Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles Paper • 2602.01590 • Published 9 days ago • 33
WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora Paper • 2602.02053 • Published 9 days ago • 40
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision Paper • 2601.03193 • Published Jan 6 • 47
Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics Paper • 2512.12602 • Published Dec 14, 2025 • 44
DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action Paper • 2511.22134 • Published Nov 27, 2025 • 22