Hi, my name is Zhengliang Shi. I am now a second-year Master student majoring in Computer Science and Technology from General Artificial Intelligence Lab of Shandong University. My supervisor is Zhaochun Ren and Pengjie Ren. Previously, I was supervised by Dr. Shuo Zhang in Bloomberg. Besides, I am fortunate to closely work with Dr. Weiwei Sun in Carnegie Mellon University. I obtained my Bachelor's degree in Shandong University majoring in Computer Science and Technology (graduated in 2023) and my research advisor is Zhaochun Ren.

📖 My current research interests primarily focus on large language models (LLMs), particularly:

• LLM-based agent: building a real-world agent based on the foundation model to solve complex and practical tasks, e.g., tool-use agents.
• Retrieval-augmented generation: enhancing models with factual knowledge from diverse sources of information and reduce their hallucination.

🔍 Currently Applying for PhD Positions in 2026

I am actively applying for PhD positions in 2026 and am eager to explore opportunities in LLM-based agents, post-training of foundation models, and other related topics. Feel free to reach out if you are looking for a self-motivated student. I would be happy to discuss how my background aligns with your research goals.

More details about me: CV and undergraduate transcript (GPA: 93.46/100, Rank: 2/182).

📚 News

• 2025.05.20: Our new paper named DRO (Direct retrieval-augmented optimization) has been released. Thank the co-authors from CMU, Baidu, UvA, Leiden university and UoB.
• 2025.05.16: Two papers have been accepted by ACL 2025 🎉🎉🎉. See you guys in Vienna!
• 2025.02.27: I will visit Leiden University, Netherlands.
• 2025.01.20: One paper has been accepted by TheWebConf 2025 (WWW). See you guys in Sydney!
• 2024.10.01: One paper has been accepted by EMNLP 2024.

📚 Publications (selected)

* indicates equal contribution

• Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers
  - Zhengliang Shi, Lingyong Yan, Dawei Yin, Suzan Verberne, Maarten de Rijke, Zhaochun Ren
• Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models
  - Zhengliang Shi, Lingyong Yan, Weiwei Sun, Yue Feng, Pengjie Ren, Xinyu Ma, Shuaiqiang Wang, Dawei Yin, Maarten de Rijke, Zhaochun Ren
• 🔍 Retrieval Models Aren’t Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
  - Zhengliang Shi, Yuhan Wang, Lingyong Yan, Pengjie Ren, Shuaiqiang Wang, Dawei Yin, Zhaochun Ren
• Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents
  - Zhengliang Shi, Shen Gao, Lingyong Yan, Yue Feng, Xiuyi Chen, Zhumin Chen, Dawei Yin, Suzan Verberne, Zhaochun Ren; Accepted by WWW 2025
• Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering
  - Zhengliang Shi, Shuo Zhang, Weiwei Sun, Shen Gao, Pengjie Ren, Zhumin Chen, Zhaochun Ren; Accepted by ACL 2024
• Learning to Use Tools via Cooperative and Interactive Agents
  - Zhengliang Shi, Shen Gao, Xiuyi Chen, Yue Feng, Lingyong Yan, Haibo Shi, Dawei Yin, Pengjie Ren, Suzan Verberne, Zhaochun Ren; Accepted by ACL 2023
• Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum
  - Shen Gao*, Zhengliang Shi*, Minghang Zhu, Bowen Fang, Xin Xin, Pengjie Ren, Zhumin Chen, Jun Ma; Accepted by AAAI 2024
• Contrastive Learning Reduces Hallucination in Conversations
  - Weiwei Sun, Zhengliang Shi, Shen Gao, Pengjie Ren, Maarten de Rijke, Zhaochun Ren; Accepted by AAAI 2023

💻 Experience

• 2025.4 - Present, Researcher, Tencent, TEG multimodal department , Shenzhen, China. Supervised by Zhaopeng Tu.
• 2025.3 - 2025.4, Visiting scholar, Leiden University , Leiden, Netherlands. Supervised by Suzan Verberne and Zhaochun Ren.
• 2023.5 - 2025.3, Researcher, Baidu, Search Science Team , Beijing, China. Supervised by Dawei Yin and Lingyong Yan.
• 2021.9 - 2023.5, Research Assistant, Shandong University IRlab , Qingdao, China.

📌 Services

• 2025 Area Chair for ACL Rolling Review; Program Committee for SIGIR and TheWebConf (WWW); Review for IPM (CCF-B journal) and ECIR
• 2024 Reviewer for IJCAL, AAAI, ACL, EMNLP, NAACL, IPM

💬 Invited Talks

• 2025.03, Not Just Generation: Incentivizing Language Models to Reason and Search, Search Engine Amsterdam, Amsterdam, Netherlands
• 2023.05, Towards a More Reliable Evaluation for Open-Domain Dialogue system, Paper Reporting for ACL-IJCAL-SIGIR (AIS) 2023 Conference, Changsha, China.

🎊 Honors (Selected)

• 2023 Excellent Graduate, Shandong University, China
• 2022 Dean’s Scholarship, Shandong University, Department of Computer Science
• 2022 Presidential Scholarship, Shandong University, China
• 2021 National Scholarship, Ministry of Education, China
• 2021, 2022, 2023 Academic Scholarship, Shandong University, China

🎊 Awards (Selected)

• 2022 Third Prize of World Artificial Intelligence Challenge Competition (WAIC)
• 2021,2022 Second Prize of the American Mathematical Modeling Competition
• 2021 First Prize of National Mathematical Modeling Competition
• 2021 First Prize of the National College Students' Innovation and Entrepreneurship Competition