OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks Paper • 2606.29537 • Published Jun 28 • 24
A Cartography of Open Collaboration in Open Source AI: Mapping Practices, Motivations, and Governance in 14 Open Large Language Model Projects Paper • 2509.25397 • Published Sep 29, 2025 • 14
DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines Paper • 2310.03714 • Published Oct 5, 2023 • 37