I am a Ph.D. student at Penn State, advised by Prof. Minhao Cheng. I am currently a research intern at ByteDance Seed, where I work on long-context pretraining, spanning model architecture, load balancing, data, and evaluation. On the side, I open-source long-horizon autonomous agents. Sleepless Agent, released two months before OpenClaw, is a long-horizon autonomous agent for research. Overall, I aim to build practical coding agents from two angles: designing the long-horizon agent on top of a base LLM, and strengthening the atomic LLM capabilities the agent depends on.
Before Penn State, I received my B.Sc. in Mathematics, Physics, and Computer Science from UESTC. My earlier research centered on graph machine learning, including fairness, counterfactual reasoning, and self-supervised learning on graphs. That perspective continues to shape how I think about the data and structure side of language models. In the summer of 2025, I was an Applied Scientist Intern at Amazon, where I worked on long-horizon autonomous agents.
I'm a big fan of open-source. Most of what I build lives on GitHub, and my papers are tracked on Google Scholar. I'm generally happy to chat about research, agents, or open-source, so feel free to drop me a line at gzjz07 [at] outlook [dot] com, or find me on X, LinkedIn, or WeChat (JZGZ07).
Code Repos
- Sleepless Agent (820★) is a long-horizon autonomous agent for research. Released 2 months before OpenClaw.
- ContextAgent (74★) is a lightweight multi-agent framework for context-driven system design.
Publications
See below for papers I've worked on. You can also check out my Google Scholar profile.
-
Coded State for Long-Horizon Language Agents
Zhimeng Guo, Hangfan Zhang, Teng Xiao, Siyuan Xu, Huaisheng Zhu, Shijie Zhou, Minhao Cheng. -
ContextAgent: Lightweight Context-Driven Multi-Agent System Design
Zhimeng Guo, Hangfan Zhang, Siyuan Xu, Huaisheng Zhu, Teng Xiao, Jingyi Chen, Minhao Cheng. -
Adaptive Code Watermarking Through Reinforcement Learning
Zhimeng Guo, Huaisheng Zhu, Siyuan Xu, Hangfan Zhang, Teng Xiao, Minhao Cheng.@inproceedings{guo2026adaptive, title = {Adaptive Code Watermarking Through Reinforcement Learning}, author = {Guo, Zhimeng and Zhu, Huaisheng and Xu, Siyuan and Zhang, Hangfan and Xiao, Teng and Cheng, Minhao}, booktitle = {Forty-third International Conference on Machine Learning}, year = {2026} } -
Simple Denoising Diffusion Language Models
Huaisheng Zhu, Zhengyu Chen, Shijie Zhou, Zhihui Xie, Yige Yuan, Shiqi Chen, Zhimeng Guo, Siyuan Xu, Hangfan Zhang, Vasant Honavar, Teng Xiao. -
Self-Aware Reinforcement Learning for Improving LLMs with Minimal Data
Hangfan Zhang, Siyuan Xu, Zhimeng Guo, Huaisheng Zhu, Shicheng Liu, Xinrun Wang, Qiaosheng Zhang, Yang Chen, Peng Ye, Lei Bai, Shuyue Hu. -
Do Audio LLMs Really LISTEN, or Just Transcribe? Measuring Lexical vs. Acoustic Emotion Cues Reliance
Jingyi Chen, Zhimeng Guo, Jiyun Chun, Pichao Wang, Andrew Perrault, Micha Elsner.
-
Practical and Effective Code Watermarking for Large Language Models
Zhimeng Guo, Minhao Cheng.@inproceedings{guo2025practical, title = {Practical and Effective Code Watermarking for Large Language Models}, author = {Guo, Zhimeng and Cheng, Minhao}, booktitle = {The Thirty-ninth Annual Conference on Neural Information Processing Systems}, year = {2025}, url = {https://openreview.net/forum?id=RpE4HeuX69} } -
Simple Distillation for One-Step Diffusion Models
Huaisheng Zhu, Teng Xiao, Shijie Zhou, Zhimeng Guo, Hangfan Zhang, Siyuan Xu, Vasant G. Honavar. -
Reinforcement Learning for Large Language Models via Group Preference Reward Shaping
Huaisheng Zhu, Siyuan Xu, Hangfan Zhang, Teng Xiao, Zhimeng Guo, Shijie Zhou, Shuyue Hu, Vasant G. Honavar.
Experience
- ByteDance Seed, Research Intern (Jan 2026 — Present). Long context pretraining.
- Amazon, Applied Scientist Intern (Jun 2025 — Sep 2025). Long-horizon automatic agent.
- Penn State, Ph.D. student in Informatics (2021 — Present). Advised by Prof. Minhao Cheng.
- UESTC, B.Sc. in Mathematics, Physics, and Computer Science (Sep 2017 — Jun 2021).
Awards & Services
- Reviewer for AISTATS, NeurIPS, ICLR, ICML.
- Outstanding Undergraduate Thesis Award.
- Ranked 46 / 4103 in IEEEXtreme 24-Hour Programming Competition.
- Meritorious Winner, 2019 MCM/ICM Mathematical Contest in Modeling.