Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents Paper • 2610.20344 • Published 13 days ago • 63
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published 28 days ago • 156
LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches Paper • 2610.06647 • Published 22 days ago • 60
Realtime-Venus: A full-duplex interaction system with asynchronous delegation Paper • 2609.13814 • Published Sep 12 • 162