EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Paper • 2601.15876 • Published 1 day ago • 60
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Paper • 2601.14724 • Published 2 days ago • 52
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs Paper • 2601.13836 • Published 3 days ago • 34
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development Paper • 2601.11077 • Published 7 days ago • 62