---
id: "sebastian-raschka-ahead-of-ai"
title: "Controlling Reasoning Effort in LLMs (Ahead of AI)"
creator: "Sebastian Raschka"
creator_url: "https://magazine.sebastianraschka.com/p/controlling-reasoning-effort-in-llms"
url: "https://magazine.sebastianraschka.com/p/controlling-reasoning-effort-in-llms"
level: "advanced"
level_max: null
category: "model-training"
subcategory: "post-training-rl"
region: "West"
license: "closed"
license_scope: "linked-resource"
models: ["any"]
source_date: null
date_added: "2026-10-18"
---

[Model Training](/model-training/index.md)

# Controlling Reasoning Effort in LLMs (Ahead of AI)

by [Sebastian Raschka](https://magazine.sebastianraschka.com/p/controlling-reasoning-effort-in-llms)

[Read the original →](https://magazine.sebastianraschka.com/p/controlling-reasoning-effort-in-llms)

A free Ahead of AI article on training controllable reasoning effort.

Raschka distinguishes training-time improvements from spending more computation during inference. He then discusses how reasoning models can be trained to vary their effort, with research examples rather than a universal recipe.

Level: [Advanced](/levels/index.md#advanced)
Models: any
Category: [Model Training](/model-training/index.md)
Tags: 
Source date: date not stated
Added: 2026-10-18
Last verified: 2026-10-18
Status: ok
Prerequisites: Requires implementation experience or critical reading of technical methods and system trade-offs.
Subcategory: [post training rl](/model-training/post-training-rl/index.md)
Region: West
Original language: en
Access: free
Resource reuse: closed: No general open-reuse grant established from the inspected page. Closed is the conservative index bucket, not a legal finding; the resource is publicly readable. [Facet definitions](/about/index.md#facets)

Summary in our own words. Rights remain with the original creator. [Credit and correction policy](/about/index.md#credit-policy).

[Plain-text Markdown copy](/model-training/post-training-rl/sebastian-raschka-ahead-of-ai/index.md)