Academic Homepage
Ph.D. / Postdoctoral Fellow / Master Supervisor
Assistant Professor, Chongqing University of Posts and Telecommunications (CQUPT)
Building intelligent software systems through large language models, multi-agent collaboration, and cognitive reasoning.
About
Jiangping Huang is a faculty member and master supervisor at Chongqing University of Posts and Telecommunications (CQUPT). He received his Ph.D. in Computer Science from Wuhan University and worked as a postdoctoral research fellow at Nanyang Technological University, Singapore from 2022 to 2024.
His research lies at the intersection of artificial intelligence, intelligent software engineering, multi-agent systems, and intelligent robotics, with a particular focus on LLM-based software engineering, intelligent requirements engineering, code generation and self-repair, trace-driven debugging, cognitive multi-agent collaboration, and human-AI/robot collaboration.
He has participated in a key project of the National Natural Science Foundation of China, served as a major contributor to several NSFC and national-level projects, and led multiple provincial and ministerial projects. His work has resulted in nearly 20 academic papers, more than 10 national invention patent applications, more than 10 software copyrights, and a Chongqing Science and Technology Progress Award. He also serves as a reviewer for conferences and journals including AAAI, EMNLP, NLPCC, ACM TKDD, and ACM TALLIP.
黄江平，博士、博士后，硕士生导师，博士毕业于武汉大学，曾在新加坡南洋理工大学从事博士后研究，现任重庆邮电大学教师。主要研究方向包括人工智能、智能软件工程与智能机器人，重点关注多智能体系统、智能需求工程、代码生成与自修复、软件逆向工程、认知智能与人机协同等前沿问题。
近年来，围绕大语言模型与多智能体系统赋能软件开发智能化这一主线，持续开展人工智能与软件工程交叉研究。先后参与国家自然科学基金重点项目1项，主研国家自然科学基金面上项目3项、国家社科基金项目1项，主持省部级项目7项。已发表学术论文近20篇，申请国家发明专利10余项，登记软件著作权10余项，获重庆市科技进步奖1项。
Research Vision
My research is organized around intelligent software systems rather than isolated NLP or ML tasks. The goal is to build a closed loop from requirements understanding, code generation, testing, runtime analysis, fault diagnosis, and self-repair to intelligent agents and embodied systems.
以人工智能为核心，以智能软件工程为主阵地，以多智能体与认知机制为方法特色，面向智能机器人和真实应用场景扩展，构建从需求理解、代码生成、运行分析、故障诊断到自我修复的智能软件系统闭环。
Research Areas
This direction studies how LLM-based agents reason, remember, reflect, coordinate, and adapt when solving complex technical tasks. We are especially interested in cognitive multi-agent architectures that divide roles, exchange evidence, recover from failures, and remain trustworthy under uncertainty.
This direction builds AI-driven methods for the full software lifecycle, from requirements analysis to code generation, testing, trace analysis, debugging, repair, and evolution. The emphasis is on verifiable software artifacts, requirement-code-test alignment, and systems that use runtime evidence instead of relying only on generated text.
This direction extends cognitive and collaborative AI toward embodied systems that perceive environments, plan tasks, make decisions, and collaborate with humans. Students can work on language-to-goal grounding, adaptive task planning, human-robot interaction, and intelligent systems that connect software agents with physical or simulated environments.
Selected Recent Publications
ICSE 2026 · CCF A, Top-tier SE Conference
LLM-generated code debugging, trace-driven multi-agent repair
Neurocomputing
LLM-based code generation, UML activity diagrams, structure-guided generation
ASE 2025 · CCF A, Top-tier SE Conference
Intelligent requirements engineering, knowledge-guided multi-agent collaboration
Information Processing & Management
Multimodal recommendation, self-supervised learning
Neural Processing Letters
Federated learning, resource allocation
LREC-COLING 2024
Address matching, semantic understanding, structure-aware information
Research Group
The CSMA Research Group is based at Chongqing University of Posts and Telecommunications (CQUPT) and works on artificial intelligence, intelligent software engineering, multi-agent systems, intelligent robotics, and application-driven intelligent systems.
The group maintains collaboration and academic exchange with universities and research institutions including Nanyang Technological University, Peking University, Wuhan University, and Beihang University.
Cognitive and collaborative intelligence for software, robotics, and real-world AI.
Visit CSMA Research Group Personal updates: https://h-jp.github.ioProspective Students
Highly motivated students who are interested in AI, LLMs, multi-agent systems, intelligent software engineering, and intelligent robotics are welcome to contact me. The group is particularly suitable for students who are willing to engage in real research problems, system building, rigorous experiments, and academic writing.
团队更适合积极主动、愿意持续投入科研和系统开发的同学。对于希望在研究生阶段真正提升科研能力、工程能力和学术表达能力，并有志于发表高水平论文、继续攻读博士或进入高水平研发平台的学生，团队将提供持续指导和支持。
Student Supervision
Multiple undergraduate students received Outstanding Undergraduate Thesis/Design recognition.
Supervised students have continued to graduate study at universities including University of Science and Technology Beijing, University of Electronic Science and Technology of China, Southeast University, Beijing University of Posts and Telecommunications, and Wuhan University.
Graduate student Wenguang Ye works on multi-agent code generation and self-repair and is expected to continue Ph.D. study at Wuhan University.
Recent Updates
Blog / Notes
Research notes, learning methods, mentoring reflections, and academic life. The section is intended to record how research ideas are formed, systems are built, students are trained, and academic judgment is developed over time.
A good AI automation toolchain should move implementation details into reliable workflows while keeping human attention on goals, judgment, and thinking.
Read more好的 AI 自动工具链，应当把重复实现细节沉淀为可靠流程，同时让人的注意力回到目标、判断和真正需要思考的问题上。
Read moreAI coding tools are changing software development from manual editing toward intent expression, review, testing, and repair.
Read moreContact
欢迎对人工智能、大语言模型、多智能体系统、智能软件工程、代码生成与自修复、智能需求工程、智能机器人等方向感兴趣的同学联系交流。
For prospective students: please include your background, research interests, programming experience, and any relevant projects or writing samples when contacting me.