Shangheng Du
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Shangheng Du has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Jianwen Sun
Central China Normal University
5 shared publications - Xiaoxuan Shen
Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, China
5 shared publications - Qing Li
Central China Normal University, Wuhan, China
4 shared publications - Sannyuya Liu
Central China Normal University
4 shared publications - Ruxia Liang
The National Engineering Research Center of Educational Big Data; the Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, China
2 shared publications - Zongkai Yang
National Engineering Research Center of Educational Big Data, Central China Normal University, Wuhan, China
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 11 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (9) , 1-37
A Survey on the Optimization of Large Language Model-based Agents
With the rapid development of Large Language Models (LLMs), LLM-based agents have been widely adopted in various fields, becoming essential for autonomous decision-making and interactive tasks. However, current work typically relies on prompt design or fine-tuning strategies applied to vanilla LLMs, which often leads to limited effectiveness in complex agent-related environments. Although numerous recent studies have explored various strategies to optimize LLM-based agents for complex agent tasks, a systematic review summarizing and comparing these methods from a holistic perspective remains lacking. In this survey, we provide a comprehensive review of LLM-based agent optimization approaches, categorizing them into parameter-driven and parameter-free methods. We first focus on parameter-driven optimization, covering fine-tuning-based optimization, reinforcement learning-based optimization, and hybrid strategies, analyzing key aspects such as trajectory data construction, reward function design, and optimization algorithms. Additionally, we briefly discuss parameter-free strategies that optimize agent behavior through prompt engineering and external knowledge retrieval. Finally, we summarize the evaluation for agents, review key applications of LLM-based agents, and discuss the major challenges and promising future directions. A curated collection of the surveyed works is provided at https://github.com/YoungDubbyDu/LLM-Agent-Optimization.
- 11 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (9) , 1-37
Top Cited PapersOpen AccessA Survey on the Optimization of Large Language Model-based Agents
With the rapid development of Large Language Models (LLMs), LLM-based agents have been widely adopted in various fields, becoming essential for autonomous decision-making and interactive tasks. However, current work typically relies on prompt design or fine-tuning strategies applied to vanilla LLMs, which often leads to limited effectiveness in complex agent-related environments. Although numerous recent studies have explored various strategies to optimize LLM-based agents for complex agent tasks, a systematic review summarizing and comparing these methods from a holistic perspective remains lacking. In this survey, we provide a comprehensive review of LLM-based agent optimization approaches, categorizing them into parameter-driven and parameter-free methods. We first focus on parameter-driven optimization, covering fine-tuning-based optimization, reinforcement learning-based optimization, and hybrid strategies, analyzing key aspects such as trajectory data construction, reward function design, and optimization algorithms. Additionally, we briefly discuss parameter-free strategies that optimize agent behavior through prompt engineering and external knowledge retrieval. Finally, we summarize the evaluation for agents, review key applications of LLM-based agents, and discuss the major challenges and promising future directions. A curated collection of the surveyed works is provided at https://github.com/YoungDubbyDu/LLM-Agent-Optimization.
- Open Access
- 10 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (1) , 1-28
Question Embedding on Weighted Heterogeneous Information Network for Knowledge Tracing
Knowledge Tracing (KT) aims to predict students’ future performance on answering questions based on their historical exercise sequences. To alleviate the problem of data sparsity in KT, recent works have introduced auxiliary information to mine question similarity, resulting in the enhancement of question embeddings. Nonetheless, there remains a gap in developing an approach that effectively incorporates various forms of auxiliary information, including relational information (e.g., question–student , question–skill relation), relationship attributes (e.g., correctness indicating a student's performance on a question), and node attributes (e.g., student ability ). To tackle this challenge, the Similarity-enhanced Question Embedding (SimQE) method for KT is proposed, with its central feature being the utilization of weighted and attributed meta-paths for extracting question similarity. To capture multi-dimensional question similarity semantics by integrating multiple relations, various meta-paths are constructed for learning question embeddings separately. These embeddings, each encoding different similarity semantics, are then fused to serve the task of KT. To capture finer-grained similarity by leveraging the relationship attributes and node attributes on the meta-paths, the biased random walk algorithm is designed. In addition, the auxiliary node generation method is proposed to capture high-order question similarity. Finally, extensive experiments conducted on six datasets demonstrate that SimQE performs the best among 10 representative question embedding methods. Furthermore, SimQE proves to be more effective in alleviating the problem of data sparsity.
- 10 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (1) , 1-28
Open AccessQuestion Embedding on Weighted Heterogeneous Information Network for Knowledge Tracing
Knowledge Tracing (KT) aims to predict students’ future performance on answering questions based on their historical exercise sequences. To alleviate the problem of data sparsity in KT, recent works have introduced auxiliary information to mine question similarity, resulting in the enhancement of question embeddings. Nonetheless, there remains a gap in developing an approach that effectively incorporates various forms of auxiliary information, including relational information (e.g., question–student , question–skill relation), relationship attributes (e.g., correctness indicating a student's performance on a question), and node attributes (e.g., student ability ). To tackle this challenge, the Similarity-enhanced Question Embedding (SimQE) method for KT is proposed, with its central feature being the utilization of weighted and attributed meta-paths for extracting question similarity. To capture multi-dimensional question similarity semantics by integrating multiple relations, various meta-paths are constructed for learning question embeddings separately. These embeddings, each encoding different similarity semantics, are then fused to serve the task of KT. To capture finer-grained similarity by leveraging the relationship attributes and node attributes on the meta-paths, the biased random walk algorithm is designed. In addition, the auxiliary node generation method is proposed to capture high-order question similarity. Finally, extensive experiments conducted on six datasets demonstrate that SimQE performs the best among 10 representative question embedding methods. Furthermore, SimQE proves to be more effective in alleviating the problem of data sparsity.
- Open Access
- 8 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (2) , 1-28
Heterogeneous Evolution Network Embedding with Temporal Extension for Intelligent Tutoring Systems
Graph embedding (GE) aims to acquire low-dimensional node representations while maintaining the graph’s structural and semantic attributes. Intelligent tutoring systems (ITS) signify a noteworthy achievement in the fusion of AI and education. Utilizing GE to model ITS can elevate their performance in predictive and annotation tasks. Current GE techniques, whether applied to heterogeneous or dynamic graphs, struggle to efficiently model ITS data. The GEs within ITS should retain their semidynamic, independent, and smooth characteristics. This article introduces a heterogeneous evolution network (HEN) for illustrating entities and relations within an ITS. Additionally, we introduce a temporal extension graph neural network (TEGNN) to model both evolving and static nodes within the HEN. In the TEGNN framework, dynamic nodes are initially improved over time through temporal extension (TE), providing an accurate depiction of each learner’s implicit state at each time step. Subsequently, we propose a stochastic temporal pooling (STP) strategy to estimate the embedding sets of all evolving nodes. This effectively enhances model efficiency and usability. Following this, a heterogeneous aggregation network is devised to proficiently extract heterogeneous features from the HEN. This network employs both node-level and relation-level attention mechanisms to craft aggregated node features. To emphasize the superiority of TEGNN, we perform experiments on several real ITS datasets and show that our method significantly outperforms the state-of-the-art approaches. The experiments validate that TE serves as an efficient framework for modeling temporal information in GE, and STP not only accelerates the training process but also enhances the resultant accuracy.
- 8 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (2) , 1-28
Open AccessHeterogeneous Evolution Network Embedding with Temporal Extension for Intelligent Tutoring Systems
Graph embedding (GE) aims to acquire low-dimensional node representations while maintaining the graph’s structural and semantic attributes. Intelligent tutoring systems (ITS) signify a noteworthy achievement in the fusion of AI and education. Utilizing GE to model ITS can elevate their performance in predictive and annotation tasks. Current GE techniques, whether applied to heterogeneous or dynamic graphs, struggle to efficiently model ITS data. The GEs within ITS should retain their semidynamic, independent, and smooth characteristics. This article introduces a heterogeneous evolution network (HEN) for illustrating entities and relations within an ITS. Additionally, we introduce a temporal extension graph neural network (TEGNN) to model both evolving and static nodes within the HEN. In the TEGNN framework, dynamic nodes are initially improved over time through temporal extension (TE), providing an accurate depiction of each learner’s implicit state at each time step. Subsequently, we propose a stochastic temporal pooling (STP) strategy to estimate the embedding sets of all evolving nodes. This effectively enhances model efficiency and usability. Following this, a heterogeneous aggregation network is devised to proficiently extract heterogeneous features from the HEN. This network employs both node-level and relation-level attention mechanisms to craft aggregated node features. To emphasize the superiority of TEGNN, we perform experiments on several real ITS datasets and show that our method significantly outperforms the state-of-the-art approaches. The experiments validate that TE serves as an efficient framework for modeling temporal information in GE, and STP not only accelerates the training process but also enhances the resultant accuracy.
- 2 August 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 278
Document-level relation extraction with hierarchical dependency tree and bridge path
- 2 August 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 278
Document-level relation extraction with hierarchical dependency tree and bridge path
- 11 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (1) , 2838-2847
Weighted Heterogeneous Graph-Based Three-View Contrastive Learning for Knowledge Tracing in Personalized e-Learning Systems
Personalized e-learning systems are applications of consumer electronics in the field of education that provide individualized and adaptive services for users. Knowledge tracing (KT), as a key technology, aims to model learners’ knowledge states through the interactions between learners and learning resources, and predicts their future performance. However, the problem of interaction sparsity in educational resources leads to the fact that simple representations of questions usually fail to accurately capture students’ knowledge states. In this paper, inspired by the data-driven paradigm, we propose a novel knowledge tracing method named weighted heterogeneous graph-based Three-view Contrastive Learning framework for Knowledge Tracing (TCL4KT). Technically, three different view encoders in TCL4KT complement each other to obtain question embeddings with rich information. Specifically, TCL4KT considers the semantic information of higher-order, heterogeneous and the downstream task on a weighted heterogeneous graph of KT to learn high-quality representations. Besides, a meta-path-based positive sample selection strategy and joint contrastive loss are employed to gain better prediction performance. Experimental results on four datasets demonstrate the superiority of TCL4KT over baseline models, and further analysis verifies the effectiveness of our three-view contrastive learning framework.
- 11 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (1) , 2838-2847
Weighted Heterogeneous Graph-Based Three-View Contrastive Learning for Knowledge Tracing in Personalized e-Learning Systems
Personalized e-learning systems are applications of consumer electronics in the field of education that provide individualized and adaptive services for users. Knowledge tracing (KT), as a key technology, aims to model learners’ knowledge states through the interactions between learners and learning resources, and predicts their future performance. However, the problem of interaction sparsity in educational resources leads to the fact that simple representations of questions usually fail to accurately capture students’ knowledge states. In this paper, inspired by the data-driven paradigm, we propose a novel knowledge tracing method named weighted heterogeneous graph-based Three-view Contrastive Learning framework for Knowledge Tracing (TCL4KT). Technically, three different view encoders in TCL4KT complement each other to obtain question embeddings with rich information. Specifically, TCL4KT considers the semantic information of higher-order, heterogeneous and the downstream task on a weighted heterogeneous graph of KT to learn high-quality representations. Besides, a meta-path-based positive sample selection strategy and joint contrastive loss are employed to gain better prediction performance. Experimental results on four datasets demonstrate the superiority of TCL4KT over baseline models, and further analysis verifies the effectiveness of our three-view contrastive learning framework.
- 18 May 2023
- Published by Springer Nature in User Modeling and User-Adapted Interaction
- Vol. 34 (3) , 1-33
Deep adversarial group recommendation with user feature space separation
- 18 May 2023
- Published by Springer Nature in User Modeling and User-Adapted Interaction
- Vol. 34 (3) , 1-33
Deep adversarial group recommendation with user feature space separation
- 29 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (6) , 8653-8667
Autobalanced Multitask Node Embedding Framework for Intelligent Education
Recently, online education has become popular. Many e-learning platforms have been launched with various intelligent services aimed at improving the learning efficiency and effectiveness of learners. Graphs are used to describe the pairwise relations between entities, and the node embedding technique is the foundation of many intelligent services, which have received increasing attention from researchers. However, the graph in the intelligent education scenario has three noteworthy properties, namely, heterogeneity, evolution, and lopsidedness, which makes it challenging to implement ecumenical node embedding methods on it. In this article, an autobalanced multitask node embedding model is proposed, named MNE, and applied to the interaction graph, settling a few actual tasks in intelligent education. More specifically, MNE builds two purpose-built self-supervised node embedding learning tasks for heterogeneous evolutive graphs. Edge-specific reconstruction tasks are built according to the semantic information and properties of the heterogeneous edges, and an evolutive weight regression task is designed, aiding the model to perceive the evolution of learners’ implicit cognitive states. Then, both aleatoric and epistemic uncertainty quantification techniques are introduced, achieving both task-and node-level weight estimation and instructing subtask autobalancing. Experimental results on real-world datasets indicate that the proposed model outperforms the state-of-the-art graph embedding methods on two assessment tasks and demonstrates the validity of the proposed multitask framework and subtask balancing mechanism. Our implementations are available at https://github.com/ccnu-mathits/MNE4HEN.
- 29 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (6) , 8653-8667
Autobalanced Multitask Node Embedding Framework for Intelligent Education
Recently, online education has become popular. Many e-learning platforms have been launched with various intelligent services aimed at improving the learning efficiency and effectiveness of learners. Graphs are used to describe the pairwise relations between entities, and the node embedding technique is the foundation of many intelligent services, which have received increasing attention from researchers. However, the graph in the intelligent education scenario has three noteworthy properties, namely, heterogeneity, evolution, and lopsidedness, which makes it challenging to implement ecumenical node embedding methods on it. In this article, an autobalanced multitask node embedding model is proposed, named MNE, and applied to the interaction graph, settling a few actual tasks in intelligent education. More specifically, MNE builds two purpose-built self-supervised node embedding learning tasks for heterogeneous evolutive graphs. Edge-specific reconstruction tasks are built according to the semantic information and properties of the heterogeneous edges, and an evolutive weight regression task is designed, aiding the model to perceive the evolution of learners’ implicit cognitive states. Then, both aleatoric and epistemic uncertainty quantification techniques are introduced, achieving both task-and node-level weight estimation and instructing subtask autobalancing. Experimental results on real-world datasets indicate that the proposed model outperforms the state-of-the-art graph embedding methods on two assessment tasks and demonstrates the validity of the proposed multitask framework and subtask balancing mechanism. Our implementations are available at https://github.com/ccnu-mathits/MNE4HEN.