Hey, I am Zach! I am a third-year CS PhD student at University of Chicago, advised by Ce Zhang. Previously, I worked at Meta Superintelligence Labs (MSL) on agentic post-training for Muse Spark / Muse. I also work closely with James Zou and Bo Li.
My research interests are centered on large language models with a recent focus on self-evolving agents, reinforcement learning, test-time scaling, and interdisciplinary scientific applications.
I am Assistant Editor of the journal Data-centric Machine Learning Research (DMLR) under the JMLR family. I also contributed to Codabench, which is one of the most commonly used open source competition platforms according to ML Contests.
News
- Oct2026SEIS (Self Evolving Inference System) is now available
- Oct2026LEAP (Speculative Agent) is now available
- Sep2026BRIDGE (Agent Memory) is accepted at NeurIPS 2026
- May2026Start research internship at Meta Superintelligence Labs, working on post-training for Muse Spark / Muse
- Apr2026Prefill Prefill-capable Decode (PPD) Disaggregation is accepted at ICML 2026
- Jan2026Divide and Conquer Agents is accepted at ICLR 2026
- Nov2025Start research internship at Together AI
Selected Publications
- SEIS: Self-Evolving Inference SystemsZhen Xu, Jingyu Liu, Zongze Li, Tahseen Rabbani, Ce Zhang
- LEAP: Learning Efficient Action Proposals for LLM AgentsZhen Xu, Qizheng Zhang, Gerry Wan, Shang Zhu, Ce Zhang
- When Does Divide and Conquer Work for LLM in Processing Long Context? A Noise Decomposition FrameworkZhen Xu, Shang Zhu, Jue Wang, Junlin Wang, Ben Athiwaratkun, Chi Wang, James Zou, Ce ZhangICLR 2026[PDF]Invited presentations at Citadel Securities
- Codabench: Flexible, easy-to-use, and reproducible meta-benchmark platformZhen Xu, Sergio Escalera, Adrien Pavão, Magali Richard, Wei-Wei Tu, Quanming Yao, Huan Zhao, Isabelle GuyonPatterns Cell Press 2022[PDF]