ART – a new open-source RL framework for training agents
Hey HN, I wanted to share a new project we've been working on for the last couple of months called ART (https://github.com/OpenPipe/ART). ART is a new open-source framework for training agents using reinforcement learning (RL). RL allows you to train an agent to perform better at any task whose outcome can be measured and quantified. There are many excellent projects focused on training LLMs with RL, such as GRPOTrainer (https://huggingface.co/docs/trl/main/en/grpo_trainer) and verl…
In plain words
ART is an open-source reinforcement learning framework for training agents to perform measurable tasks. It is designed for developers and researchers working with agent-based systems that require multi-turn workflows, such as agents calling tools sequentially and responding to feedback. The framework addresses limitations in existing RL projects by providing better support for complex, iterative agent interactions.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN, I wanted to share a new project we've been working on for the last couple of months called ART (https://github.com/OpenPipe/ART). ART is a new open-source framework for training agents using reinforcement learning (RL). RL allows you to train an agent to perform better at any task whose outcome can be measured and quantified. There are many excellent projects focused on training LLMs with RL, such as GRPOTrainer (https://huggingface.co/docs/trl/main/en/grpo_trainer) and verl (https://github.com/volcengine/verl). We've used these frameworks extensively for customer-facing projects at OpenPipe, but grew frustrated with some key limitations: - Multi-turn workflows, where the agent calls a tool, gets a response, and calls another, are not well supported. This makes them a non-starter for any task that requires an agent to perform a sequence of actions. - Other frameworks typically have low GPU efficiency. They may require multiple H100 GPUs just to train a small 7B parameter model, and aren't able to keep the GPUs busy consistently during both the "rollout" and "training" phases of the training loop. - Existing frameworks are typically not a convenient shape for integrating with existing agentic codebases. Existing trainers expect you to call raw text completion endpoints, and don't automatically provide industry-standard chat completion APIs. ART is designed to address these limitations and make it easy to train high-quality agents. We've also shared many details and practical lessons learned is in this post, which walks through a demo of training an email research agent that outperforms o3 (https://openpipe.ai/blog/art-e-mail-agent). You can also find out more about ART's architecture in our announcement post (https://openpipe.ai/blog/art-trainer-a-new-rl-trainer-for-ag...). Happy to answer any questions you have!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, April 2025
the whole month →- IB
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
- UC
Life & fun · 2025 · filiph.github.io
- IB
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
