Chenxin Li | 李宸鑫
Hi! I'm Chenxin Li, a final-year Ph.D. candidate at The Chinese University of Hong Kong (CUHK). Before CUHK, I received my master's and bachelor's degrees from Xiamen University, along with a second bachelor's degree in Economics.
My recent interest lies in scaling LLM/VLM agents for digital automation, especially CLI agents for executable computer-use workflows (Claw-Eval-Live, Auto R&D CLI Agent, ODE, HybridClaw) and visual agents for design artifacts (BlenderAgent, PSAgent, Code-to-chart/web). Across these projects, I build agent harnesses, benchmarks, and feedback loops for agent training, making agent behavior more reliable, verifiable, and useful in real-world workflows.
I have interned at ByteDance Seed, Tencent Hunyuan, Tencent AI Lab, Ant Ling, etc. In my spare time, I explore agent-native workflows through 📝 Blogs and 🛠️ OpenAgentLabs. I anticipate graduating in the summer of 2026 and am interested in industrial positions (Profile). Please feel free to reach out via email (chenxinli@link.cuhk.edu.hk) or WeChat (jasonchenxinli).
LinkedIn |
 Scholar |
GitHub |
X |
Blogs |
OpenAgentLabs
🚀 Selected Work [Google Scholar]
* Equal contribution, † Project Leader, ‡ Corresponding author
|
|
|
Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows
Chenxin Li†, Zhengyang Tang, Huangxin Lin, Yunlong Lin, Shijue Huang, Shengyuan Liu, Bowen Ye, Rang Li, Lei Li, Benyou Wang, Yixuan Yuan
[Project] [Paper] [Code]
A live workflow-agent benchmark with refreshable demand signals and verifiable execution traces; 105 tasks across 22 categories, 13 frontier models, top model passes only 66.7%.
|
|
|
Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents
Shijue Huang, Hangyu Guo, Chenxin Li, Junting Lu, Xinyu Geng, Zhaochen Su, Zhenyu Li, Shuang Chen, Hongru Wang, Yi R Fung
[Project] [Paper] [Code]
An on-policy data-evolution framework for visual-native multimodal deep-search agents, using agent rollouts to evolve training data and improve search behavior.
|
🛠️ Open Agent Labs [Organization]
I build agent tools that help people work smarter by turning repetitive, inefficient workflows into AI-native experiences.
|
|
|
IRBlenderAgent: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering
Parker Liu*, Chenxin Li*, Zhengxin Li, Yipeng Wu, Wuyang Li, Zhiqin Yang, Zhenyuan Zhang, Yunlong Lin, Sirui Han, Brandon Y. Feng
NeurIPS 2025
[Project] [Paper] [Code]
An agentic inverse-rendering framework that closes the loop from visual understanding to structured code generation, Blender execution, and environment feedback.
|
🧭 Selected Experience [LinkedIn]
LLM Agent
- ByteDance Seed: Visual coding agent and CLI agent
- Tencent AI Lab: Tool-use and coding agents for Blender manipulation
- Ant Ling: Agent memory and context compression
- AMD: Visual token compression for efficient VLMs
World Model
- Giga AI: World model for embodied brains
- Hedra AI: Omnimodal attention for commercial video generation
Quant
- JoinQuant: Agentic RL for quant alpha-factor mining
|
🎓 Professional Activities
- Workshop Organizer: AIM-FM: Advancements In Foundation Models Towards Intelligent Agents (NeurIPS 2024)
- Talks: "UKAN" at VALSE Summit (Jun 2025) and DAMTP, University of Cambridge (Jul 2024)
- Conference Reviewer: ICLR, NeurIPS, ICML, ACL, CVPR, ICCV, ECCV, EMNLP, AAAI, ACM MM
- Journal Reviewer: Nature Machine Intelligence, PAMI, TIP, DMLR, PR, TNNLS
|
🌱 Hobbies Beyond Work
- Vibe-coding Agent Workflows: I enjoy building agent tools through vibe coding, which has shaped how I think in an increasingly AI-native way.
- Reading: I read history, philosophy, and sociology over the long term. I enjoy reasoning from first principles to anticipate future trends and make my bets accordingly.
- Stock Investment: I see investing as real-world RL: making decisions, receiving feedback, and refining strategies. As agents dramatically amplify productivity, what matters shifts to where we bet our resources and attention.
|
|
