Jingheng Ye

Jingheng Ye

I am a first-year Ph.D. student in Computer Engineering at Northeastern University (NEU), advised by Prof. Weiyan Shi at the CHATS Lab. Prior to NEU, I obtained my M.S. in Computer Science from Tsinghua University in 2025, where I was a member of the THUKE Lab advised by Prof. Hai-Tao Zheng. I received my B.S. from South China University of Technology in 2022.

My research centers on building reliable and trustworthy LLM Agents. Currently, my research interests lie in:

  • Agent Safety & Evaluation: Detecting and benchmarking unsafe behaviors in LLM agents, specifically assessing the risks posed to Human-AI Collaboration in high-stakes scenarios.
  • Reliable & Aligned Agents: Developing frameworks to build agents that are robust, aligned with human intent, and capable of complex reasoning and planning.
  • Personalized AI: Designing agents that adapt to individual user needs and contexts, such as clarifying user intent in real-world tasks or providing tailored pedagogical feedback in education.

I am currently looking for Research Intern positions for Summer 2026. You can find my CV here: Jingheng Ye’s CV.

🔥 News

  • 2025.09: 🎓 Started my Ph.D. journey at Northeastern University!

  • 2025.09: 🎉 Two papers accepted to EMNLP 2025 (one Industry Track, one Main Conference).

  • 2025.05: 🎉 One paper accepted to ACL 2025 (CLEME 2.0).

  • 2024.12: 🎉 EXCGEC is accepted by AAAI 2025 (Oral).

  • 2024.12: 🏅 Awarded the National Scholarship.

📝 Selected Publications

EMNLP 2025 Position: LLMs Can be Good Tutors in English Education
Jingheng Ye, Shen Wang, Deqing Zou, et al.

EMNLP 2025 ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questions
Jingheng Ye, Yong Jiang, Xiaobin Wang, et al.

AAAI 2025 Oral EXCGEC: A Benchmark of Edit-wise Explainable Chinese Grammatical Error Correction
Jingheng Ye*, Shang Qin*, Yinghui Li, et al.

ACL 2025 CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction
Jingheng Ye*, Zishan Xu*, Yinghui Li, et al.

EMNLP 2023 CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correction
Jingheng Ye*, Yinghui Li*, Qingyu Zhou, et al.

EMNLP 2023 MixEdit: Revisiting Data Augmentation and Beyond for Grammatical Error Correction
Jingheng Ye, Yinghui Li, Yangning Li, et al.

EMNLP 2023 A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check
Haojing Huang*, Jingheng Ye*, Qingyu Zhou, et al.

💻 Experience

  • Northeastern University, Boston, MA
    • Research Assistant, Sep 2025 - Present
    • Advisor: Prof. Weiyan Shi. Focus: Code Sabotage & Agent Safety.
  • Squirrel AI, Shanghai, China
    • Research Intern, Aug 2024 - Jun 2025
    • Advisor: Dr. Qingsong Wen. Topic: AI Education.
  • Alibaba (Tongyi Lab), Hangzhou, China
    • Research Intern, Dec 2023 - Aug 2024
    • Advisor: Dr. Yong Jiang. Topic: LLM Agents.
  • Tencent, Shenzhen, China
    • Software Engineering Intern, Jul 2021 - Sep 2021
    • Topic: Database System Testing (TDSQL).

🥇 Honors and Awards

  • 2025.06 Outstanding Graduate of Beijing (Top 1%)
  • 2024.12 National Scholarship (Top 0.2%)
  • 2023.08 CCL23-Eval CLTC Track-1, Second Prize
  • 2022.10 CCL22-Eval CLTC Task-4, First Prize
  • 2019.12 National Scholarship (Top 0.2%)