AReaL Project

Reinforcement learning infrastructure designed to bridge foundation model training with modern agent-based applications,

[AReaL Project @AReaL_AI]

🙌Welcome to the AReaL community. First tweet.💥Big release.
We are excited to announce the release of AReaL 2.0: RL as Micro-Service! Thanks to the great efforts from the AReaL community and collaborators❤️
In AReaL 2.0, we rebuilt online agent RL around four decoupled components: Training Service, Inference Serivce, WeightUpdate Service and Agent Service.
Change one URL in your existing agent, start learning from production traffic.
#AIAgent #agenticRL #AReaL #LLM
💻 GitHub: https://t.co/RbwexnGixj

[PyTorch @PyTorch]

🎉Ant Group has joined the PyTorch Foundation as a Gold Member. Through @TheInclusionAI, Ant Group works on open models, infrastructure and agent technologies that make AI easier to build and use. It also helped launch and continues to invest in AReaL @AReaL_AI, a PyTorch Ecosystem Landscape project. Welcome, @ant_oss! #PyTorch #OpenSourceAI #inclusiveAGI

[Pony @XiaotengMa1996]

Post-training is becoming continual, online, and self-evolving.

Excited to join the AReaL community with Mind Lab and support AReaL 2.0.

We also contributed AReaL-MinT:
https://t.co/C31lzkask2

#AReaL #MindLab #MinT #AgentRL #ContinualLearning #PEFT

[Binhang Yuan-HKUST-AReaL @Hades317]

Excited to release AReaL 2.0🥳This is our biggest update so far, and the first big milestone after AReaL joined the @PyTorch Ecosystem.
Check out our work: https://t.co/PqG2xJDbYJ
Vision report for self-evolving RL system substrate: https://t.co/penVzqHshU

[AReaL Project @AReaL_AI]

Since joining @PyTorch Ecosystem, this is our first big move.
Open collaboration is central to AReaL 2.0. We're building the infrastructure that lets algorithms learn from real agents in the wild.
The community is now working with ecosystem partners on hardware adaptation, low-resource RL, service-oriented agent training, and reproducible agent RL examples. Come build with us🤗
https://t.co/RbwexnGixj

[AReaL Project @AReaL_AI]

🙌Welcome to the AReaL community. First tweet.💥Big release.
We are excited to announce the release of AReaL 2.0: RL as Micro-Service! Thanks to the great efforts from the AReaL community and collaborators❤️
In AReaL 2.0, we rebuilt online agent RL around four decoupled components: Training Service, Inference Serivce, WeightUpdate Service and Agent Service.
Change one URL in your existing agent, start learning from production traffic.
#AIAgent #agenticRL #AReaL #LLM
💻 GitHub: https://t.co/RbwexnGixj

[AReaL Project @AReaL_AI]

AReaL 2.0 supports:
✅ Hermes Agent: zero-code-change online RL
✅ Claude Code RL: 800 steps, stable gain, anti-collapse via KPop
✅ LoRA RL: lean deployments etc.
Check the details: https://t.co/hdGOHb8fTg