MiroMindAI / MiroThinkerLinks
MiroThinker is a series of open-source agentic models trained for deep research and complex tool use scenarios.
☆1,266Updated last week
Alternatives and similar repositories for MiroThinker
Users that are interested in MiroThinker are comparing it to the libraries listed below
Sorting:
- MiroMind Research Agent: Fully Open-Source Deep Research Agent with Reproducible State-of-the-Art Performance on FutureX, GAIA, HLE, Brow…☆1,449Updated 2 weeks ago
- [COLM’25] DeepRetrieval — 🔥 The First Search Agent Trained by On-Policy Reinforcement Learning☆677Updated 2 months ago
- ☆524Updated 2 months ago
- When Agent Becomes the Scientist – Building Closed-Loop System from Hypothesis to Verification☆817Updated 3 weeks ago
- Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414☆471Updated last month
- [EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)☆788Updated last month
- ☆330Updated 3 months ago
- (ACL-2025 main conference) SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automat…☆307Updated 3 months ago
- RepoMaster: The open-source AI agent that masters GitHub. It turns any code repository into a powerful tool, achieving a new level of aut…☆457Updated last month
- [NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS☆1,229Updated 2 months ago
- adds Sequence Parallelism into LLaMA-Factory☆598Updated 2 months ago
- Train your Agent model via our easy and efficient framework☆1,642Updated last week
- Complex Reasoning Rag System, Agentic Rag System☆229Updated 2 weeks ago
- [NeurIPS 2025] A Graph-based LLM Framework for Real-world SE Tasks☆495Updated 2 months ago
- ☆937Updated this week
- ✨ A synthetic dataset generation framework that produces diverse coding questions and verifiable solutions - all in one framwork☆297Updated 3 months ago
- QwQ is the reasoning model series developed by Qwen team, Alibaba Cloud.☆528Updated 8 months ago
- [ICML 2025] "SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator"☆556Updated 4 months ago
- Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/g…☆312Updated last week
- ScaleCUA is the open-sourced computer use agents that can operate on corss-platform environments (Windows, macOS, Ubuntu, Android).☆967Updated 2 months ago
- Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI (Kunlun Inc.), specializing in vision-language reasoning.☆3,123Updated last week
- A scalable, end-to-end training pipeline for general-purpose agents☆361Updated 5 months ago
- Tree Search for LLM Agent Reinforcement Learning☆250Updated 2 months ago
- ✨✨R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning☆272Updated 7 months ago
- [Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models☆1,155Updated last month
- ☆247Updated last month
- A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.☆669Updated this week
- LightAgent: Lightweight AI agent framework with memory, tools & tree-of-thought. Supports multi-agent collaboration, self-learning, and m…☆431Updated 3 weeks ago
- [EMNLP2025] From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery☆278Updated last month
- 🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents☆2,337Updated last week