Token Complexity Theory for AI-Augmented Computing

📰 ArXiv cs.AI

arXiv:2606.12647v1 Announce Type: cross Abstract: AI-augmented computing delegates natural language queries, code generation requests, and other open-ended tasks to a cluster of AI models that processes queries and generates responses. This paradigm introduces a resource dimension that neither classical time nor space complexity captures: the cost of sending queries to and receiving responses from such a cluster. We introduce token complexity, a formal resource measure defined as the minimum exp

Published 12 Jun 2026
Read full paper → ← Back to Reads