TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models Paper • 2610.07767 • Published 21 days ago • 62
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 27 days ago • 235
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published Sep 15 • 318
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning Paper • 2608.26105 • Published Aug 26 • 82