Lists (2)
Stars
DeerFlow is a community-driven framework for deep research, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
A scalable graph learning toolkit for extremely large graph datasets. (WWW'22, 🏆 Best Student Paper Award)
Official repository for paper "DeepCritic: Deliberate Critique with Large Language Models"
Agentic RAG R1 Framework via Reinforcement Learning
🌐 WebWalker: Benchmarking LLMs in Web Traversal
A Comprehensive Library for Memory of LLM-based Agents.
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge ba…
verl: Volcano Engine Reinforcement Learning for LLMs
MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts
Scaling Deep Research via Reinforcement Learning in Real-world Environments.
Official PyTorch implementation for "Large Language Diffusion Models"
Code of paper 'UltraIF: Advancing Instruction Following from the Wild'.
程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).
Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.
A comprehensive benchmark and evaluation toolkit, LIFBench, for assessing instruction-following capabilities and stability of large language models (LLMs) in long-context scenarios.
Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities
OctoTools: An agentic framework with extensible tools for complex reasoning
🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability
II-Researcher: a new open-source framework designed to aid building search / research agents
程序员延寿指南 | A programmer's guide to live longer
An Open-source RL System from ByteDance Seed and Tsinghua AIR