False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 150
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models Paper • 2610.07767 • Published Oct 6 • 44
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published Sep 15 • 271
Alaya-EVOKE: From Linear-Scaling Supervision to Endless World Paper • 2608.13546 • Published Aug 13 • 75