AI RESEARCH
LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
arXiv CS.AI
•
ArXi:2605.09806v1 Announce Type: cross Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require, wasting compute, latency, and context budgets. While