Qi Chen
I am a Member of Technical Staff (Agent Research Lead) at Moonlake AI, working on 3D coding agents. My research focuses on agent evaluation, evaluation-driven agent design, and recursive self-improvement. I’m particularly interested in coding as a universal interface for extending agents’ capabilities from the digital world to the physical world.
Previously, I worked on coding agents at AWS Agentic AI. I received my Ph.D. in Applied Mathematics from Peking University (2023), advised by Prof. Zhouchen Lin, Prof. Yisen Wang, and Prof. Jiansheng Yang. My doctoral research focused on scaling deep equilibrium models to Transformer architectures and large-scale datasets.
Always happy to connect and explore opportunities to collaborate.
news
| Aug 2026 | Led the launch of Moonlake’s 3D Agent for robotics simulation. |
|---|---|
| Apr 2026 | Designed and built an internal benchmark for evaluating game-development agents. |
| Mar 2026 | Joined Moonlake AI as a Member of Technical Staff (Research), working on 3D coding agents. |
| Dec 2025 | Led evaluation and benchmark development for Kiro autonomous agent, featured in Matt Garman’s keynote at AWS re:Invent 2025. |
| Dec 2024 | Initiated and led the launch of Amazon Q Developer’s /doc agent, featured in Matt Garman’s keynote at AWS re:Invent 2024. |
selected publications
- AAAICREAD: A Classification-Restoration Framework with Error Adaptive Discretization for Watch Time Prediction in Video Recommender SystemsIn AAAI, 2024
- TIPEquilibrium Image Denoising with Implicit DifferentiationIEEE Transactions on Image Processing, 2023
- BigDataEfficient and Scalable Implicit Graph Neural Networks with Virtual EquilibriumIn IEEE International Conference on Big Data (Big Data), 2022