Databricks built a RAG agent it says can handle every kind of enterprise search

Databricks' KARL agent uses reinforcement learning to generalize across six enterprise search behaviors — the problem that breaks most RAG pipelines.
IEEE

RLCoder: Reinforcement Learning for Repository-Level Code Completion

Abstract: Repository-level code completion aims to generate code for unfinished code snippets within the context of a specified repository. Existing approaches mainly rely on retrievalaugmented ...
IEEE

A Reinforcement Learning Environment for Automatic Code Optimization in the MLIR Compiler

Abstract: Code optimization is a crucial task that aims to enhance code performance. However, this process is often tedious and complex, highlighting the necessity for automatic code optimization ...
GitHub

PRIME-RL: Async RL Training at Scale

PRIME-RL is a framework for large-scale asynchronous reinforcement learning. It is designed to be easy-to-use and hackable, yet capable of scaling to 1000+ GPUs. Beyond that, here is why we think you ...
GitHub

Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning

REC-R1 is a general framework that bridges generative large language models (LLMs) and recommendation systems via reinforcement learning. Check the paper here.