Reinforcement Learning for LLMs and Agents
Improve your models' performance and reliability on any task.
1. Define your task
Submit prompts and create custom reward functions that evaluate model outputs on your specific tasks.
2. Run RL
Our platform applies the reinforcement learning algorithms behind Deepseek R1 to optimize your model's performance.
3. Get Better Results
Deploy your improved model that's been optimized based on your specific reward criteria.
Specialized Models for Your Approach
Tired of tuning prompts to make generic models do what you want? Train your model to be good at your task—all you need to tell us is what's good and what's bad. We'll make the model perform reliably.
Learn how we taught a research agent to use tools › Beating o3-mini on performance and costAlready know what you want?
Start training in seconds.
Built for researchers and developers
$ pip install runrl
from runrl import RunRL
client = RunRL()
client.create_run(
model_name="runrl/dsp",
prompt_file="math_prompts.jsonl",
reward_file="steganography_reward.py",
)
Specialized Enterprise Agents
Custom reward development
We'll work with you to define targets, measure your agent performance, and help you outperform closed models.
World-class RL expertise
Work directly with our RL research team on your problems.
Integration with your stack
Seamlessly deploy your optimized agents into your existing infrastructure and workflows.