Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics
Paper • 2609.36608 • Published • 6
None defined yet.
Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?
Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics