TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models Paper • 2610.07767 • Published Oct 6 • 43
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 150
LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches Paper • 2610.06647 • Published Oct 5 • 34