Reporium
GraphWikiTaxonomyStacksInsightsTrendsArchitectureAI-NativeFAQ
Ask anything about the repo library…
Loading repo…
←Library/AReaL
Library/AReaLForked

areal-project/AReaL

AReaL

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

View on GitHub↗Upstream areal-project/AReaL↗

Builder

areal-project

areal-project

areal-project • individual

Stars

5,234

Using upstream star count

Forks

508

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Feb 24, 2025

Project creation date

README Summary

<h1 align="center"> <em>AReaL</em>: A Large-Scale Asynchronous Reinforcement Learning System </h1>

Community Evaluation

Loading…

AI Dev Skills

Unmapped

AI Agent DevelopmentLanguage Model Fine-tuningLarge Language Model TrainingLLM Reasoning SystemsPolicy Gradient MethodsReinforcement Learning for LLMsReward Model Training

Tags

AI Agent DevelopmentLanguage Model Fine-tuningLarge Language Model TrainingLLM Reasoning SystemsPolicy Gradient MethodsReinforcement Learning for LLMsReward Model TrainingAI AgentsAI SafetyActiveAnthropic / ClaudeBackendBenchmarkingDistillationEvalsFSDPForkedGPU / CUDAGRPOGemmaGoogle AIGoogle CloudHuggingFaceKubernetesLLM ServingLarge Language ModelsLoRA / PEFTMachine LearningOpenAIOpenAI Agents SDKPyTorchPythonQwenRLHFRayReinforcement LearningResearch / PapersRoadmapSGLangTool UseTransformersTutorialvLLM

Taxonomy

AI Trends

Agentic AILLM ReasoningReinforcement Learning from Human FeedbackAI Agents

category

Foundation ModelsAI AgentsModel TrainingEvals & BenchmarkingInference & ServingMLOps & InfrastructureDev Tools & AutomationCloud & PlatformsLearning ResourcesSecurity & Safety

Deployment Context

Self-hostedCloud API

Modalities

Text

Skill Areas

Reinforcement Learning for LLMsLarge Language Model TrainingLLM Reasoning SystemsAI Agent DevelopmentPolicy Gradient MethodsReward Model TrainingLanguage Model Fine-tuning

tag

AI AgentsAI SafetyAnthropic / ClaudeBackendBenchmarkingDistillationEvalsFSDPForkedGPU / CUDAGRPOGemmaGoogle AIGoogle CloudHuggingFaceKubernetesLLM ServingLarge Language ModelsLoRA / PEFTMachine LearningOpenAIOpenAI Agents SDKPyTorchPythonQwenRLHFRayReinforcement LearningResearch / PapersRoadmapSGLangTool UseTransformersTutorialvLLMActive

Use Cases

LLM Reasoning EnhancementAI Agent TrainingReinforcement Learning from Human FeedbackMulti-step Reasoning TasksDecision-making Agent Development

Recent Activity

Updated 2 months ago

7 Days

0

30 Days

0

90 Days

20

fix(archon): Wrap router gate in nn.Module for DTensor hook compatibility (#1029)

fishcrap • Mar 16, 2026

978532e

Add opt-in support for Hugging Face kernels (#1033)

lewtun • Mar 16, 2026

8d84d9f

docs: add online proxy mode training guide (#1006)

Zijun Gao • Mar 16, 2026

5634943

Quality

research
Quality
medium
Maturity
research

Categories

Evals & BenchmarkingPrimaryInference & ServingMLOps & InfrastructureDev Tools & AutomationCloud & PlatformsLearning ResourcesSecurity & SafetyFoundation ModelsAI AgentsModel TrainingSafety & AlignmentSearch & KnowledgeOther AI / ML

PM Skills

Cost & EfficiencySafety & AlignmentScale & ReliabilityData & EvaluationDeveloper PlatformAI-Native Architecture

Languages

Python100.0%

Timeline

Project created
Feb 24, 2025
Forked
Mar 13, 2026
Your last push
2 months ago
Upstream last push
16 days ago
Tracked since
Mar 17, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…