In this episode, we speak with Kyle Corbitt, co-founder and CEO of OpenPip, recently acquired by CoreWeave, to explore the evolving role of reinforcement learning in building smarter, more reliable AI agents. Kyle shares the journey of OpenPipe from supervised fine-tuning to developing ART (Agent Reinforcement Trainer), their open-source RL toolkit designed to train AI agents that can think, adapt, and perform with greater autonomy. The discussion spans technical insights, practical applications, startup lessons from YC’s Startup School, and the future of agent-based AI systems.

Key Topics Covered:
Why reinforcement learning is gaining attention in modern Agent development
The transition from supervised fine-tuning (SFT) to reinforcement learning (RL)
Practical differences between RL and SFT, including weight movement and model reliability
OpenPipe’s approach with ART: supporting multi-turn agent training and tool use
How ART differs from OpenAI’s RFT implementation
The importance of consistent agent behavior in production and how RL helps
Avoiding reward hacking and the role of Ruler, OpenPipe’s LLM-based judging system
Cost-efficiency strategies in RL training using serverless infrastructure
OpenPipe’s long-term vision for self-improving agents
Advice for AI startup founders on building in a rapidly evolving ecosystem

Memorable Outtakes:
On why reinforcement learning matters now:
"What RL does… is it actually lets you solve the reliability problem. You can make your smaller model significantly more reliable—even more performant in your domain—through RL." 
On OpenAI's RFT vs. OpenPipe’s ART:
"What you're missing [with OpenAI's RFT API] is the ability to define custom tools and multi-turn agent behavior. With ART, you own the code, define the tools, and have full control of the reward signal."  

Guest information, Mentioned Tools and Projects:
Kyle Corbitt: https://www.linkedin.com/in/kcorbitt/
OpenPipe: https://openpipe.ai 
OpenPipe GitHub: https://github.com/OpenPipe/OpenPipe
ART (Agent Reinforcement Trainer): https://github.com/OpenPipe/ART
Ruler: LLM-based evaluation tool for training agents (part of the ART package): https://openpipe.ai/blog/ruler
DeepSeek R1: https://api-docs.deepseek.com/
OpenAI RFT: https://platform.openai.com/docs/guides/reinforcement-fine-tuning
SkyPilot: scale AI workloads  https://github.com/skypilot-org/skypilot

Notable Blog Posts:
Ruler (LLM-as-a-Judge): https://www.openpipe.ai/blog/ruler
Reward Hacking Post: https://www.openpipe.ai/blog/reward-hacking
Serverless RL Backend: https://www.openpipe.ai/blog/serverless-rl
ART Trainer: A New RL Trainer for Agents: https://openpipe.ai/blog/art-trainer-a-new-rl-trainer-for-agents

Sponsored by:
🔥 ODSC AI West 2025 – The Leading AI Training Conference
Join us in San Francisco from October 28th–30th for expert-led sessions on generative AI, LLMOps, and AI-driven automation.
Use the code podcast for 10% off any ticket.
Learn more: https://odsc.ai


Training Agents with Reinforcement Learning: Kyle Corbitt

With Ai X Podcast, Open Data Science Conference (ODSC) brings its vast experience in building community and its knowledge of the data science and AI fields to the podcast platform. The interests and challenges of the data science community are wide ranging. To reflect this Ai X Podcast will offer a similarly wide range of content, from one-on-one interviews with leading experts, to career talks, to educational interviews, to profiles of AI Startup Founders. Join us every two weeks to discover what’s going on in the data science community.

Find more ODSC lightning interviews, webinars, live trainings, certifications, bootcamps here - https://aiplus.training/  
Don't miss out on this exciting opportunity to expand your knowledge and stay ahead of the curve.

Training Agents with Reinforcement Learning: Kyle Corbitt

ODSC's Ai X Podcast