MiroMindAI / MiroRLLinks
MiroRL is an MCP-first reinforcement learning framework for deep research agent.
☆141Updated this week
Alternatives and similar repositories for MiroRL
Users that are interested in MiroRL are comparing it to the libraries listed below
Sorting:
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆181Updated 3 weeks ago
- ☆74Updated 2 weeks ago
- ☆274Updated 3 months ago
- ☆207Updated 6 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆190Updated 5 months ago
- A version of verl to support tool use☆341Updated last 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
- A Comprehensive Survey on Long Context Language Modeling☆180Updated last month
- ☆197Updated last week
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆248Updated 3 months ago
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆81Updated 2 months ago
- ☆198Updated 4 months ago
- ☆313Updated 3 months ago
- Async pipelined version of Verl☆117Updated 4 months ago
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆150Updated last month
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆245Updated 4 months ago
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆128Updated 4 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆167Updated last month
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆138Updated 4 months ago
- ☆65Updated 9 months ago
- A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architect…☆64Updated 3 months ago
- Extrapolating RLVR to General Domains without Verifiers☆146Updated 3 weeks ago
- Reproducing R1 for Code with Reliable Rewards☆251Updated 3 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆285Updated last month
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆101Updated 3 weeks ago
- ☆327Updated last month
- ☆161Updated 4 months ago
- MiroTrain is an efficient and algorithm-first framework for post-training large agentic models.☆77Updated this week
- WideSearch: Benchmarking Agentic Broad Info-Seeking☆80Updated 3 weeks ago
- ☆238Updated this week