GitHub

verl: Volcano Engine Reinforcement Learning for LLMs

verl is a flexible, efficient and production-ready RL training library for large language models (LLMs). verl is the open-source version of HybridFlow: A Flexible and Efficient RLHF Framework paper.
IEEE

Aligning Crowd-Sourced Human Feedback for Reinforcement Learning on Code Generation by ...

Abstract: This paper studies how AI-assisted programming and large language models (LLM) improve software developers' ability via AI tools (LLM agents) like Github Copilot and Amazon CodeWhisperer, ...
IEEE

Adaptive Modulation and Coding in 5G Networks with Deep Learning

Abstract: As part of the present work, it aims to examine the use of deep learning in the improvement of AMC in 5G networks. While traditional AMC methods like the ones mentioned above are applicable ...
Microsoft

Agent Lightning: Adding reinforcement learning to AI agents without code rewrites

AI agents are reshaping software development, from writing code to carrying out complex instructions. Yet LLM-based agents are prone to errors and often perform poorly on complicated, multi-step tasks ...