Scalable Prompt Routing via Fine-Grained Latent Task Discovery Paper • 2603.19415 • Published 15 days ago • 6
Reinforcement-aware Knowledge Distillation for LLM Reasoning Paper • 2602.22495 • Published Feb 26 • 1
VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning Paper • 2601.20055 • Published Jan 27 • 7