LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 13 days ago • 203
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models Paper • 2607.12463 • Published 15 days ago • 108
GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems Paper • 2606.28187 • Published Jun 26 • 13
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published May 22 • 82
Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding Paper • 2605.20104 • Published May 19 • 7
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published May 12 • 196