A Survey of Reinforcement Learning for Large Reasoning Models

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

System 2 Reasoning Link Collection

ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning

A rich-documented PyTorch implementation of Carlini-Wagner's L2 attack.

PyTorch implementation of adversarial attacks [torchattacks]

List of papers on hallucination detection in LLMs.

Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

Source code for the X Recommendation Algorithm

.NET language playground

Hebrew Machine and Deep Learning Tutorials

Smart Activation Script

The Roslyn .NET compiler provides C# and Visual Basic languages with rich code analysis APIs.

This repo is used for reviewing new .NET designs.

.NET is a cross-platform runtime for cloud, mobile, desktop, and IoT apps.

Open-source Windows and Office activator featuring HWID, Ohook, TSforge, KMS38, and Online KMS activation methods, along with advanced troubleshooting.

The official repo for the design of the C# programming language