Skip to content
View yzh3434's full-sized avatar
3 followers · 2 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report yzh3434

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
yzh3434/README.md

Banner

👋 Hello there!

version profile views followers stars mood

👨🏻‍💻 About Me

🎓 南京大学 人工智能学院 计算机科学与技术专业 研一在读

🔬 研究方向: 多智能体路径规划

💼 正在寻找 2026 暑期 大模型应用相关实习

✍️ 业余爱好: 健身、阅读

💬 欢迎就 RAG、MAPF、LLM Agent 等话题交流

✉️ 邮箱: yzh1580708947@gmail.com

🎯 Current Focus

探索多智能体路径规划(MAPF)的新型问题

以及 RAG 系统在垂直领域的工程化落地。

🛠 Tech Stack

Python C C++ Java ROS LangChain LangGraph Milvus Neo4j Docker Git GitHub Linux

📊 GitHub Stats

Stats Top Langs

📫 How to reach me

Gmail WeChat

Pinned Loading

  1. graphrag-cooking-assistant graphrag-cooking-assistant Public

    基于 Datawhale All-in-RAG（C9）二次开发，构建 Neo4j 图 + Milvus 向量的图RAG 烹饪问答系统。完成四项改进：BM25+RRF 融合、父文档回填、智能路由（规则短路→function-calling）、CRAG 网络纠错；自建 120 题（含 20 道OOD数据）四层评测闭环，其中两项改进已合并入原开源项目。

    Python 2

  2. agent-control-flow-eval agent-control-flow-eval Public

    对比四种大模型智能体控制流（Direct/CoT/ReAct/Reflexion）在 GSM8K 与 HotpotQA 上的任务成功率、交互轮数与 token 开销。

    Python