DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)

verl: Volcano Engine Reinforcement Learning for LLMs

Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents

Open-source implementation of AlphaEvolve

easydou

改进过的rule版本

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Benchmarking LLMs' Gaming Ability in Multi-Agent Environments

A framework for few-shot evaluation of language models.

This repository contains a collection of resources and papers on Diffusion Models for RL, accompanying the paper "Diffusion Models for Reinforcement Learning: A Survey"

A curated list of Diffusion Model in RL resources (continually updated)

This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs!

This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

Official PyTorch implementation for "Large Language Diffusion Models"

PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437

Source code of the ICML24 paper "Self-Composing Policies for Scalable Continual Reinforcement Learning" (selected for oral presentation)

A Doudizhu reinforcement learning AI

C++/python fight the lord with pybind11 (强化学习AI斗地主), Accepted to AIIDE-2020

基于DouZero定制AI实战欢乐斗地主

将DouZero用于欢乐斗地主自动化

Douzero with ResNet and GPU support for Windows

Evaluation of PerfectDou vs DouZero ResNet.