---
format: "aidr-story-markdown/v1"
id: "9f229cc48a900694457ba7f83d7dd4c1c9cb04b19b264c33a38833699b1d5285"
canonical_url: "https://aidr.today/9f229cc4?lang=en"
title: "Supervised Fine-Tuning for Reasoning Large Language Models: A Survey"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-30T04:00:00.000Z"
category: "Research"
topics: ["reasoning","llm"]
source_urls: ["https://arxiv.org/abs/2610.37681","https://arxiv.org/abs/2610.37684"]
summary: "A survey reviews supervised fine-tuning methods for reasoning large language models, categorizing approaches into data-centric and algorithm-centric innovations."
---

# Supervised Fine\-Tuning for Reasoning Large Language Models: A Survey

> [Open the canonical story](<https://aidr.today/9f229cc4?lang=en>)

**Published:** 2026-10-30T04:00:00.000Z
**Category:** Research
**Topics:** reasoning, llm

## Summary

A survey reviews supervised fine\-tuning methods for reasoning large language models, categorizing approaches into data\-centric and algorithm\-centric innovations\.

## Sources

- [Story source](<https://arxiv.org/abs/2610.37681>)
- [Story source](<https://arxiv.org/abs/2610.37684>)