Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills Paper • 2603.25158 • Published 8 days ago • 46
CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents Paper • 2603.24440 • Published 9 days ago • 93
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks Paper • 2603.24755 • Published 9 days ago • 27
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale Paper • 2603.25040 • Published 8 days ago • 125
MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens Paper • 2603.23516 • Published 28 days ago • 45
From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents Paper • 2603.22386 • Published 11 days ago • 54
Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought Paper • 2603.22847 • Published 10 days ago • 25
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model Paper • 2603.21986 • Published 11 days ago • 120