AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents Paper • 2603.14465 • Published Mar 15 • 23
\$OneMillion-Bench: How Far are Language Agents from Human Experts? Paper • 2603.07980 • Published Mar 9 • 27
DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution Paper • 2601.13761 • Published Jan 20 • 16
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning Paper • 2512.07461 • Published Dec 8, 2025 • 80
