CoreWeave Arena: Serverless inference and serverless RL

Summary

CoreWeave Arena provides a platform for validating AI workloads end-to-end—including pre-training, building agents, and post-training via Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL)—before committing to production. The presentation demonstrates how Serverless Inference and Serverless RL can be used to build and improve AI agents, specifically showing how RL can significantly boost agent performance and reliability, which is then deployed using CoreWeave Serverless Inference.

Technical details

• CoreWeave Arena 0s

  A platform for end-to-end validation of AI workloads, supporting pre-training, agent building, and post-training (SFT/RL).

• Serverless Inference 80s

  Allows access to various open-source models for running agents (e.g., Quen 314b instruct) and generating outputs from natural language prompts.

• Agent Tracing and Signals 120s

  Agent performance is tracked using collected traces. Custom signals can be configured to flag specific issues, such as 'misalignment between the user request and the SQL statement that generates the distribution list.'

• Serverless RL Workflow 170s

  Users can run RL jobs, monitor progress via dashboards, and track best-performing model checkpoints. The process involves creating an environment, writing agent code, and defining training scenarios.

• Model Deployment 280s

  After RL optimization, the specific model weights and a model URI are accessed via the 'artifacts' tab, providing sample Python code for integration using Coreweave Serverless Inference.

Mentioned resources

• CoreWeave ARENA (Platform)
• CoreWeave Serverless Inference (Product)
• Serverless Inference docs (Documentation)

Channel & topics

• Weights & Biases
• AI Agents
• Reinforcement Learning (RL)
• Large Language Models (LLMs)
• Serverless Computing
• Prompt Engineering
• Model Validation
• CoreWeave ARENA
• CoreWeave Serverless Inference
• Serverless Inference docs