---
title: "Discussion on \"The Rise and Fall of Reinforcement Learning for LLM “Reasoning”\" | Hashnode"
description: "Discussion on \"The Rise and Fall of Reinforcement Learning for LLM “Reasoning”\". Examination Reveals Flaws: LLMs Rely on Pre-training"
url: "https://hashnode.com/posts/the-rise-and-fall-of-reinforcement-learning-for-llm-reasoning/6821005dc98bb14564c12620"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [The Rise and Fall of Reinforcement Learning for LLM “Reasoning”](https://ai-cosmos.hashnode.dev/the-rise-and-fall-of-reinforcement-learning-for-llm-reasoning?utm_source=hashnode&utm_medium=feed)

Examination Reveals Flaws: LLMs Rely on Pre-training

May 11, 2025 · 4 min read · ai-cosmos.hashnode.dev  
Updated Oct 3, 2025  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#ai-literacy](https://hashnode.com/tag/ai-literacy)
-   [#reinforcement-learning](https://hashnode.com/tag/reinforcement-learning)
-   [#ai-myths](https://hashnode.com/tag/ai-myths)
-   [#ai-research](https://hashnode.com/tag/ai-research)
-   [#llm](https://hashnode.com/tag/llm)
-   [#transformers](https://hashnode.com/tag/transformers)

## Written by

[Gerard Sans](https://hashnode.com/@gerardsans)

@gerardsans · London, UK

  
[View profile](https://hashnode.com/@gerardsans)

AI/ML Google Developer Expert, AI/ML Cloud Champion, Angular GDE

I help developers succeed in Artificial Intelligence and Web3; Former AWS Amplify Developer Advocate. I am very excited about the future of the Web and JavaScript. Always happy Computer Science Engineer and humble Google Developer Expert. I love sharing my knowledge by speaking, training and writing about cool technologies. I love running communities and meetups such as Web3 London, GraphQL London, GraphQL San Francisco, mentoring students and giving back to the community.

## Responses 1

Markdown supported · ⌘↵ to post

[Areeba Nishat](https://hashnode.com/@arib)

[May 12, 2025](https://hashnode.com/posts/the-rise-and-fall-of-reinforcement-learning-for-llm-reasoning/6821005dc98bb14564c12620/comment/682162a3e01e79f193864d74)

Reinforcement Learning (RL), especially RLHF (Reinforcement Learning from Human Feedback), was once seen as a promising path to improve large language model reasoning. It helped align models with human preferences and refine outputs. However, its limitations became clear — RL tends to optimize for appearing right rather than actually thinking right. As a result, focus has shifted toward alternative methods like supervised fine-tuning, tool use, and architectural innovations that promote true reasoning over reward hacking.

[Gerard Sans](https://hashnode.com/@gerardsans)

[May 12, 2025](https://hashnode.com/posts/the-rise-and-fall-of-reinforcement-learning-for-llm-reasoning/6821005dc98bb14564c12620/comment/682162a3e01e79f193864d74#reply-6821e9d9045a1e491917e163)

Thanks for reading and for your reply. However, you are overlooking key findings in the research that clearly indicate a lack of actual ‘reasoning’ or ‘thinking’. It’s important to recognize that your framing reflects anthropomorphism, a cognitive bias that attributes human traits to AI.

While reinforcement learning introduces a different signal compared to next-token prediction during pre-training, the underlying backpropagation mechanism used in post-training remains unchanged. Adjusting weights through this process does not amount to cognitive reasoning. The transformer’s behavior during inference also remains the same. Post-training is more accurately described as ‘stochastic funneling’ or ‘manifold sculpting’, modeling existing distributions to favor the examples seen during fine-tuning, based on the data and tasks involved.
