Building reliable agents and writing down how I learn.
I work on AI agent systems that combine multilingual dialogue, tool use, domain reasoning, and memory-augmented retrieval. This site is my public notebook for projects, AI paper notes, learning notes, and technical writing.
Write Markdown, publish pages.
The site is folder-driven. Add Markdown files under writing or projects, and the website automatically renders list pages and detail pages.
Blogs, paper notes, and learning notes.
How to Evaluate an AI Agent Beyond Accuracy
A practical note on why production agents need evaluation beyond simple answer accuracy.
Learning Note: Agent Memory Is Not Just More Context
A short learning note about why agent memory should be selective, structured, and useful for future decisions.
Reading Template: Memory-augmented Agents
A reusable structure for reading papers about memory, retrieval, and long-horizon agents.
Reading with judgment.
Small notes, useful memory.
Project evidence, not just a resume.
Production-level Multilingual Customer Service Agent
A desensitized project note about building multilingual LLM agents for overseas customer-service scenarios.
Reasoning Data Distillation and Post-training Optimization
A desensitized project note about constructing reasoning data and improving model behavior through post-training.
Memory-augmented Multimodal RAG for Long-horizon Agents
A research-oriented project direction connecting memory, multimodal retrieval, and reliable long-horizon interaction.
联系方式
Email, GitHub, and LinkedIn are grouped here. Keep the top navigation clean, while still making professional links easy to find.