2025 Sky Camp

Run LLMs, AI, and Batch Jobs Anywhere

SkyPilot is a framework for running LLMs, AI, and batch jobs on any cloud, offering maximum cost savings, highest GPU availability, and managed execution.

Turning any GitHub Repository into a Programming Agent Environment

While Large Language Models’ coding capabilities have advanced rapidly, corresponding evaluation benchmarks on real-world programming setups are yet to catch up. Building …

A High-Throughput and Memory-Efficient Inference and Serving Engine for LLMs

High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the

Train Real-World Long-Horizon Agents via Reinforcement Learning

Most existing RL frameworks are optimized for tasks that involve stateless interactions over short horizons, such as search-augmented reasoning or simple code execution. In contrast,

A Query Engine for Data Processing with LLMs

The powerful semantic capabilities of modern language models (LMs) create exciting opportunities for building AI-based analytics systems that reason over vast knowledge corpora …

Multi-Agent System Failure Taxonomy

While the formal definition of agents remains debated, this study defines an LLM-based agent as an artificial entity with three components: (1) prompt specifications (initial state), (2) conversation trace …

Automatically Analyze your Model Traces

If you train models, build agents, or tune prompts, you’re familiar with the unsightly practice of manually reading through pages of mind numbing AI reasoning, tool …

Compiling Declarative Language Model Calls into Self-Improving Pipelines

DSPy is a framework for algorithmically optimizing LM prompts and weights, especially when LMs are used one or more times within a pipeline. To

System Optimization through Reflective Text Evolution

GEPA (Genetic-Pareto) is a framework for optimizing arbitrary systems composed of text components—like AI prompts, code snippets, or textual specs—against any evaluation metric. It employs LLMs to reflect

Democratizing Reinforcement Learning for LLMs

We are a open-source initiative spawning from the Sky Computing Lab to democratize reinforcement learning (RL) techniques and develop scalable systems for large language models (LLMs) …