TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization Paper • 2601.16480 • Published Jan 23 • 51
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Paper • 2601.15876 • Published Jan 22 • 91
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Paper • 2601.14724 • Published Jan 21 • 74
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs Paper • 2601.13836 • Published Jan 20 • 35
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development Paper • 2601.11077 • Published Jan 16 • 65