Yuanfu Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuanfu Sun has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Qiaoyu Tan
New York University Shanghai, Shanghai, China
5 shared publications - Jing Ma
Case Western Reserve University
2 shared publications Yi Fang
Department of Computer Science New York University ( Shanghai
2 shared publicationsZhengnan Ma
Department of Computer Science New York University ( Shanghai
2 shared publicationsDongzhe Fan
Department of Computer Science New York University ( Shanghai
1 shared publication- Jiajin Liu
Department of Computer Science New York University ( Shanghai
1 shared publication
Latest Publications
- Open Access
- 21 April 2026
- Published by Springer Nature
- p. 189-208
Recommender Systems for STEM Education Research
- 21 April 2026
- Published by Springer Nature
- p. 189-208
Open AccessRecommender Systems for STEM Education Research
- Open Access
GraphSearch: Agentic Search-Augmented Reasoning for Zero-Shot Graph Learning
Recent advances in search-augmented large reasoning models (LRMs) enable the retrieval of external knowledge to reduce hallucinations in multistep reasoning. However, their ability to operate on graph-structured data, prevalent in domains such as e-commerce, social networks, and scientific citations, remains underexplored. Unlike plain text corpora, graphs encode rich topological signals that connect related entities and can serve as valuable priors for retrieval, enabling more targeted search and improved reasoning efficiency. Yet, effectively leveraging such structure poses unique challenges, including the difficulty of generating graph-expressive queries and ensuring reliable retrieval that balances structural and semantic relevance. To address this gap, we introduce GraphSearch, the first framework that extends search-augmented reasoning to graph learning, enabling zero-shot graph learning without task-specific fine-tuning. GraphSearch combines a Graph-aware Query Planner, which disentangles search space (e.g., 1-hop, multi-hop, or global neighbors) from semantic queries, with a Graph-aware Retriever, which constructs candidate sets based on topology and ranks them using a hybrid scoring function. We further instantiate two traversal modes: GraphSearch-R, which recursively expands neighborhoods hop by hop, and GraphSearch-F, which flexibly retrieves across local and global neighborhoods without hop constraints. Extensive experiments across diverse benchmarks show that GraphSearch achieves competitive or even superior performance compared to supervised graph learning methods, setting state-of-the-art results in zero-shot node classification and link prediction. These findings position GraphSearch as a flexible and generalizable paradigm for agentic reasoning over graphs.
Open AccessGraphSearch: Agentic Search-Augmented Reasoning for Zero-Shot Graph Learning
Recent advances in search-augmented large reasoning models (LRMs) enable the retrieval of external knowledge to reduce hallucinations in multistep reasoning. However, their ability to operate on graph-structured data, prevalent in domains such as e-commerce, social networks, and scientific citations, remains underexplored. Unlike plain text corpora, graphs encode rich topological signals that connect related entities and can serve as valuable priors for retrieval, enabling more targeted search and improved reasoning efficiency. Yet, effectively leveraging such structure poses unique challenges, including the difficulty of generating graph-expressive queries and ensuring reliable retrieval that balances structural and semantic relevance. To address this gap, we introduce GraphSearch, the first framework that extends search-augmented reasoning to graph learning, enabling zero-shot graph learning without task-specific fine-tuning. GraphSearch combines a Graph-aware Query Planner, which disentangles search space (e.g., 1-hop, multi-hop, or global neighbors) from semantic queries, with a Graph-aware Retriever, which constructs candidate sets based on topology and ranks them using a hybrid scoring function. We further instantiate two traversal modes: GraphSearch-R, which recursively expands neighborhoods hop by hop, and GraphSearch-F, which flexibly retrieves across local and global neighborhoods without hop constraints. Extensive experiments across diverse benchmarks show that GraphSearch achieves competitive or even superior performance compared to supervised graph learning methods, setting state-of-the-art results in zero-shot node classification and link prediction. These findings position GraphSearch as a flexible and generalizable paradigm for agentic reasoning over graphs.
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5912-5923
TrustGLM: Evaluating the Robustness of GraphLLMs Against Prompt, Text, and Structure Attacks
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5912-5923
Open AccessTrustGLM: Evaluating the Robustness of GraphLLMs Against Prompt, Text, and Structure Attacks
- Open Access
GraphICL: Unlocking Graph Learning Potential in LLMs through Structured Prompt Design
The growing importance of textual and relational systems has driven interest in enhancing large language models (LLMs) for graph-structured data, particularly Text-Attributed Graphs (TAGs), where samples are represented by textual descriptions interconnected by edges. While research has largely focused on developing specialized graph LLMs through task-specific instruction tuning, a comprehensive benchmark for evaluating LLMs solely through prompt design remains surprisingly absent. Without such a carefully crafted evaluation benchmark, most if not all, tailored graph LLMs are compared against general LLMs using simplistic queries (e.g., zero-shot reasoning with LLaMA), which can potentially camouflage many advantages as well as unexpected predicaments of them. To achieve more general evaluations and unveil the true potential of LLMs for graph tasks, we introduce Graph In-context Learning (GraphICL) Benchmark, a comprehensive benchmark comprising novel prompt templates designed to capture graph structure and handle limited label knowledge. Our systematic evaluation shows that general-purpose LLMs equipped with our GraphICL outperform state-of-the-art specialized graph LLMs and graph neural network models in resource-constrained settings and out-of-domain tasks. These findings highlight the significant potential of prompt engineering to enhance LLM performance on graph learning tasks without training and offer a strong baseline for advancing research in graph LLMs.
Open AccessGraphICL: Unlocking Graph Learning Potential in LLMs through Structured Prompt Design
The growing importance of textual and relational systems has driven interest in enhancing large language models (LLMs) for graph-structured data, particularly Text-Attributed Graphs (TAGs), where samples are represented by textual descriptions interconnected by edges. While research has largely focused on developing specialized graph LLMs through task-specific instruction tuning, a comprehensive benchmark for evaluating LLMs solely through prompt design remains surprisingly absent. Without such a carefully crafted evaluation benchmark, most if not all, tailored graph LLMs are compared against general LLMs using simplistic queries (e.g., zero-shot reasoning with LLaMA), which can potentially camouflage many advantages as well as unexpected predicaments of them. To achieve more general evaluations and unveil the true potential of LLMs for graph tasks, we introduce Graph In-context Learning (GraphICL) Benchmark, a comprehensive benchmark comprising novel prompt templates designed to capture graph structure and handle limited label knowledge. Our systematic evaluation shows that general-purpose LLMs equipped with our GraphICL outperform state-of-the-art specialized graph LLMs and graph neural network models in resource-constrained settings and out-of-domain tasks. These findings highlight the significant potential of prompt engineering to enhance LLM performance on graph learning tasks without training and offer a strong baseline for advancing research in graph LLMs.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 2440-2459
GraphICL: Unlocking Graph Learning Potential in LLMs through Structured Prompt Design
Yuanfu Sun, Zhengnan Ma, Yi Fang, Jing Ma, Qiaoyu Tan. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 2440-2459
Open AccessGraphICL: Unlocking Graph Learning Potential in LLMs through Structured Prompt Design
Yuanfu Sun, Zhengnan Ma, Yi Fang, Jing Ma, Qiaoyu Tan. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.