Code and Data for Tau-Bench

Next paradigm for LLM Agent. Unify plan and action through recursive code generation for adaptive, human-like decision-making.

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

Open-source unified multimodal model

"AI-Trader: Can AI Beat the Market?" Live Trading Bench: https://ai4trade.ai

Contrastive Language-Audio Pretraining

(Netflix 2025) Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning

Contexts Optical Compression

Official inference framework for 1-bit LLMs

"LightAgent: Lightweight and Cost-Effective Mobile Agents"

"LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"

The best ChatGPT that $100 can buy.

"DeepResearch-Eval: An End-to-End Evaluation Framework for DeepResearch Systems"

Official repo for NeurIPS 2025: Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis

Quantile Advantage Estimation for Entropy-Safe Reasoning

[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.

Wan: Open and Advanced Large-Scale Video Generative Models

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

[WWW'25 Oral] Large Language Models Empowered Personalized Web Agents.

Youtu-GraphRAG boosts cost efficiency, inference accuracy, and cross-domain adaptability, pushing the boundaries of performance in complex QA.

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

[CVPR 2025] FLAIR: VLM with Fine-grained Language-informed Image Representations

"VideoRAG: Chat with Your Videos"

Reference PyTorch implementation and models for DINOv3

[Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems