ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Paper • 2605.20342 • Published May 19 • 34
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale Paper • 2603.25040 • Published Mar 26 • 134
OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions Paper • 2602.05843 • Published Feb 5 • 61
OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent Paper • 2601.07779 • Published Jan 12 • 28
ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data Paper • 2509.15221 • Published Sep 18, 2025 • 111
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency Paper • 2508.18265 • Published Aug 25, 2025 • 225
