---
title: Length-Controlled Reasoning
url: https://www.emergentmind.com/topics/length-controlled-reasoning
type: topic
---

# Length-Controlled Reasoning

Length-controlled reasoning is the study of how large language models and large reasoning models regulate the amount of explicit chain-of-thought they generate, typically measured in output or reasoning tokens, so as to balance correctness, latency, token cost, and, in some settings, safety. A central 2025 contribution in this area is "Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty" [2506.10446], which argues that reasoning should not be shortened uniformly: simple problems often benefit from concise solutions, whereas difficult problems may require longer deliberation. In that formulation, the goal is selective concision rather than global brevity, and the reported outcomes are shortened outputs on GSM8K and MATH500 while preserving or enhancing accuracy, together with improved accuracy on AIME2024 [2506.10446].

## 1. Problem formulation and motivation

The modern length-control literature begins from a shared empirical observation: RL-trained or CoT-p

Source: https://www.emergentmind.com/topics/length-controlled-reasoning