TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code
2026 · ICSE 2026 · CCF A, Top-tier SE Conference
Focus: LLM-generated code debugging, trace-driven multi-agent repair
Publications
Selected recent publications reflecting the current research focus on intelligent software engineering, large language models, multi-agent collaboration, and AI-driven systems are listed below. DOI, PDF, code, page numbers, and citation counts are intentionally omitted unless verified in the site data.
Structure-guided function-level code generation with LLMs via UML activity diagrams
2026 · Neurocomputing
Focus: LLM-based code generation, UML activity diagrams, structure-guided generation
Envisioning Intelligent Requirements Engineering via Knowledge-Guided Multi-Agent Collaboration
2025 · ASE 2025 · CCF A, Top-tier SE Conference
Focus: Intelligent requirements engineering, knowledge-guided multi-agent collaboration
FUMMER: A fine-grained self-supervised momentum distillation framework for multimodal recommendation
2024 · Information Processing & Management
Focus: Multimodal recommendation, self-supervised learning
A Dynamic Adaptive and Resource-Allocated Selection Method Based on TOPSIS and VIKOR in Federated Learning
2024 · Neural Processing Letters
Focus: Federated learning, resource allocation
StructAM: Enhancing Address Matching through Semantic Understanding of Structure-aware Information
2024 · LREC-COLING 2024
Authors: Zhang, Zhaoqi; Balsebre, Pasquale; Luo, Siqiang; Hai, Zhen; Huang, Jiangping; and others
Item Type: Conference Paper
Proceedings: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation
Place: Torino, Italy
Date: 2024-05
Focus: Address matching, semantic understanding, structure-aware information
Tags: Semantic Understanding, Address Matching, Structure-aware Information
Publication Records
TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code
Published in ICSE 2026, 2026
LLM-generated code debugging, trace-driven multi-agent repair.
Recommended citation: Jiangping Huang, Wenguang Ye, Weisong Sun, Jian Zhang, Mingyue Zhang, and Yang Liu. "TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code." ICSE 2026.
Structure-guided function-level code generation with LLMs via UML activity diagrams
Published in Neurocomputing, 2026
LLM-based code generation, UML activity diagrams, structure-guided generation.
Recommended citation: "Structure-guided function-level code generation with LLMs via UML activity diagrams." Neurocomputing, 2026.
Envisioning Intelligent Requirements Engineering via Knowledge-Guided Multi-Agent Collaboration
Published in ASE 2025, 2025
Intelligent requirements engineering, knowledge-guided multi-agent collaboration.
Recommended citation: Jiangping Huang, Dongmin Jin, Weisong Sun, Yang Liu, and Zhi Jin. "Envisioning Intelligent Requirements Engineering via Knowledge-Guided Multi-Agent Collaboration." ASE 2025.
StructAM: Enhancing Address Matching through Semantic Understanding of Structure-aware Information
Published in LREC-COLING 2024, 2024
Address matching, semantic understanding, structure-aware information.
Recommended citation: Zhang, Zhaoqi; Balsebre, Pasquale; Luo, Siqiang; Hai, Zhen; Huang, Jiangping; and others. "StructAM: Enhancing Address Matching through Semantic Understanding of Structure-aware Information." Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, Torino, Italy, 2024-05.
FUMMER: A fine-grained self-supervised momentum distillation framework for multimodal recommendation
Published in Information Processing & Management, 2024
Multimodal recommendation, self-supervised learning.
Recommended citation: "FUMMER: A fine-grained self-supervised momentum distillation framework for multimodal recommendation." Information Processing & Management, 2024.
A Dynamic Adaptive and Resource-Allocated Selection Method Based on TOPSIS and VIKOR in Federated Learning
Published in Neural Processing Letters, 2024
Federated learning, resource allocation.
Recommended citation: "A Dynamic Adaptive and Resource-Allocated Selection Method Based on TOPSIS and VIKOR in Federated Learning." Neural Processing Letters, 2024.