Jian Xie

I am Jian Xie (Pronounced as "Jyen Shyeh", 谢健), a first-year Ph.D. student at The Ohio State University, where I am fortunate to work under the guidance of Prof. Yu Su. I have a broad interest in Natural Language Processing, with a current focus on Language Agents. My primary interests lie in agentic training, including mid-training and post-training, with a focus on digital agents. Feel free to reach out to me if you have any questions or want to collaborate!

News

  • 2026. May. I started my summer internship at Meta Superintelligence Lab, working on self-evolving agents. Feel free to grab a coffee or chat if you are in the Bay Area!

  • 2026. May. Thrilled to release QUEST, a family of open models ranging from 2B to 35B that serve as general-purpose deep research agents designed to handle a wide range of search tasks!

  • 2026. May. ARM2 is accepted to ACL 2026 Findings; Agent Learning via Early Experience is accepted to ICML 2026! Thanks to all collaborators!

  • 2025. Oct. ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code is out!

  • 2025. Sep. Mind2Web 2 and ARM are accepted to NeurIPS 2025! ARM got a
    Spotlight (3%)!

  • 2025. May. Thrilled to release ARM: A reasoning model able to adaptively select reasoning formats based on the task, achieving a better trade-off between effectiveness and efficiency!

  • 2025. May. AAAR-1.0 is accepted to ICML 2025; Mechanistic Interpretability of
    Implicit Reasoning in Transformers     is accepted to ACL 2025 Findings! Thanks to all collaborators!

  • 2025. Jan. One paper is accepted to NAACL 2025.

  • 2024. Oct. New Preprint: An in-depth analysis of why language agents struggle with planning tasks, while also exploring the mechanisms and limitations of the follow-up strategies. Some potential solutions are in the works!

  • 2024. Oct. Got the national scholarship—it's been a dream of mine since undergrad!

  • 2024. Aug. I will present at ACL2024@Bangkok and share our paper Irrelevant Information. Looking forward to chatting with old friends and meeting new ones!

  • 2024. Jul. Two papers, Irrelevant Information and Deductive Beam Search, are accepted to COLM 2024. Thanks to all collaborators!

  • 2024. Jun. Invited talk on language agent planning at CUHK, AITIME, and ByteDance.

  • 2024. May. TravelPlanner has been accepted as a Spotlight (3.5%) at ICML 2024!

  • 2024. Feb. New Preprint TravelPlanner : a benchmark crafted for evaluating language agents in tool-use and complex planning within multiple constraints.

  • 2024. Jan. Two papers have been accepted to ICLR 2024. Knowledge Conflict got a Spotlight (5%) ! See you in Vienna, Austria!

Featured Publications

QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks

Jian Xie, Tianhe Lin, Zilu Wang, Yuting Ning, Yuekun Yao, Tianci Xue, Zhehao Zhang, Zhongyang Li, Kai Zhang, Yufan Wu, Shijie Chen, Boyu Gou, Mingzhe Han, Yifei Wang, Vint Lee, Xinpeng Wei, Xiangjun Wang, Yu Su, Huan Sun arXiv Preprint

TravelPlanner: A Benchmark for Real-World Planning with Language Agents

Jian Xie, Kai Zhang, Jiangjie Chen, Tinghui Zhu, Renze Lou, Yuandong Tian, Yanghua Xiao, Yu Su ICML 2024 Spotlight (3.5%)

Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts

Jian Xie, Kai Zhang, Jiangjie Chen, Renze Lou, Yu Su ICLR 2024 Spotlight (5%)

ARM: Adaptive Reasoning Model

Siye Wu, Jian Xie, Yikai Zhang, Aili Chen, Kai Zhang, Yu Su, Yanghua Xiao NeurIPS 2025 Spotlight (3%)
See More