Researcher @ DP Technology // Beijing, China

Guojiang
Zhao

LLM Reasoning · Self-Evolving Agents · AI for Science
M.S. Carnegie Mellon University  ·  B.S. XUPT (Ranked 1st)

Hello! I am Guojiang Zhao (you can also call me Cody), currently working at DP Technology, where I am fortunate to be mentored by Zhifeng Gao and Guolin Ke. My research focuses on molecular design, large language models (LLMs) reasoning, and self-evolving agents. Broadly, my interests lie in AI for Science (AI4S), particularly in molecular and materials generation, virtual characterization, and property prediction. Building on these directions, I am now exploring LLM-driven reasoning frameworks and multi-agent systems to advance intelligent scientific discovery and molecular design.

I received my M.S. in Information Systems Management from Carnegie Mellon University in 2023, and my B.S. in Information and Computing Science (Mathematics track) from Xi'an University of Posts and Telecommunications (XUPT), where I ranked first in my major. In addition, I have had visiting research experiences at the National University of Singapore (NUS) and the Stan Z. Li Lab at Westlake University. Previously, I also gained industry research experience through internships at WeChat (Tencent), and Huawei.

If you are interested in AI4S, LLM reasoning, or intelligent agents, feel free to reach out — I am always happy to discuss and collaborate!

Email Scholar GitHub
Guojiang Zhao
agent_profile.py — running
❯ python agent_profile.py # Initializing researcher profile...   name = "Guojiang Zhao (Cody)" role = "Researcher @ DP Technology" focus = [   "LLM Reasoning",   "Self-Evolving Agents",   "Agentic RL",   "AI for Science", ]   papers = 24 # incl. Nature npj, ICLR Spotlight, ACL×3 1st_auth = 8 # first / co-first author patents = 14 edu = "CMU M.S. · XUPT B.S. #1"   ❯ _
20+Publications
8+CCF-A / SCI Q1
7+First / Co-First
14+Patents
News 🔥
2026.05
Our paper on Geometry-Aware Dual-Engine Framework for Ultralow-Threshold Organic Laser Design has been accepted by CCS Chemistry (JCR Q1, IF: 11.2)!
2026.05
After three years of paper recycling, our work on O2-GEN has finally been accepted by JACS Au!
2026.04
Two papers are accepted by ACL (1 main conference, 1 Findings).
2026.03
We propose SpecXMaster, an intelligent framework leveraging Agentic Reinforcement Learning (RL) for NMR molecular spectral interpretation.
2026.03
One paper is accepted by ICLR 2026 Workshop. Congratulations!
2026.02
Our work on Latent Poincaré Shaping for Agentic RL was featured by 机器之心!
2025.08
One paper is accepted by Nature npj Computational Materials.
2025.08
Excited to release: MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs — a two-stage framework (Mol-SFT + Mol-RL) that shifts LLMs from memorization to interpretable molecular reasoning for chemistry. Enjoy the fun of MolReasoner!
2025.06
One paper is accepted by Journal of Chemical Information and Modeling.
2025.06
One paper is accepted at TRL@ACL 2025 (Oral).
2025.02
Two papers are accepted by ICLR 2025 (1 Spotlight).
2024.09
One paper is accepted by TNNLS.
2024.03
One paper is accepted by TKDE.
2022.08
One paper is accepted by TMLR.
2022.05
One paper is accepted by ACL.
2022.02
One paper is accepted by TNNLS.
🌟 Open Source Contributions
Computer-Use Agents Agent Infrastructure GitHub stars
CLI-Anything
Making all software agent-native. Auto-generates CLI interfaces from any source code — so AI agents can operate any application.
GitHub stars
AI for Science Molecular Representation GitHub stars
Uni-Mol Series
Official repository of Uni-Mol: A Universal 3D Molecular Representation Learning Framework. Leading toolkit for molecular property prediction and generation.
GitHub stars
Reinforcement Learning LLM Reasoning GitHub stars
Awesome-RL-for-LRMs
A curated collection of resources on Reinforcement Learning for Large Reasoning Models (LRMs). Comprehensive survey of RL applications in modern reasoning systems.
GitHub stars
AI for Science Drug Design GitHub stars
CBGBench
A benchmark for generative target-aware molecule design. Unified implementation of 7+ methods for de novo design, linker design, fragment growing, and more. ICLR 2025 Spotlight.
GitHub stars
AI for Science LLM Reasoning GitHub stars
MolReasoner
A two-stage framework (Mol-SFT + Mol-RL) that transitions LLMs from memorization to interpretable molecular reasoning. Achieves state-of-the-art performance in molecule captioning and text-based de novo molecule generation.
GitHub Paper stars
📝 Selected Publications
JACS Au 2026JCR Q1, 2-year IF 2024: 8.7
Fast and Flexible 3D Molecule Design Framework for Novel Organic Optoelectronic Materials
Guojiang Zhao*, Zheng Cheng*, Kele Xu, Tianjiao Wan, Ming Feng, Shuqi Lu, Hongshuai Wang, Zijian Gao, Qi Ou, Liang Hu, Dawei Feng, Zifeng Zhao, Zhifeng Gao
PDFCode
arXiv 2025
MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs
Guojiang Zhao*, Sihang Li*, Zixiang Lu, Zheng Cheng, Haitao Lin, Lirong Wu, Hanchen Xia, Hengxing Cai, Wentao Guo, Hongshuai Wang, Mingjun Xu, Siyu Zhu, Guolin Ke, Linfeng Zhang, Zhifeng Gao
PDFCode
Nature npj Comp. Materials 2025SCI Q1, 5-year IF: 13.0
Virtual Characterization via Knowledge-Enhanced Representation Learning: from Organic Conjugated Molecules to Devices
Guojiang Zhao*, Qi Ou*, Zifeng Zhao*, Shangqian Chen, Haitao Lin, Xiaohong Ji, Zhen Wang, Hongshuai Wang, Hengxing Cai, Lirong Wu, Shuqi Lu, FengTianCi Yang, Yaping Wen, Yingfeng Zhang, Haibo Ma, Zhifeng Gao, Zheng Cheng
PDFCode
JCIM 2025SCI Q1, 2-year IF 2024: 5.3
Data-Driven Parametrization of All-Atom Force Fields for Organic Semiconductors
Guojiang Zhao*, Taiping Hu, Hongshuai Wang, Lirong Wu, Shuqi Lu, FengTianCi Yang, Shangqian Chen, Zhifeng Gao, Xinyan Wang, Zheng Cheng
PDF
ACL 2026 FindingsCCF-A
ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design
Yutang Ge*, Guojiang Zhao*, Sihang Li, Zheng Cheng, Zifeng Zhao, Hanchen Xia, Guolin Ke, Linfeng Zhang, Zhifeng Gao, Yuguang Wang
PDFCode
ICLR 2025★ SpotlightCCF-A
CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph
Haitao Lin*, Guojiang Zhao*, Odin Zhang, Yufei Huang, Lirong Wu, Zicheng Liu, Siyuan Li, Cheng Tan, Zhifeng Gao, Stan Z. Li
PDFCode
ACL 2026CCF-A
T⋆: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning
Hanchen Xia, Baoyou Chen, Yutang Ge, Guojiang Zhao, Siyu Zhu
PDF
ICLR 2026 Workshop
Variational Latent Reasoning Guided by Rendered Chain-of-Thought
Fanmeng Wang, Haotian Liu, Guojiang Zhao, Hongteng Xu, Zhifeng Gao
PDFCode
ICLR 2025CCF-A
A Simple yet Effective DDG Predictor is An Unsupervised Antibody Optimizer and Explainer
Lirong Wu, Yunfan Liu, Haitao Lin, Yufei Huang, Guojiang Zhao, Zhifeng Gao, et al.
PDFCode
arXiv 2026
Latent Poincaré Shaping for Agentic Reinforcement Learning
Hanchen Xia, Baoyou Chen, Zelin Zang, Yutang Ge, Guojiang Zhao, Siyu Zhu
PDFMedia
arXiv 2026
SpecXMaster Technical Report
Yutang Ge, Yaning Cui, Hanzheng Li, Jun-Jie Wang, Fanjie Xu, Jinhan Dong, Yongqi Jin, Dongxu Cui, Peng Jin, Guojiang Zhao, Hengxing Cai, Rong Zhu, Linfeng Zhang, Xiaohong Ji, Zhifeng Gao
PDF
arXiv 2026
Innovator-VL: A Multimodal Large Language Model for Scientific Discovery
Zichen Wen, Boxue Yang, Shuang Chen, et al. (with Guojiang Zhao)
PDF
Preprint 2025
Closed-Loop AI Enables Organic Continuous-Wave Laser
Yun-Tao Ding*, Guojiang Zhao*, Meng-Han Feng, Pei-Wei Si, Jin-Lin Qing, Hui-Qin Zhou, Yan-Ting Zhang, Xiao Chen, Wenjie Zhang, Zhangyue Yin, Wen-Jing Sun, Xue Jia, Ya-Ting Wang, Bing Sun, Yong Huo, Yamin Zhang, Guolin Ke, Linfeng Zhang, Chun-Lin Sun, Bowen Liu, Qi Ou, Zhifeng Gao, Zhigang Shuai, Hao-Li Zhang
PDFCode
TRL@ACL 2025OralCCF-A
R3: "This is My SQL, Are You With Me?" A Consensus-Based Multi-Agent System for Text-to-SQL Tasks
Hanchen Xia, Feng Jiang, Naihao Deng, Cunxiang Wang, Guojiang Zhao, Rada Mihalcea, Yue Zhang
PDF
TNNLS 2024SCI Q1, IF: 8.9, CCF-B
Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting
Lirong Wu, Haitao Lin, Guojiang Zhao, Cheng Tan, Stan Z. Li
PDFCode
TKDE 2024SCI Q1, IF: 10.4, CCF-A
A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation
Lirong Wu, Haitao Lin, Zhangyang Gao, Guojiang Zhao, Stan Z. Li
PDFCode
arXiv 2023
Uni-QSAR: An Auto-ML Tool for Molecular Property Prediction
Zhifeng Gao, Xiaohong Ji, Guojiang Zhao, Hongshuai Wang, Hang Zheng, Guolin Ke, Linfeng Zhang
PDF
TNNLS 2022SCI Q1, IF: 8.9, CCF-B
Deep Clustering and Visualization for End-to-End High-Dimensional Data Analysis
Lirong Wu, Lifan Yuan, Guojiang Zhao, Haitao Lin, Stan Z. Li
PDFCode
TMLR 2022
Exploring Generative Neural Temporal Point Process
Haitao Lin, Lirong Wu, Guojiang Zhao, Pai Liu, Stan Z. Li
PDFCode
ACL 2022CCF-A
Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings
Jiangbin Zheng, Yile Wang, Ge Wang, Jun Xia, Yufei Huang, Guojiang Zhao, Yue Zhang, Stan Z. Li
PDF
Full list → Google Scholar ↗
🤝 Academic Services
Conference Reviewer
  • ICLR CCF-A
  • ICML CCF-A
  • ACL CCF-A
  • AAAI CCF-A
Journal Reviewer
  • Archives of Computational Methods in Engineering JCR Q1 · IF 11.9
Honors & Awards
  • European Good Design Award — Bronze 2022
  • National Scholarship 国家奖学金 2019
📑 Standards
  • General Technical Specification for Health and Wellness Robots (康养机器人通用技术规范) First author — T/YGAZXH 4—2025, released on 2025.01.25
🔖 Patents
🤖 Robotics-related Patents
  • A health monitoring intelligent robot management system and method (一种应用于健康监测的智能化机器人管理系统及方法) China Patent: ZL202410898780.X, authorized 2025.01.10
  • A health management system and method based on multi-source data acquisition and analysis (基于多源数据采集分析的健康管理系统及方法) China & Japan Patent: ZL202411580423.5, authorized 2025.01.07
  • A multimodal human-machine collaboration interaction system and method (多模态下人机协同交互系统及方法) China & U.S. Patent: ZL202411348336.7 / 12322393, authorized 2024.12.13
  • Unmanned sightseeing interactive robot (无人驾驶观光交互机器人) China Patent: ZL202110339122.3, authorized 2023.04.07
  • Preschool education robot (幼教机器人) China Patent: ZL202120388786.9, authorized 2023.05.23
  • Unmanned sightseeing interactive robot (design patent) (无人驾驶观光交互机器人) China Patent: ZL202130732575.3, authorized 2022.08.05
  • Smart robot control GUI for display screen panels (显示屏幕面板的智能机器人控制交互图形用户界面) China Patent: 2021301914491, authorized 2021.11.05
  • A robotic arm motion control device (一种机器人手臂动作控制装置) China Patent: ZL202020755905.0, authorized 2021.01.01
  • Robot (JZR360260) China Patent: ZL202030213430.8, authorized 2020.11.06
🔬 AI4S-related Patents
  • A method and device for processing charge carrier mobility prediction models (一种电荷载流子迁移率预测模型的处理方法和装置) China Patent: ZL202411310786.7, filed 2024
  • A system for molecular generation tasks based on autoregressive models (一种基于自回归模型处理分子生成任务的系统) China Patent: ZL202411319712.X, filed 2024
  • A molecular conformation generator with conditional constraints (一种带有条件约束的分子构象生成器的处理方法和装置) China Patent: ZL202411310784.8, filed 2024
  • A method and device for generating multi-ring conjugated system molecules (一种多环共轭体系分子生成模型的处理方法和装置) China Patent: ZL202411345540.3, filed 2024
  • Stacked ensemble model for molecular property prediction (用于分子属性预测的堆叠式集成模型的处理方法和装置) PCT Patent: PCT/CN2023/130061
🌍 Visitor Map