Stars
Sparking "Thinking with Videos" via Reinforcement Learning
Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
DeepExperience / DeepAgent
Forked from RUC-NLPIR/DeepAgent🛠️ DeepAgent: A General Reasoning Agent with Scalable Toolsets
Next paradigm for LLM Agent. Unify plan and action through recursive code generation for adaptive, human-like decision-making.
**Deep Video Discovery (DVD)** is a deep-research style question answering agent designed for understanding extra-long videos.
Sparking "Thinking with Videos" via Reinforcement Learning
Task-Aware Agent-driven Prompt Optimization Framework
The development and future prospects of large multimodal reasoning models.
MiniMax-M2, a model built for Max coding & agentic workflows.
🔥 [EMNLP 2025] Official open-source repo for Boosting Multi-modal Keyphrase Prediction with Dynamic Chain-of-Thought in Vision-Language Models
Marco Search Agent for Realistic and Challenging Agentic Search
Search Self-Play: Pushing the Frontier of Agent Capability without Supervision
DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师，自动分析大量数据，一键生成专业分析报告！
🛠️ DeepAgent: A General Reasoning Agent with Scalable Toolsets
MCP-Universe is a comprehensive framework designed for developing, testing, and benchmarking AI agents
[Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
Automatic Video Generation from Scientific Papers
Rubric Reward Model to reduce “miracle steps” and unfaithful CoT in math; SFT+PPO training and verified evaluation.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Scaling Deep Research via Reinforcement Learning in Real-world Environments.
Train your Agent model via our easy and efficient framework