# hkust-nlp/simpleRL-reason

Simple RL training for reasoning

Repository: https://github.com/hkust-nlp/simpleRL-reason
Canonical: https://ross.abutalabs.com/products/simplerl-reason
Language: Python
License: MIT
License Family: permissive
Last push: 2025-12-23T13:44:52+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 58, release rhythm 35, longevity 41
- inputs: {"age_days": 585, "days_push": 253, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3874, forks 285 (observed 2026-08-28T04:08:27.850194+00:00)

## What it is
A research codebase from HKUST-NLP implementing a simple reinforcement learning recipe (rule-based rewards on GSM8K/Math data) to train LLMs' reasoning abilities from base models without SFT. It includes training/eval code, model checkpoints for 10 base models, and analysis tools accompanying the SimpleRL-Zoo paper.

## Use cases
- train an LLM with reinforcement learning to improve math reasoning
- run zero RL training on base models like Qwen2.5 or Llama3
- reproduce SimpleRL-Zoo paper results
- compare reasoning behaviors across models during RL training
- fine-tune a 7B model with only 8K examples and rule-based rewards
- analyze response length and accuracy trends during RL training

## When to choose
- you want a minimal, proven RL recipe for eliciting reasoning in base LLMs
- you need to reproduce or extend the SimpleRL-Zoo results
- you want to train with rule-based rewards instead of a reward model
- you're researching emergent reasoning behaviors during RL

## When to avoid
- you need production-grade, supported LLM training infrastructure
- you want RLHF with human preference data or reward models
- you need SFT pipelines or general instruction tuning
- you lack multi-GPU resources for large model training

## Facets
- artifact type: library
- maturity: active
- function: llm-training, reinforcement-learning, machine-learning
- domain: large-language-models, machine-learning, deep-learning
- platform: python
- tags: rlhf, rule-based-reward, zero-rl, math-reasoning, verl, model-training, research-code, natural-language-processing, gpu, linux

## Member repositories
- hkust-nlp/simpleRL-reason (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:27.850194+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 2026-08-29T18:25:46.882681+00:00, confidence not recorded.
  - readme: https://github.com/hkust-nlp/simpleRL-reason (fetched 2026-08-28T04:08:27.850194+00:00, sha b2c7ca8b4770)
- Data as of 2026-08-30T08:39:29.467469+00:00.