MiroMindAI / MiroTrainLinks
MiroTrain is an efficient and algorithm-first framework for post-training large agentic models.
☆88Updated last month
Alternatives and similar repositories for MiroTrain
Users that are interested in MiroTrain are comparing it to the libraries listed below
Sorting:
- MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.☆236Updated 2 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆163Updated last month
- The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning☆317Updated 4 months ago
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆109Updated 4 months ago
- ☆72Updated 3 months ago
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆155Updated 4 months ago
- G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning☆85Updated 4 months ago
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆292Updated 2 weeks ago
- The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆167Updated 3 months ago
- Official Implementation of ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay☆130Updated 4 months ago
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆157Updated 2 weeks ago
- repo for paper https://arxiv.org/abs/2504.13837☆196Updated 3 months ago
- ☆59Updated 4 months ago
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models (NeurIPS 2025)☆152Updated 3 weeks ago
- official code for "BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning"☆36Updated 8 months ago
- ☆96Updated 3 weeks ago
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding☆57Updated 9 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆176Updated 2 months ago
- MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources☆197Updated 2 weeks 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…☆326Updated last month
- "what, how, where, and how well? a survey on test-time scaling in large language models" repository☆70Updated this week
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆179Updated 4 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆190Updated 6 months ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆113Updated 4 months ago
- MiroThinker is open-source agentic models trained for deep research and complex tool use scenarios.☆412Updated last week
- REverse-Engineered Reasoning for Open-Ended Generation☆69Updated last month
- Towards a Unified View of Large Language Model Post-Training☆152Updated last month
- Multimodal RewardBench☆53Updated 7 months ago
- RM-R1: Unleashing the Reasoning Potential of Reward Models☆138Updated 3 months ago
- [NeurIPS'25 Spotlight] ARM: Adaptive Reasoning Model☆54Updated 2 months ago