RepoClassBench
RepoClassBench (RCB): is a repository-level code-generation benchmark. Retrieve-RepoTools-Reflect (RRR) is a framework for code generation using Language Models (LLMs) with static-analysis tools in an agent setup.
Tracing the path to self-adapting AI agents
Introducing Trace, Microsoft and Stanford University’s novel AI optimization framework, now available as a Python library. Trace adapts dynamically and optimizes a wide range of applications from language models to robot control.
Generative AI in Real-World Workplaces
Trace
Trace is a new AutoDiff-like tool for training AI systems end-to-end with general feedback (like numerical rewards or losses, natural language text, compiler errors, etc.). Trace generalizes the back-propagation algorithm by capturing and propagating an…
AgentInstruct Methodology
Demo explaining the AgentInstruct methodology outlined in the paper “AgentInstruct: Toward Generative Teaching with Agentic Flows”