Yinjie Wang

photo.png
About Me

I am a PhD student at the University of Chicago, working with Professor Victor Veitch and Professor Mengdi Wang. I currently focus on reinforcement learning for digital agents, while collaborating closely with Seed Pretrain Lab and Princeton AI Lab.

Before that, I graduated from the School of Gifted Young at USTC, where I majored in Math, ranked first in Probability and Statistics Track. I published first-author paper in top theoretical statistics journal Biometrika.

I love open-source projects, see my real-time RL project, OpenClaw-RL (also first open-source RL framework supports CLI/GUI/SWE/tool-use agents) and RLAnything , co-evolve RL for LLM coders CURE , and RL for diffusion large language models dLLM-RL (first open-source post-training framework for DLM). My research has been supported by ByteDance Seed, Thinking Machines and Fireworks AI.

Agentic RL / Post-training
View full
  1. OpenClaw-RL: Train Any Agent Simply by Talking
    Yinjie Wang, Xuyang Chen, Xiaolong Jin, and 2 more authors
    Real-time RL & RL for digital (CLI/GUI/SWE/Tool-call) Agents, 18 invited talks
  2. RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
    Yinjie Wang, Tianbao Xie, Ke Shen, and 2 more authors
    ICML 2026
  3. Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
    Yinjie Wang, Ling Yang, Bowen Li, and 3 more authors
    ICLR 2026, Gave talk at DeepMind & NVIDIA
  4. Co-evolving LLM Coder and Unit Tester via Reinforcement Learning
    Yinjie Wang, Ling Yang, Ye Tian, and 2 more authors
    Neurips 2025 Spotlight
  5. MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation
    Ye Tian, Ling Yang, Jiongfan Yang, and 10 more authors
    ICLR 2026
  6. Variational Co-Evolution via Reinforcement Learning
    Qiahao Zheng, Hancong Jin, Junbo Niu, and 3 more authors
    COLM 2026
  7. Reinforcement Learning for Multimodal Diffusion Language Models via Bidimensional Trajectory and Thought Optimization
    Bowen Li, Yinjie Wang, Yunzhi Zhang, and 5 more authors
    ECCV 2026
  8. Automated Hierarchical Graph Construction for Multi-source Electronic Health Records
    Yinjie Wang, Doudou Zhou, Yue Liu, and 2 more authors
    Gave talk at Harvard University
Theoretical Statistics
  1. Nonparametric Inference for Balance in Signed Networks
    Yinjie Wang*, Xuyang Chen*, and Weijing Tang
    Biometrika 2026 / In charge of most theorems