Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents Paper • 2610.20344 • Published Oct 14 • 41
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models Paper • 2610.07767 • Published Oct 6 • 43
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published Sep 15 • 241