MiroMindAI / MiroThinkerLinks
MiroThinker is open-source agentic models trained for deep research and complex tool use scenarios.
☆274Updated this week
Alternatives and similar repositories for MiroThinker
Users that are interested in MiroThinker are comparing it to the libraries listed below
Sorting:
- MiroFlow is an agent framework that simplifies the development of complex, multi-agent systems. Build, manage, and scale your AI agents w…☆384Updated this week
- MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.☆223Updated 3 weeks ago
- Implementation for OAgents: An Empirical Study of Building Effective Agents☆242Updated this week
- ☆293Updated 3 months ago
- ☆122Updated this week
- ☆89Updated 3 months ago
- MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search too…☆296Updated last week
- The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆163Updated last month
- Efficient Agent Training for Computer Use☆129Updated 2 months ago
- AutoCoA (Automatic generation of Chain-of-Action) is an agent model framework that enhances the multi-turn tool usage capability of reaso…☆125Updated 5 months ago
- ☆161Updated 4 months ago
- ☆79Updated 4 months ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆113Updated 3 months ago
- A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning☆246Updated 2 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains☆163Updated 2 months ago
- Official implementation for "ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization"☆82Updated 3 months ago
- Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414☆327Updated this week
- Test-time preferenece optimization (ICML 2025).☆162Updated 3 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆141Updated this week
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆150Updated last month
- ☆341Updated this week
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆239Updated 3 months ago
- 🔧Tool-Star: Empowering LLM-brained Multi-Tool Reasoner via Reinforcement Learning☆243Updated 3 weeks ago
- [ACL 2025] Code and data for OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis☆157Updated last month
- MiroTrain is an efficient and algorithm-first framework for post-training large agentic models.☆77Updated this week
- Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.☆305Updated last week
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆190Updated 5 months ago
- ☆96Updated 3 months ago
- ☆407Updated last month
- ☆197Updated last week