TsinghuaC3I/Awesome-RL-for-LRMs
A Survey of Reinforcement Learning for Large Reasoning Models
This survey paper helps AI researchers and practitioners understand how Reinforcement Learning (RL) improves the reasoning abilities of Large Reasoning Models (LRMs). It compiles and organizes academic papers on topics like reward design, policy optimization, and training resources. The target audience is researchers and engineers working on advanced AI models, particularly those involved in developing or improving intelligent agents and large language models.
2,368 stars.
Use this if you are an AI researcher or engineer seeking a structured overview of current research in applying Reinforcement Learning to enhance Large Reasoning Models and their applications.
Not ideal if you are a non-technical user looking for a basic introduction to AI or a tool to directly solve a business problem without technical implementation.
Stars
2,368
Forks
127
Language
TeX
License
MIT
Category
Last pushed
Nov 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/TsinghuaC3I/Awesome-RL-for-LRMs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
open-thought/reasoning-gym
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Hmbown/Hegelion
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
LLM360/Reasoning360
A repo for open research on building large reasoning models
bowang-lab/BioReason
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model | NeurIPS '25
Peiyang-Song/Awesome-LLM-Reasoning-Failures
Repo for "Large Language Model Reasoning Failures"