AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents Paper • 2602.06855 • Published Feb 6 • 82
What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation Diversity Paper • 2511.15593 • Published Nov 19, 2025 • 59
Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance Paper • 2511.13254 • Published Nov 17, 2025 • 139
