Nov 16, 05:28 UTC it is #22, climbing from #24 to #22 over the last 6 checks.

What is the highest rank Agent-R^2: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis reached?

#19 on Hugging Face · Daily papers, on Nov 16, 03:28 UTC. Trendoday checks this list every 120 minutes.

How long has Agent-R^2: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis been trending?

It was first seen on Nov 14, 2026 and has been on the list on 3 days (17 checks) since.