Selected Publications

Survey & Tutorials

• Minhua Lin, Zongyu Wu, Zhichao Xu, Hui Liu, Xianfeng Tang, Qi He, Charu Aggarwal, Hui Liu, Xiang Zhang, Suhang Wang. “A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications” (Preprint) [paper, project page]
• Fali Wang, Minhua Lin, Yao Ma, Hui Liu, Xianfeng Tang, Qi He, Jiliang Tang, Jian Pei, Suhang Wang. “A Tutorial on Small Language Models in the Era of Large Language Models: Architecture, Capabilities, and Trustworthiness” (KDD 2025) [paper]
• Zhichao Hou, Minhua Lin, MohamadAli Torkamani, Suhang Wang, Xiaorui Liu. “Adversarial Robustness in Graph Neural Networks: Recent Advances and New Frontier” In 11th IEEE International Conference on Data Science and Advanced Analytics (DSAA 2024) [paper]
• Haitong Luo, Fali Wang, Weiyao Zhang, Xianren Zhang, Zhiwei Zhang, Tianxiang Zhao, Minhua Lin, Jiahao Zhang, Hui Liu, Xianfeng Tang, Qi He, Suhang Wang, Xuying Meng, and Yujun Zhang. “Graphs for LLMs: A Survey of Graph-Assisted Large Language Models” In the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)

Preprints

• Minhua Lin*, Juncheng Wu*, Zijun Wang, Zhan Shi, Yisi Sang, Bing He, Zewen Liu, Tianxin Wei, Zongyu Wu, Zhiwei Zhang, Dakuo Wang, Xiang Zhang, Benoit Dumoulin, Cihang Xie, Yuyin Zhou, Suhang Wang, Hanqing Lu (* indicates equal contribution). “Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents” [paper, code]
• Minhua Lin, Zhiwei Zhang, Hanqing Lu, Hui Liu, Xianfeng Tang, Qi He, Xiang Zhang, Suhang Wang. “MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution” [paper, code]
• Tianxin Wei, Zhan Shi, Minhua Lin, Bing He, Zewen Liu, Yisi Sang, Yuanchen Bei, Xuying Ning, Jiaru Zou, Ting-Wei Li, Xiao Lin, Yanjun Zhao, Chi Wang, Benoit Dumoulin, Dakuo Wang, Jingrui He, Hanqing Lu. “Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents”
• Zewen Liu, Zhan Shi, Yisi Sang, Bing He, Minhua Lin, Tianxin Wei, Dakuo Wang, Benoit Dumoulin, Wei Jin, Hanqing Lu. “Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams”
• Zongyu Wu*, Yuwei Niu*, Hongcheng Gao, Minhua Lin, Zhiwei Zhang, Zhifang Zhang, Yilong Wang, Sike Fu, Junjie Xu, Qi Shi, Junjie Ao, Enyan Dai, Lei Feng, Xiang Zhang, Suhang Wang (* indicates equal contribution). “LanPHal: Rethinking the Impact of Language Priors on Hallucinations in Large Vision-Language Models” [paper, code, project page]

Peer Reviewed Papers

2026

• Minhua Lin, Enyan Dai, Hui Liu, Xianfeng Tang, Yuliang Yan, Zhenwei Dai, Jingying Zeng, Zhiwei Zhang, Fali Wang, Hongcheng Gao, Chen Luo, Xiang Zhang, Qi He, Suhang Wang. “How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use” In the Fourteenth International Conference on Learning Representations (ICLR 2026) [paper, code]
• Minhua Lin, Hui Liu, Xianfeng Tang, Jingying Zeng, Zhenwei Dai, Chen Luo, Zheng Li, Xiang Zhang, Qi He, Suhang Wang. “How Far are LLMs from Real Search? Rethinking the Complementary Role between Search and Learning” In the Transactions on Knowledge Discovery from Data (TKDD 2026) [paper code]
• Minhua Lin, Hanqing Lu, Zhan Shi, Bing He, Rui Mao, Zhiwei Zhang, Zongyu Wu, Xianfeng Tang, Hui Liu, Zhenwei Dai, Xiang Zhang, Suhang Wang, Benoit Dumoulin, Jian Pei. “Position: Agentic Evolution is the Path to Evolving LLMs” In the Fourteenth International Conference on Learning Representations In the First Workshop on Agent Skills on ACM Confernece on AI and Agentic Systems (Agent Skill@ACM CAIS 2026) [paper, code]
• Minhua Lin, Zhengzhang Chen, Yanchi Liu, Xujiang Zhao, Zongyu Wu, Junxiang Wang, Xiang Zhang, Suhang Wang, Haifeng Chen. “Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation” In the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026) [paper, code]
• Bin Ma, Yuyuan Feng, Minhua Lin, Enyan Dai. “Do Explanations Increase the Risk of Decision Logic Leakage? Explanation-Guided Stealing of Graph Models” In 32th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2026) [paper, code]
• Shuo Yan, Yuliang Yan, Bin Ma, Chenao Li, Haochun Tang, Jiahua Lu, Minhua Lin, Yuyuan Feng, Enyan Dai. “General Protein Pretraining or Domain-Specific Designs? Benchmarking Protein Modeling on Realistic Applications” In 32th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2026 D&B Track) [paper, code]
• Zhiwei Zhang, Yudi Lin, Linlin Wu, Fali Wang, Yi Xin, Xiaomin Li, Minhua Lin, Xianfeng Tang, Qi He, Suhang Wang. “Adversarial Reinforcement Learning for Robust Diffusion Large Language Model Unlearning” In 43-th International Conference on Machine Learning (ICML 2026) [paper, code]
• Hongcheng Gao, Zihao Huang, Jingyi Tang, Lin Xu, Xinhao Li, Haoyang Li, Yue Liu, Minhua Lin, Xinlong Yang, Taihang Hu, Ge Wu, Baolong Bi, Hongyu Chen, Zhiqi Huang, Wentao Zhang. “Position: Reasoning After Perception Means Reasoning Without Vision” In 43-th International Conference on Machine Learning (ICML 2026 Position Paper) [paper, code]
• Zhiwei Zhang, Xiaomin Li, Yudi Lin, Hui Liu, Ramraj Chandradevan, Linlin Wu, Minhua Lin, Fali Wang, Xianfeng Tang, Qi He, Suhang Wang. “Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation” In the Fourteenth International Conference on Learning Representations (ICLR 2026) [paper, code]
• Zhiwei Zhang, Hui Liu, Xiaomin Li, Zhenwei Dai, Jingying Zeng, Fali Wang, Minhua Lin, Ramraj Chandradevan, Linlin Wu, Zhen Li, Chen Luo, Zongyu Wu, Xianfeng Tang, Qi He, Suhang Wang “Bradley-Terry and Multi-Objective Reward Modeling Are Complementary” In the Fourteenth International Conference on Learning Representations (ICLR 2026) [paper, code]
• Zongyu Wu, Minhua Lin, Zhiwei Zhang, Fali Wang, Xianren Zhang, Xiang Zhang, Suhang Wang. “Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models” In the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026 Oral) [paper]

  2025

• Minhua Lin*, Zhiwei Zhang*, Enyan Dai, Zongyu Wu, Yilong Wang, Xiang Zhang, Suhang Wang (* indicates equal contribution). “Are You Using Reliable Graph Prompts? Trojan Prompt Attacks on Graph Neural Networks” In 31th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2025) [paper, code]
• Minhua Lin, Enyan Dai, Junjie Xu, Jinyuan Jia, Xiang Zhang, Suhang Wang. “Stealing Training Graphs from Graph Neural Networks” In 31th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2025) [paper, code]
• Enyan Dai*, Minhua Lin*, Suhang Wang (* indicates equal contribution). “PreGIP: Watermarking the Pretraining of Graph Neural Networks for Deep Intellectual Property Protection” In 31th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2025) [paper, code]
• Zhiwei Zhang, Minhua Lin, Junjie Xu, Zongyu Wu, Enyan Dai, Suhang Wang. “Robustness-Inspired Defense Against Backdoor Attacks on Graph Neural Networks” In 13th International Conference on Learning Representations (ICLR 2025) [paper, code]
• Zhengpin Li, Minhua Lin, Jian Wang, Suhang Wang. “Fairness-aware Prompt Tuning for Graph Neural Networks” In Proceedings of the ACM Web Conference 2025 (WWW 2025) [paper]
• Junjie Xu, Zongyu Wu, Minhua Lin, Xiang Zhang, Suhang Wang. “LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning” In Proceedings of 2025 IEEE International Conference on Big Data (IEEE BigData 2025)[paper, code]
• Quan Li, Wenchao Yu, Suhang Wang, Minhua Lin, Lingwei Chen, Wei Cheng, and Haifeng Chen, “Extreme Event Prediction with Hierarchical Knowledge Distillation and Expert Fusion” In 25th IEEE International Conference on Data Mining (ICDM 2025) [paper]

2024

• Binghui Wang*, Minhua Lin*, Tianxiang Zhou, Pan Zhou, Ang Li, Meng Pang, Cai Fu, Hai Li, Yiran Chen (* indicates equal contribution). “Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Function” In 17th ACM International Conference on Web Search and Data Mining (WSDM 2024) [paper, code]

• Zhiwei Zhang, Minhua Lin, Enyan Dai, Suhang Wang. “Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective” In 30th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2024) [paper, code]

2023

• Minhua Lin, Teng Xiao, Enyan Dai, Xiang Zhang, Suhang Wang. “Certifiably Robust Graph Contrastive Learning” In Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023) [paper, code]

• Enyan Dai*, Minhua Lin*, Xiang Zhang, Suhang Wang (* indicates equal contribution). “Unnoticeable Backdoor Attacks on Graph Neural Networks” In Proceedings of the ACM Web Conference 2023 (WWW 2023) [paper, code]