K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs Paper • 2605.09635 • Published Jul 23 • 64
ReferTrack: Referring Then Tracking for Embodied Visual Tracking Paper • 2607.20061 • Published Jul 22 • 53
AREX: Towards a Recursively Self-Improving Agent for Deep Research Paper • 2607.21461 • Published Jul 23 • 154
SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Paper • 2607.20145 • Published Jul 22 • 75
RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM Paper • 2607.11683 • Published Jul 13 • 150
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources Paper • 2606.29538 • Published Jul 16 • 145
BadWAM: When World-Action Models Dream Right but Act Wrong Paper • 2607.15207 • Published Jul 16 • 54