K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts Paper • 2606.02404 • Published Jun 1 • 59
LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training Paper • 2605.29888 • Published May 28 • 34
ResearchMath-14K: Scaling Research-Level Mathematics via Agents Paper • 2605.28003 • Published May 27 • 50