AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts Paper • 2601.20730 • Published 3 days ago • 18
TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization Paper • 2601.16480 • Published 8 days ago • 50
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Paper • 2601.14724 • Published 10 days ago • 73
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Paper • 2601.15876 • Published 9 days ago • 89
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs Paper • 2601.13836 • Published 11 days ago • 34
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development Paper • 2601.11077 • Published 15 days ago • 64
view article Article The Heterogeneous Feature of RoPE-based Attention in Long-Context LLMs Nov 15, 2025 • 13