MiroMindAI / MiroThinkerLinks
MiroThinker is open-source agentic models trained for deep research and complex tool use scenarios.
☆704Updated this week
Alternatives and similar repositories for MiroThinker
Users that are interested in MiroThinker are comparing it to the libraries listed below
Sorting:
- Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414☆459Updated last month
- ☆505Updated 2 months ago
- [COLM’25] DeepRetrieval — 🔥 The First Search Agent Trained by On-Policy Reinforcement Learning☆671Updated last month
- When Agent Becomes the Scientist – Building Closed-Loop System from Hypothesis to Verification☆786Updated last month
- ☆323Updated 2 months ago
- Train your Agent model via our easy and efficient framework☆1,622Updated this week
- adds Sequence Parallelism into LLaMA-Factory☆591Updated last month
- [EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)☆786Updated 2 weeks ago
- MiroMind Research Agent: Fully Open-Source Deep Research Agent with Reproducible State-of-the-Art Performance on FutureX, GAIA, HLE, Brow…☆852Updated last week
- ✨ A synthetic dataset generation framework that produces diverse coding questions and verifiable solutions - all in one framwork☆289Updated 2 months ago
- (ACL-2025 main conference) SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automat…☆303Updated 2 months ago
- [NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS☆1,224Updated 2 months ago
- ✨✨R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning☆270Updated 6 months ago
- A scalable, end-to-end training pipeline for general-purpose agents☆361Updated 4 months ago
- ☆918Updated this week
- QwQ is the reasoning model series developed by Qwen team, Alibaba Cloud.☆527Updated 7 months ago
- Complex Reasoning Rag System, Agentic Rag System☆203Updated last week
- [ICML 2025] "SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator"☆555Updated 3 months ago
- Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI (Kunlun Inc.), specializing in vision-language reasoning.☆2,949Updated this week
- [NeurIPS 2025] A Graph-based LLM Framework for Real-world SE Tasks☆490Updated 2 months ago
- Codebase for Iterative DPO Using Rule-based Rewards☆261Updated 7 months ago
- 🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents☆2,197Updated last week
- Think Beyond Images☆516Updated 2 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…☆439Updated 2 weeks ago
- Tree Search for LLM Agent Reinforcement Learning☆241Updated last month
- A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in Large Language Models☆97Updated last week
- [EMNLP2025] From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery☆260Updated 2 weeks ago
- The official implementation of the ICML 2024 paper "MemoryLLM: Towards Self-Updatable Large Language Models" and "M+: Extending MemoryLLM…☆255Updated 3 months ago
- (ICML'25 Outstanding) CollabLLM: From Passive Responders to Active Collaborators☆256Updated last month
- R1-like Computer-use Agent☆87Updated 8 months ago