# LeapLabTHU/Absolute-Zero-Reasoner

Official Repository of Absolute Zero Reasoner

Repository: https://github.com/LeapLabTHU/Absolute-Zero-Reasoner
Canonical: https://ross.abutalabs.com/products/absolute-zero-reasoner
Homepage: https://andrewzh112.github.io/absolute-zero-reasoner/
Language: Python
License: MIT
License Family: permissive
Last push: 2025-08-24T00:13:19+00:00

## Health v2 (maintenance only)
Score: 36/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 38, release rhythm 35, longevity 34
- inputs: {"age_days": 488, "days_push": 375, "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 1893, forks 298 (observed 2026-08-28T04:05:50.580351+00:00)

## What it is
Official implementation of Absolute Zero Reasoner (AZR), a system that trains LLM reasoning via reinforced self-play with zero external data, using a code executor to verify self-generated tasks. It provides training and evaluation pipelines for deduction, abduction, and induction reasoning modes.

## Use cases
- train a reasoning model without human-curated datasets
- replicate the Absolute Zero paper results
- run RL with verifiable rewards on code-based reasoning tasks
- evaluate LLMs on math and coding reasoning benchmarks
- experiment with self-play task proposal and solving
- use sandboxed code execution as a reward signal

## When to choose
- you want to train or fine-tune LLMs with zero external reasoning data
- you need a research-grade RLVR training pipeline with code-executor verification
- you want to reproduce or extend the Absolute Zero paper

## When to avoid
- you need a production-ready inference or serving framework
- you lack GPU resources for RL training
- you want a plug-and-play chatbot rather than a research training codebase

## Facets
- artifact type: library
- maturity: active
- function: llm-training, reinforcement-learning, machine-learning, benchmarking
- domain: large-language-models, machine-learning, deep-learning, artificial-intelligence
- platform: python
- tags: self-play, rlvr, zero-data, reasoning, code-executor, research-code, verifiable-rewards, gpu, linux

## Member repositories
- LeapLabTHU/Absolute-Zero-Reasoner (main) score 36

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:50.580351+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 2026-08-30T03:12:55.164478+00:00, confidence not recorded.
  - readme: https://github.com/LeapLabTHU/Absolute-Zero-Reasoner (fetched 2026-08-28T04:05:50.580351+00:00, sha 2eefaf0c66ac)
  - homepage: https://andrewzh112.github.io/absolute-zero-reasoner/ (fetched 2026-08-29T10:51:55.445192+00:00, sha e18facaa607f)
- Data as of 2026-08-30T08:39:29.467469+00:00.