Hello! I’m a PhD student in the NLP group at King’s College London, working with Prof. Yulan He and Dr. Lin Gui.

Professional Summary

My current research centers on agentic coding in machine learning and artificial intelligence. I explore methods for reliable code reproduction from academic papers, effective memory management, tool utilization, and the creation of synthetic trajectories to perform supervised fine-tuning and reinforcement learning for improving large language model performance on complex coding tasks.

Experience

• Meta — Research Engineer (Nov. 2025 – Now). Developing AI Scientist agents: LLM systems that automate research tasks and machine learning engineering workflows.
• AstraZeneca — Internship (Jul. 2025 – Oct. 2025). Supervised by Dr. Saseendran and Dr. Jin on generating multiple tokens per decoding step in Diffusion Language Models to accelerate decoding.

Education

• King's College London, London, United Kingdom Sep. 2023 – Jun. 2027 (expected)
  Ph.D. in Computer Science.
  Supervised by Prof. Yulan He with Dr. Lin Gui as co-advisor. Focus areas: Agentic Coding, AI for scientific discovery, In-context learning.
• Southeast University, Nanjing, China Sep. 2020 – Jun. 2023
  M.S. in Software Engineering.
  Supervised by Prof. Deyu Zhou with research on question answering and code generation.
• Hefei University of Technology, Hefei, China Sep. 2016 – Jun. 2020
  B.E. in Computer Science and Technology.

Awards and Honors

• NMES International Studentship (2023 – 2027)
• Outstanding Graduate Student, Hefei University of Technology (2020)
• Merit Student, Hefei University of Technology (2018)

Invited Talks

• Meta, LLaMA Community Meet-up (Apr. 6, 2025): “Towards Automatic Code Reproduction for Scientific Papers: Benchmarks and Methodologies.” [event post]

Competitions

• National First Prize (Top 0.65%), China Undergraduate Mathematical Contest in Modelling (2018). Team-based modeling competition solving open-ended applied problems.
• 1st Place, Spider Leaderboard (2022). Our model G3R achieved the top rank on the “exact set match without values” metric and is currently 5th overall.

Publications

• SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers [arXiv]
  Yanzheng Xiang, Hanqi Yan, Shuyin Ouyang, Lin Gui, Yulan He
  In COLM 2025.
• G3R: A Graph-Guided Generate-and-Rerank Framework for Cross-domain Text-to-SQL Generation [paper]
  Yanzheng Xiang, Qian-Wen Zhang, Xu Zhang, Zejie Liu, Yunbo Cao, Deyu Zhou
  In Findings of ACL 2023.
• Addressing Order Sensitivity of In-Context Demonstration Examples in Causal Language Models [arXiv]
  Yanzheng Xiang, Hanqi Yan, Lin Gui, Yulan He
  In Findings of ACL 2024.
• The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis [paper]
  Yuxiang Zhou, Jiazheng Li, Yanzheng Xiang, Hanqi Yan, Lin Gui, Yulan He
  In EMNLP 2024.
• A Divide-And-Conquer Approach for Multi-label Multi-hop Relation Detection in Knowledge Base QA [paper]
  Deyu Zhou, Yanzheng Xiang, Linhai Zhang, Chenchen Ye, Qian-Wen Zhang, Yunbo Cao
  In Findings of EMNLP 2021.
• PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA [paper]
  Xinyu Wang, Yanzheng Xiang, Lin Gui, Yulan He
  In Findings of ACL 2025.
• Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective [paper]
  Hanqi Yan, Yanzheng Xiang, Guangyi Chen, Yifei Wang, Lin Gui, Yulan He
  In EMNLP 2024.