Welcome! I’m Junjie HUANG, a Ph.D. candidate at the Chinese University of Hong Kong, advised by Prof. Michael R. Lyu. I am currently a Research Intern at ByteDance Seed, mentored by Dr. Wanjun Zhong. Previously, I received my Bachelor’s degree in 2020 and Master’s degree in 2023 from Beihang University, advised by Prof. Ke Xu.
I am currently working on general agents, building strong agent harness and training general agentic LLM. Besides, I am also interested in code agents. Discussions and collaborations are warmly welcomed!
🚀 I will be on the industry job market this year (expected to graduate in 2027). Feel free to reach out at my email/wechat (id: junjieh9) if you would like to share opportunities, collaborate, or just chat :)
Highlights
- Agent Foundation Model (@ ByteDance Seed)
- Agent Foundation Models: improving the MCP tool-use ability of Seed 2.0, evaluated on MCPMark, BFCL, and τ-bench.
- Environment Synthesis: scaling real-world environment synthesis for evolving general agent intelligence with Agent-World — a self-evolving training arena spanning 2,000+ environments, 19K+ tools, 20 categories, and evaluated on 23 benchmarks.
- General Agent: improving end-to-end task-completion ability of agents, deployed as Doubao Super Mode 豆包超能模式.
- AI for Code and Software Engineering (Ph.D.)
- Code Intelligence: CodeXGLUE (NeurIPS 2021), CoSQA (ACL 2021), CoCoNote (ASE 2024)
- LLM for Software Engineering: iKnow (ASE 2025, 🏆 ACM SIGSOFT Distinguished Paper), CodeAD (arXiv 2025), LUNAR (FSE 2025), LoFI (ISSRE 2024), FaultProfIT (ICSE-SEIP 2024)
- MLSys: PreServe (ICSE 2026, 🏆 ACM SIGSOFT Distinguished Paper), L4 (FSE 2025)
🔥 News
- 2026.04: 🚀 We released Agent-World — a self-evolving training arena scaling real-world environment synthesis for general agent intelligence (2,000+ environments, 19K+ tools, evaluated on 23 benchmarks). [website] [paper]
- 2026.02: 🚀 Seed 2.0 is released — I contributed to its MCP tool-use agent ability. [model card]
- 2025.12: 🌱 I joined ByteDance Seed as a Research Intern, working on Agent Foundation Models.
- 2025.10: 🎉 Our PreServe is accepted by ICSE 2026 and won the 🏆 ACM SIGSOFT Distinguished Paper Award!
- 2025.08: 🎉 Our iKnow is accepted by ASE 2025 and won the 🏆 ACM SIGSOFT Distinguished Paper Award!
- 2025.04: 🎉 Our LUNAR and L4 are accepted by FSE 2025!
- 2024.08: 🎉 Our CoCoNote is accepted by ASE 2024!
- 2024.07: 🎉 Our LoFI is accepted by ISSRE 2024!
📝 Selected Publications
(* indicates equal contribution, full publication list)
Agent Foundation Model
-
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence (arXiv 2026)
Guanting Dong, Junting Lu, Junjie Huang, Wanjun Zhong, Longxiang Liu, Shijue Huang, Zhenyu Li, Yang Zhao, Xiaoshuai Song, Xiaoxi Li, Jiajie Jin, Yutao Zhu, Hanbin Wang, Fangyu Lei, Qinyu Luo, Mingyang Chen, Zehui Chen, Jiazhan Feng, Ji-Rong Wen, Zhicheng Dou
[website] [paper] -
Seed 2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity (Seed Technical Report, 2026)
ByteDance Seed Team (Junjie Huang as a core contributor of general agent ability)
[model card]
LLM for Software Engineering
-
iKnow: an Intent-Guided Chatbot for Cloud Operations with Retrieval-Augmented Generation (ASE 2025) 🏆 ACM SIGSOFT Distinguished Paper Award
Junjie Huang, Yuedong Zhong, Guangba Yu, Zhihan Jiang, Minzhi Yan, Wenfei Luan, Tianyu Yang, Rui Ren, Michael R. Lyu
[code] [paper] -
CodeAD: Synthesize Code of Rules for Log-based Anomaly Detection with LLMs (Under Review)
Junjie Huang, Junjie Huang, Minghua He, Jinyang Liu, Yintong Huo, Domenico Bianculli, Michael R. Lyu
[paper] -
No More Labelled Examples? An Unsupervised Log Parser with LLMs (FSE 2025)
Junjie Huang, Zhihan Jiang, Zhuangbin Chen, Michael R. Lyu
[code] [paper] -
Demystifying and Extracting Fault-indicating Information from Logs for Failure Diagnosis (ISSRE 2024)
Junjie Huang, Zhihan Jiang, Jinyang Liu, Yintong Huo, Jiazhen Gu, Zhuangbin Chen, Cong Feng, Hui Dong, Zengyin Yang, Michael R. Lyu
[code] [paper] -
FaultProfIT: Hierarchical Fault Profiling of Incident Tickets in Large-scale Cloud Systems (ICSE-SEIP 2024)
Junjie Huang, Jinyang Liu, Zhuangbin Chen, Zhihan Jiang, Yichen Li, Jiazhen Gu, Cong Feng, Zengyin Yang, Yongqiang Yang, Michael R. Lyu
[paper]
MLSys
-
PreServe: Intelligent Management for LMaaS Systems via Hierarchical Prediction (ICSE 2026) 🏆 ACM SIGSOFT Distinguished Paper Award
Zhihan Jiang, Yujie Huang, Guangba Yu, Junjie Huang, Jiazhen Gu, Michael R. Lyu
[code] [paper] -
L4: Diagnosing Large-scale LLM Training Failures via Automated Log Analysis (FSE 2025)
Zhihan Jiang, Junjie Huang, Guangba Yu, Zhuangbin Chen, Yichen Li, Renyi Zhong, Cong Feng, Yongqiang Yang, Zengyin Yang, Michael R. Lyu
[paper]
Code Intelligence
-
Contextualized Data-Wrangling Code Generation in Computational Notebooks (ASE 2024)
Junjie Huang, Daya Guo, Chenglong Wang, Jiazhen Gu, Shuai Lu, Jeevana Priya Inala, Cong Yan, Jianfeng Gao, Nan Duan, Michael R. Lyu
[code] [paper] -
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation (NeurIPS 2021)
Shuai Lu*, Daya Guo*, Shuo Ren*, Junjie Huang*, Alexey Svyatkovskiy, Ambrosio Blanco, Colin Clement, Dawn Drain, Daxin Jiang, Duyu Tang, Ge Li, Lidong Zhou, Linjun Shou, Long Zhou, Michele Tufano, Ming Gong, Ming Zhou, Nan Duan, Neel Sundaresan, Shao Kun Deng, Shengyu Fu, Shujie Liu
[code] [paper] -
CoSQA: 20,000+ Web Queries for Code Search and Question Answering (ACL 2021)
Junjie Huang, Duyu Tang, Linjun Shou, Ming Gong, Ke Xu, Daxin Jiang, Ming Zhou, Nan Duan
[data] [code] [paper] -
Execution-based Evaluation for Data Science Code Generation Models (EMNLP 2022 DaSH)
Junjie Huang, Chenglong Wang, Jipeng Zhang, Cong Yan, Haotian Cui, Jeevana Priya Inala, Colin Clement, Nan Duan, Jianfeng Gao
[code] [paper]
🏃 Experiences
- 2025.12 - Present: Research Intern, Agent Post-Training Team at ByteDance Seed. Mentors: Dr. Wanjun Zhong.
- 2020.06 - 2022.06: Research Intern, NLC at Microsoft Research Asia, Mentor: Dr. Nan Duan.
- 2020.05 - 2021.06: Research Intern, NLC at Microsoft Research Asia, Mentor: Dr. Duyu Tang.
- 2018.09 - 2020.04: Research Assistant, NLP Lab at Tsinghua University, Advisor: Prof. Zhiyuan Liu.
🎖 Honors and Awards
- 2026 🏆 ACM SIGSOFT Distinguished Paper Award, ICSE’26 (for PreServe)
- 2025 🏆 ACM SIGSOFT Distinguished Paper Award, ASE’25 (for iKnow)
- 2023-2027 CUHK Vice-Chancellor’s PhD Scholarship, The Chinese University of Hong Kong
- 2020-2021 National Scholarship, Ministry of Education of the P.R. China
- 2017-2018 National Scholarship, Ministry of Education of the P.R. China
- 2019 Yuanhang Scholarship, Beihang University
💻 Activities
💼 Services
- Program Committee:
- 2025: APSEC’25
- Sub-Reviewer:
- 2025: ICSE, ISSTA, DSN, ASE, FSE
- 2024: FSE, ISSTA, ISSRE
- 2023: FSE, DSN
📞 Contact
Please feel free to contact me via my email (left) if you are interested in our papers, my experience, or you just have any problem on research which I may help.