Hi, I am a second-year Ph.D. student at 
UNC-Chapel Hill advised by Prof. Zhun Deng. Currently, I study how LLM agents learn and improve through interaction, with a focus on eliciting human preferences and developing reliable evaluation methods. I have been particularly interested in AI4AI—using AI systems to automate data engineering, evaluation, and model improvement. Please feel free to reach out if you are interested in collaborating.
Before joining UNC, I completed my Master’s degree in Computer Science at 
Georgia Tech. I am also fortunate to collaborate with researchers at 
UIUC, 
Microsoft, and 
NEC Laboratories America.
Research interests: LLM Agents & Reasoning · Preference Learning & Elicitation · Reliable LLM Evaluation · AI4AI
I am actively seeking 2027 summer internships. If you have or know of any opportunities that align with my interests, please contact me at ruomeng@cs.unc.edu.🔥 News
- [10/2026] 🚀 New arXiv preprint: Speculative Evaluation of Stochastic LLMs. [paper] [code]
- [09/2026] 🎉 Three papers accepted at NeurIPS 2026 workshops: WAPA @ FLLMPT, ADE @ AutoMLR, and SpecEval @ TAE. ArXiv versions will be released soon.
- [09/2026] I will serve as a reviewer for ICLR 2027.
- [07/2026] 🎉 One paper accepted at COLM 2026.
- [07/2026] I will serve as a reviewer for AAAI 2027.
- [05/2026] 🎉 One paper accepted at ICML 2026. See you in Seoul! 🇰🇷
- [05/2026] I will serve as a reviewer for NeurIPS 2026.
- [04/2026] I will join
Alibaba Tongyi Lab as a research intern in Summer 2026. - [03/2026] 🎉 Two papers accepted at ICLR 2026 Workshops ICBINB & AIMS. See you in Rio! 🇧🇷
- [02/2026] 🚀 New arXiv preprint: Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges. [paper] [code]
- [02/2026] 🚀 New arXiv preprint: Whom to Query for What: Adaptive Group Elicitation via Multi-Turn LLM Interactions. [paper] [code]
- [01/2026] I will serve as a reviewer for ICML 2026.
- [01/2026] I will serve as a reviewer for KDD 2026.
- [11/2025] 🎉 One paper accepted at AAAI 2026 (Oral).
📝 Selected Publications
* Equal contribution.
LLM Agents & Reasoning
-
AutoMLR Workshop @NeurIPS 2026 Agentic Data Engineering for LLMs: System Design and a Controlled Empirical Study, Ruomeng Ding, Qianli Shen, ZhaoYang Han, Meixin Chen, Daoyuan Chen, Yaliang Li [paper]
-
AAAI 2026 Oral SkillGen: Learning Domain Skills for In-Context Sequential Decision Making, Ruomeng Ding, Wei Cheng, Minglai Shao, Chen Zhao [paper] [code]
-
ACL 2024 Everything of thoughts: Defying the law of penrose triangle for thought generation, Ruomeng Ding, Chaoyun Zhang, Lu Wang, Yong Xu, Minghua Ma, Wei Zhang, Si Qin, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang [paper] [code]
Preference Learning & Elicitation
-
FLLMPT Workshop @NeurIPS 2026 Who Should We Listen to More? Welfare-Aware Preference Acquisition for Pluralistic Alignment, Ruomeng Ding, Tianwei Gao, Lianrui Geng, and Zhun Deng [paper]
-
ICML 2026 Whom to Query for What: Adaptive Group Elicitation via Multi-Turn LLM Interactions, Ruomeng Ding*, Tianwei Gao*, Thomas P. Zollo, Eitan Bachmat, Richard Zemel, and Zhun Deng [paper] [code]
Reliable LLM Evaluation
-
TAE Workshop @NeurIPS 2026 Preprint Speculative Evaluation of Stochastic LLMs, Qianli Shen, Xiang Li, Ruomeng Ding, Yanxi Chen, Daoyuan Chen, Yaliang Li [paper] [code]
-
COLM 2026 Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges, Ruomeng Ding*, Yifei Pang*, He Sun, Yizhong Wang, Zhiwei Steven Wu, and Zhun Deng [paper] [code]
-
NeurIPS 2024 Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs, Rui Yang, Ruomeng Ding, Yong Lin, Huan Zhang, Tong Zhang [paper] [code]
Reliable Machine Learning & Applications
-
SDM 2025 Evidence-Based Out-of-Distribution Detection on Multi-Label Graphs, Ruomeng Ding, Xujiang Zhao, Chen Zhao, Minglai Shao, Zhengzhang Chen, Haifeng Chen
-
ESEC/FSE 2023 TraceDiag: Adaptive, Interpretable, and Efficient Root Cause Analysis on Large-Scale Microservice Systems, Ruomeng Ding, Chaoyun Zhang, Lu Wang, Yong Xu, Minghua Ma, Xiaomin Wu, Meng Zhang, Qingjun Chen, Xin Gao, Xuedong Gao, Hao Fan, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang [paper]
-
KDD 2023 Root cause analysis for microservice systems via hierarchical reinforcement learning from human feedback, Lu Wang, Chaoyun Zhang, Ruomeng Ding, Yong Xu, Qihang Chen, Wentao Zou, Qingjun Chen, Meng Zhang, Xuedong Gao, Hao Fan, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang [paper]
-
VLDB 2023 ImDiffusion: Imputed diffusion models for multivariate time series anomaly detection, Yuhang Chen, Chaoyun Zhang, Minghua Ma, Yudong Liu, Ruomeng Ding, Bowen Li, Shilin He, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang [paper] [code]
💻 Internships
- 2026.05 - 2026.08, Alibaba Token Foundry (Tongyi Lab), Hangzhou, China.
- 2024.05 - 2024.08, Microsoft Research, Redmond, WA.
- 2022.11 - 2023.08, Microsoft Research Asia, Beijing, China.
🎖 Honors and Fellowships
- Doctoral Merit Fellowship, University of North Carolina at Chapel Hill, 2025–2026
- Merit Scholarship, Georgia Institute of Technology, 2022-2023
Visitor map is temporarily unavailable.