About me

I am a second-year Master’s student at Tsinghua University. My research mainly lies in Large Language Models (LLMs), Agentic Reinforcement Learning, and Information Retrieval, with a recent emphasis on developing autonomous Search and Code Agents.

Research Interests

LLMs & Agentic Reinforcement Learning: Focuses on empowering models to learn from interaction and trial-and-error in realistic, complex environments. This includes:

• 🔍 Search Agents
  Building autonomous search agents that navigate dynamic information environments to conduct deep research and execute long-horizon knowledge synthesis.

• 💻 Code Agents
  Developing code agents that interact with software sandboxes and leverage reinforcement learning to solve complex engineering problems through trial-and-error.

Information Retrieval: Exploring advanced retrieval pipelines to connect models and users with accurate, high-quality information. Key aspects include:

• 📚 Retrieval-Augmented Generation (RAG)
  Designing retrieval and reranking pipelines to support LLMs with accurate and up-to-date external knowledge.

• 🎯 Recommender Systems (Recsys)
  Exploring retrieval and ranking methods in recommender systems, especially under sparse signals or long-term user feedback.

I am also deeply interested in leveraging Reinforcement Learning to unlock the reasoning and decision-making capabilities of LLMs across diverse, interactive environments: from web navigation to software engineering. Ultimately, I aim to explore how agentic interaction and trial-and-error can feed back into training stronger and more robust backbone models. I look forward to collaborating and exchanging ideas with researchers in these exciting areas!

Education

• 2024.08 ~ present

  🎓 M.Phil, Software Engineering, Tsinghua University, China.

• 2020.10 ~ 2024.06

  🎓 B.S., Software Engineering, Beijing Institute of Technology, China.

Recent Papers

• SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and Synthesis
  Leqi Zheng*, Jinbo Su*, Haitao Li*, Chaokun Wang, Jiajun Zhang, Shannan Yan, Zhaolu Kang, Rong Fu, Fang Niu, Hang Zhang
  [Paper]

• AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents
  Shannan Yan*, Jingchen Ni*, Leqi Zheng*, Jiajun Zhang, Peixi Wu, Dacheng Yin, Jing Lyu, Chun Yuan, Fengyun Rao
  [ Paper]

• Audio-Visual World Models: Towards Multisensory Imagination in Sight and Sound
  Jiahua Wang*, Leqi Zheng*, Jialong Wu, Yaoxin Mao
  [ Paper]

Publications

• What Should I Cite? A RAG Benchmark for Academic Citation Prediction
  Leqi Zheng*, Jiajun Zhang*, Canzhi Chen*, Chaokun Wang, Hongwei Li, Yuying Li, Yaoxin Mao, Shannan Yan, Zixin Song, Zhiyuan Feng, Zhaolu Kang, Zirong Chen, Hang Zhang, Qiang Liu, Liang Wang, Ziyang Liu
  The Web Conf 2026 (CCF-A)
  [ Paper | Code ]

• Negative Feedback Really Matters: Signed Dual-Channel Graph Contrastive Learning Framework for Recommendation
  Leqi Zheng, Chaokun Wang, Zixin Song, Cheng Wu, Shannan Yan, Jiajun Zhang, Ziyang Liu
  NeurIPS 2025 (CCF-A)
  [ Paper | Code ]

• LAGCL4Rec: When LLMs Activate Interactions Potential in Graph Contrastive Learning for Recommendation
  Leqi Zheng, Chaokun Wang, Canzhi Chen, Jiajun Zhang, Cheng Wu, Zixin Song, Shannan Yan, Ziyang Liu, Hongwei Li
  EMNLP 2025 (CCF-B)
  [ Paper | Code ]

• Balancing Self-Presentation and Self-Hiding for Exposure-Aware Recommendation Based on Graph Contrastive Learning
  Leqi Zheng, Chaokun Wang, Ziyang Liu, Canzhi Chen, Cheng Wu, Hongwei Li
  SIGIR 2025 (CCF-A)
  [ Paper | Code ]

• Learning Cross-View Object Correspondence via Cycle-Consistent Mask Prediction
  Shannan Yan, Leqi Zheng, Keyu Lv, Jingchen Ni, Hongyang Wei, Jiajun Zhang, Guangting Wang, Jing Lyu, Chun Yuan, Fengyun Rao
  CVPR 2026 (CCF-A)
  [ Paper | Code ]

• RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation
  Jiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo, Jingzhuo Wu, Leqi Zheng, Yiran Yang, Jianke Zhang, Qingbin Li, Shannan Yan, Zhetong Li, Changguo Jia, Junfei Wu, Zilei Wang, Qiang Liu, Liang Wang
  ACL 2026 (CCF-A)
  [ Paper | Code ]

• Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes
  Zhiyuan Feng, Zhaolu Kang, Qijie Wang, Zhiying Du, Jiongrui Yan, Shubin Shi, Chengbo Yuan, Huizhi Liang, Yu Deng, Qixiu Li, Rushuai Yang, Arctanx An, Leqi Zheng, Weijie Wang, Shawn Chen, Sicheng Xu, Yaobo Liang, Jiaolong Yang, Baining Guo
  ICLR 2026 (CCF-A)
  [ Paper | Code ]

• Training-free and Unbiased Graph Collaborative Filtering for Personalized Recommendations
  Ziyang Liu, Chaokun Wang, Cheng Wu, Leqi Zheng, Hao Feng, Hang Zhang
  IEEE Transactions on Knowledge and Data Engineering (CCF-A)
  [ Paper | Code ]

Models & Technical Reports

• 🆉 GLM-5.1: Towards Long-Horizon Tasks
  GLM Team, Z.AI
  [ Blog | Model Card]

• 💍 Ring-2.5-1T
  inclusionAI Team, Ant Group
  [ Blog | Model Card ]

Honors and Awards

• 2025   Yang Huiyan Scholarship at Tsinghua University
• 2024   Excellent Higher Education Graduate of Beijing Municipality
• 2023   China National Scholarship (Top 1%)
• 2022   China National Scholarship (Top 1%)
• 2021   China National Scholarship (Top 1%)

Experience

• 🏫 Research Intern
  • THUIR, Department of Computer Science and Technology, THU, 2025 ~ Now
  • Focusing on Information Retrieval.
• 🏫 Research Intern
  • Wangxuan Institute of Computer Technology, PKU, 2023
  • Worked on Recommender Systems.
• 🆉 Research Intern (Joint Research Project)
  • Z.ai, 2026
  • Working on Code Agents and LLM post-training.
• 🐜 Research Intern (Joint Research Project)
  • Ant Group, 2025 ~ 2026
  • Worked on Search Agents and LLM post-training.
• 💬 Research Collaborator (Joint School Project)
  • Sina Weibo, 2025
  • Worked on LLM and Information Retrieval.
• 🐶 Research Collaborator (Joint School Project)
  • JD.com, 2024
  • Worked on Recommender Systems.

Last updated: March 2026