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

Deepagents is an agent harness built on langchain and langgraph. Deep agents are equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - making them well-equipped …

verl: Volcano Engine Reinforcement Learning for LLMs

Large-scale language modeling tutorials with PyTorch

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

[ACL 2025] DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Nano vLLM

Demo of a customer service use case implemented with the OpenAI Agents SDK

Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

Official Repository of Absolute Zero Reasoner

Implementation of Sesame's Conversational Speech Model for Hugging Face Transformers

LUCY: Linguistic Understanding and Control Yielding Early Stage of Her

A live stream development of RL tunning for LLM agents

Simple RL training for reasoning

Fully open reproduction of DeepSeek-R1

Recipes to scale inference-time compute of open models

Accepted LLM Papers in NeurIPS 2024

A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.