# TsinghuaC3I/Awesome-RL-for-LRMs

A Survey of Reinforcement Learning for Large Reasoning Models

Repository: https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs
Canonical: https://ross.abutalabs.com/products/awesome-rl-for-lrms
Homepage: https://arxiv.org/abs/2509.08827
Language: TeX
License: MIT
License Family: permissive
Topics: awesome-list, llm, reasoning, rl, deepseek-r1, open-source, lrm
Last push: 2026-08-20T13:22:49+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 15, longevity 37
- inputs: {"age_days": 531, "days_push": 13, "days_rel": 357, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2482, forks 133 (observed 2026-08-28T04:06:55.349606+00:00)

## What it is
A curated awesome-list accompanying the survey paper 'A Survey of Reinforcement Learning for Large Reasoning Models' from Tsinghua University. It catalogs research papers on applying reinforcement learning to LLMs and Large Reasoning Models (LRMs), organized by the survey's category structure.

## Use cases
- find papers on RL for LLM reasoning
- survey reinforcement learning methods for large reasoning models
- research RL training after DeepSeek-R1
- find resources on RLHF and reasoning model training
- track recent research on LRM scalability and RL algorithms
- get started with academic literature on reasoning models

## When to choose
- you need a curated, categorized reading list of RL-for-reasoning research
- you are writing a literature review on LLM reasoning and RL
- you want to follow the state of the art since DeepSeek-R1

## When to avoid
- you need runnable training code or an RL framework rather than a paper list
- you want beginner tutorials rather than research papers

## Facets
- artifact type: learning-resource
- maturity: active
- function: reinforcement-learning, llm-training, machine-learning
- domain: reinforcement-learning, large-language-models, artificial-intelligence, tutorials, awesome-lists
- platform: cross-platform
- tags: awesome-list, survey, reasoning, large-reasoning-models, deepseek-r1, paper-list, rlhf

## Member repositories
- TsinghuaC3I/Awesome-RL-for-LRMs (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:55.349606+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:28:07.579482+00:00, confidence not recorded.
  - readme: https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs (fetched 2026-08-28T04:06:55.349606+00:00, sha 0136f4b840c5)
  - homepage: https://arxiv.org/abs/2509.08827 (fetched 2026-08-29T10:10:03.125443+00:00, sha eab8d22de1fa)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T10:10:03.132932+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T10:10:03.129322+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T10:10:03.135107+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T10:10:03.131166+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.