研究方向
作为人工智能研究员加入 MiroMind,致力于大语言模型、多模态人工智能系统与智能体框架的前沿研究,聚焦于构建具备实际应用价值的人工智能方案,以推动推理与智能能力的边界。
当前研究课题
- 智能体与推理模型
- 如何构建能够高效推理并与复杂环境交互的人工智能智能体?
- 何种架构能够支持大语言模型完成稳健的多步推理?
项目
- MiroFlow — MiroMind 自研智能体框架(GitHub 星标数 1.8k)。github.com/MiroMindAI/MiroFlow
- MiroThinker — MiroMind 自研智能体模型(GitHub 星标数 1.5k)。github.com/MiroMindAI/MiroThinker
- MiroMind-M1 — MiroMind 自研基础推理模型。github.com/MiroMindAI/MiroMind-M1
发表论文
- MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling — Technical Report 2025
- MiroFlow: Towards High-Performance, Robust, and Open-Source Reproducible Agent Framework for General Research — Technical Report 2025
- MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization — Technical Report 2025
- 100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models — Technical Review 2025