| CARVIEW |
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 exploring the memory mechanisms and reasoning/planning capabilities of language agents. Feel free to reach out to me if you have any questions or want to collaborate!
Looking for a publication-oriented research intern position for Summer 2026 in the US. Please reach out to me if you have any opportunities!
News
-
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!