About me
My name is Ruochen, feel free to call me Esther. In Chinese, my name is 赵若辰, which translates to “like a star”. I’m currently a research engineer at Apple. I hold a Ph.D. from Nanyang Technological University (NTU-NLP), advised by Associate Professor Shafiq Joty. I am currently focusing on the topic of LLM Agents, trustworthiness and reliability, with interests in Agents, LLMs, and reasoning. Specifically, I am intrigued by the research question of endowing LLMs with reasoning abilities by mimicing human thinking processes.
I graduated my PhD in August 2024. Prior to my Ph.D. journey, I received my B.S. in Mathematics from Courant Institute, New York University. I then graduated with an M.S. in Data Science from Harvard University. After spending 6 years in the U.S., I returned to Asia and have been staying in Singapore for 4 years now.
News
- [Aug 2025] I received the SG100WIT 2025 Award (Singapore 100 Women in Tech)! Really appreciate the recognition.
- [May 2025] Auto-Arena is accepted to ACL 2025.
- [Aug 2024] Successfully defended my PhD thesis and joined Apple as a research engineer. Many thanks to my supervisors.
Publications
Here is a taste of what I enjoy doing!
Designing Single and Multi-Agent Systems for Diverse Tasks
AgREE: Agentic Reasoning for Knowledge Graph Completion on Emerging Entities
Ruochen Zhao, Simone Conia, Eric Peng, Min Li, Saloni Potdar
Currently on arxiv
Paper
Auto-Arena of LLMs: Automating LLM Evaluations with Agent Peer-battles and Committee Discussions
Ruochen Zhao, Wenxuan Zhang, Yew Ken Chia, Deli Zhao, Lidong Bing
ACL 2025 Main
Paper
Chain of Ideas: Revolutionizing Research via Novel Idea Development with LLM Agents
Long Li, Weiwen Xu, Jiayan Guo, Ruochen Zhao, Xingxuan Li, Yuqian Yuan, Boqiang Zhang, Yuming Jiang, Yifei Xin, Ronghao Dang, Deli Zhao, Yu Rong, Tian Feng, Lidong Bing
EMNLP 2025 Findings
Paper
Give LLMs Tools and Reasoning Abilities like Humans
Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks
Xingxuan Li, Weiwen Xu, Ruochen Zhao, Fangkai Jiao, Shafiq Joty, Lidong Bing
ACL 2025 Main
Paper
Chain of Knowledge: A Framework for Grounding Large Language Models with Structured Knowledge Bases
Xingxuan Li*, Ruochen Zhao*, Yew Ken Chia*, Bosheng Ding, Lidong Bing, Shafiq Joty, Soujanya Poria
ICLR 2024
Paper
Retrieving Multimodal Information for Augmented Generation: A Survey
Ruochen Zhao, Hailin Chen, Weishi Wang, Fangkai Jiao, Xuan Long Do, Chengwei Qin, Bosheng Ding, Xiaobao Guo, Minzhi Li, Xingxuan Li, Shafiq Joty
EMNLP 2023 Findings
Paper
Verify-and-Edit: A Knowledge-Enhanced Chain-of-thought Framework
Ruochen Zhao*, Xingxuan Li*, Shafiq Joty, Chengwei Qin, Lidong Bing
ACL 2023 Main
Paper
Making LLMs more Trustworthy and Transparent
Explaining Language Models’ Predictions with High-Impact Concepts
Ruochen Zhao, Shafiq Joty, Yongjie Wang, Tan Wang
EACL 2024 Findings
Paper
Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications
Han Cheol Moon, Shafiq Joty, Ruochen Zhao, Megh Thakkar, Xu Chi
ACL 2023 Main
Paper
Just Thinking About LLMs and NLP In General
How Much are LLMs Contaminated? A Comprehensive Survey and the LLMSanitize Library
Mathieu Ravaut, Bosheng Ding, Fangkai Jiao, Hailin Chen, Xingxuan Li, Ruochen Zhao, Chengwei Qin, Caiming Xiong, Shafiq Joty
CoRR 2024
Paper
ChatGPT’s One-year Anniversary: Are Open-Source Large Language Models Catching up?
Hailin Chen*, Fangkai Jiao*, Xingxuan Li*, Chengwei Qin*, Mathieu Ravaut*, Ruochen Zhao*, Caiming Xiong, Shafiq Joty
arxiv
Paper