Story
arxiv_cs_cl · Nov 5, 2026 · paper
Source brief
Agent-R$^2$: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis
arxiv.orgNov 5, 2026
original source linked
In brief
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 f...
Feed lens
agenticevaluation