AI RESEARCH
Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens
arXiv CS.CL
•
ArXi:2604.26355v1 Announce Type: new Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains underexplored. We observe that reasoning tokens split into two functional types: low-entropy \textit{structural} tokens (recurring phrases that scaffold the reasoning process) and higher-entropy \textit{organic} tokens (problem-specific content that drives toward a solution.