AI RESEARCH
ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning
arXiv CS.AI
•
ArXi:2601.08310v2 Announce Type: replace-cross Recent Large Reasoning Models (LRMs) achieve strong performance by leveraging long-form Chain-of-Thought (CoT) reasoning, but uniformly applying overlong reasoning at inference time incurs substantial and often unnecessary computational cost. To address this, prior work explores various strategies to infer an appropriate reasoning budget from the input.