AINeutralarXiv – CS AI · 14h ago7/10
🧠
Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs
Researchers extend the bounded attention prefix oracle (BAPO) model to establish theoretical lower bounds on chain-of-thought reasoning tokens required by LLMs, proving that canonical tasks require Ω(n) tokens as input size n grows. Experiments with frontier models confirm linear scaling behavior, revealing fundamental computational bottlenecks in inference-time scaling.