Interactive Training 2: Auditable Control Plane for Live Model Training Paper • 2607.18314 • Published 25 days ago • 20
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents Paper • 2606.32034 • Published Jun 30 • 12
Trimming the Long-Tail of Visual World Modeling Evaluation Paper • 2606.24256 • Published Jun 23 • 43
Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems Paper • 2606.17182 • Published Jun 15 • 1
Exploring Autonomous Agentic Data Engineering for Model Specialization Paper • 2605.30407 • Published May 28 • 23