TokenRouter: Efficient Serving System for Token-Level LLM Routing Paper • 2610.12242 • Published 4 days ago • 130
Improving Test-Time Scaling with Adaptive Looped Transformers Paper • 2609.35748 • Published 14 days ago • 61
AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs Paper • 2605.15565 • Published May 15 • 16