Skip to main content

Latest Advances on Long Chain-of-Thought Reasoning

637
GitHub Stars
289
Curated Resources
7
Categories
22 hours ago
Last Refreshed
0. How to Learn & About Us1. Classical Reasoning Model2. Introduction to Long-CoT Capabilities3. Key Phenomena and Related Principles4. Algorithms5. Datasets7. Paper Lists & Awesome Resources

Use this list with your AI agent

Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:

"Show me 4.2 reinforcement learning resources from awesome-long-chain-of-thought-reasoning"

Installation instructions →

What's inside

4. Algorithms

2. Introduction to Long-CoT Capabilities

5. Datasets

  • AceMath-Instruct5.2 Training Datasets

  • AIME 20245.1 Benchmarks

    American Invitational Mathematics Examination 2024, a high-level high school math competition dataset, including all questions from AIME I and II of 2024. The problems focus on integer solutions and combinatorial reasoning.

  • AIME 20255.1 Benchmarks

    A collection of problems from AIME 2025 I & II. The difficulty is similar to AIME 2024, assessing high school students' complex math problem-solving abilities.

  • AMC 20235.1 Benchmarks

    American Mathematics Competitions 2023, a validation set consisting of 83 problems from the AMC12 competition. It includes questions from the 2022-2023 AMC12 covering topics such as algebra and geometry.

  • AM-DeepSeek-R1-Distilled5.2 Training Datasets

  • AoPS-Instruc5.2 Training Datasets

0. How to Learn & About Us

7. Paper Lists & Awesome Resources

3. Key Phenomena and Related Principles

1. Classical Reasoning Model

Showing a sample of 289 resources. View the full list on GitHub →