TsinghuaC3I/Awesome-RL-for-LRMs
A comprehensive survey and paper collection on reinforcement learning methods applied to large reasoning models.
Not currently ranked — collecting fresh signals.
star history
This repository hosts a survey paper and curated list of research works on applying reinforcement learning to Large Reasoning Models (LRMs). It catalogs papers on techniques like RLHF, GRPO, and reasoning-focused training methods for advanced LLMs. The collection covers topics including chain-of-thought reasoning, process reward models, and multi-agent RL systems for LRM improvement.
Frequently asked
- What is TsinghuaC3I/Awesome-RL-for-LRMs?
- A comprehensive survey and paper collection on reinforcement learning methods applied to large reasoning models.
- Is Awesome-RL-for-LRMs open source?
- Yes — TsinghuaC3I/Awesome-RL-for-LRMs is open source, released under the MIT license.
- What language is Awesome-RL-for-LRMs written in?
- TsinghuaC3I/Awesome-RL-for-LRMs is primarily written in TeX.
- How popular is Awesome-RL-for-LRMs?
- TsinghuaC3I/Awesome-RL-for-LRMs has 2.5k stars on GitHub.
- Where can I find Awesome-RL-for-LRMs?
- TsinghuaC3I/Awesome-RL-for-LRMs is on GitHub at https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs.