Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University

A RL Framework for multi LLM agent system

A Gym for Agentic LLMs

Resources and paper list for 'Scaling Environments for Agents'. This repository accompanies our survey on how environments contribute to agent intelligence.

🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation feedback, cross-platform NVIDIA/AMD, Kernelbook + KernelBench

A Survey of Reinforcement Learning for Large Reasoning Models

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!

Minimal and annotated implementations of key ideas from modern deep learning research.

基于Python的开源量化交易平台开发框架

基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版

🌟100+ 原创 LLM / RL 原理图📚，《大模型算法》作者巨献！💥（100+ LLM/RL Algorithm Maps ）

A scalable, end-to-end training pipeline for general-purpose agents

TradingAgents: Multi-Agents LLM Financial Trading Framework

KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA (+ more DSLs)

SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning

Scaling RL on advanced reasoning models

slime is an LLM post-training framework for RL Scaling.

Nano vLLM

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

Awesome List for Agentic RL

这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。

A Framework for LLM-based Multi-Agent Reinforced Training and Inference

The official code repo for "Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets" in ICML 2025.

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

科技爱好者周刊，每周五发布

An example of gin