XINJI MAI / OPEN SOURCE开源工作
Projects项目
Systems, models, and benchmarks I have contributed to. Explore the code and the corresponding papers.我参与的系统、模型与评测基准,以及对应的代码仓库和论文。
SELF-EVOLVING AGENTS自进化智能体
AgentEvolver
Combines self-questioning, self-navigating, and self-attributing to help agents learn from their own experience.结合自主提问、自主探索与自主归因,让智能体从自身经验中持续学习。
TOOL-INTERACTIVE REINFORCEMENT LEARNING工具交互强化学习
Agentic RL Scaling Law
Asynchronous reinforcement learning and tool interaction for spontaneous Python execution and mathematical reasoning.支持异步强化学习与工具交互,让模型自主生成、执行 Python 代码,探索数学推理能力的规模化规律。
TRADITIONAL CHINESE MEDICINE中医大语言模型
CMLM-ZhongJing
An open-source language model for Traditional Chinese Medicine, with a framework for model training and evaluation.开源中医大语言模型,提供模型训练与评估框架。