Zixuan Ke

Researcher, Salesforce AI Research

Joined

July 2019

Names

Zixuan Ke

Emails

****@uic.edu (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Researcher

Salesforce AI Research (salesforce.com)

2024 – Present

PhD student

University of Illinois, Chicago (uic.edu)

2019 – 2024

Advisors, Relations & Conflicts

PhD Advisor

Bing Liu

2019 – Present

PhD Advisor

Vincent Ng

2017 – 2019

Expertise

Large Language Model

2022 – Present

Continual/lifelong Learning

2019 – Present

NLP

2017 – Present

Publications

MAS-Zero: Designing Multi-Agent Systems with Zero Supervision
Zixuan Ke, Austin Xu, Yifei Ming, Xuan-Phi Nguyen, Ryan Chin, Caiming Xiong, Shafiq Joty
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild
Jiayu Wang, Yifei Ming, Riya Dulepet, Qinglin Chen, Austin Xu, Zixuan Ke, Frederic Sala, Aws Albarghouthi, Caiming Xiong, Shafiq Joty
- ICLR 2026 Poster
- Readers: Everyone
WAFER-QA: Evaluating Vulnerabilities of Agentic Workflows with Agent-as-Judge
Yifei Ming, Zixuan Ke, Xuan-Phi Nguyen, Jiayu Wang, Shafiq Joty
- Submitted to ICLR 2026
- Readers: Everyone
MAS-ZERO: Designing Multi-Agent Systems with Zero Supervision
Zixuan Ke, Austin Xu, Yifei Ming, Xuan-Phi Nguyen, Caiming Xiong, Shafiq Joty
- SEA @ NeurIPS 2025 Oral
- Readers: Everyone
Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning
Jiayu Wang, Yifei Ming, Zixuan Ke, Caiming Xiong, Shafiq Joty, Aws Albarghouthi, Frederic Sala
- NeurIPS 2025 poster
- Readers: Everyone
A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems
Zixuan Ke, Fangkai Jiao, Yifei Ming, Xuan-Phi Nguyen, Austin Xu, Do Xuan Long, Minzhi Li, Chengwei Qin, PeiFeng Wang, silvio savarese, Caiming Xiong, Shafiq Joty
- Accepted by TMLR
- Readers: Everyone
Expanding the Web, Smaller Is Better: A Comprehensive Study in Post-training
Zixuan Ke, Yifei Ming, Xuan-Phi Nguyen, Caiming Xiong, Shafiq Joty
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
Yifei Ming, Senthil Purushwalkam, Shrey Pandit, Zixuan Ke, Xuan-Phi Nguyen, Caiming Xiong, Shafiq Joty
- ICLR 2025 Poster
- Readers: Everyone
Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks
Zixuan Ke, Bing Liu, Wenhan Xiong, Asli Celikyilmaz, Haoran Li
- EMNLP 2023 Findings
- Readers: Everyone
Parameter-Level Soft-Masking for Continual Learning
Tatsuya Konishi, Mori Kurokawa, Chihiro Ono, Zixuan Ke, Gyuhak Kim, Bing Liu
- ICML 2023 Poster
- Readers: Everyone

View all 22 publications

Co-Authors

View all 39 co-authors