Research

Currently interested in LLM agent memory for long/infinite-horizon tasks, continual learning, and long-context reasoning.

Papers

• Hell or High Water: Evaluating Agentic Recovery from External Failures
  Andrew Wang, Sophia Hager, Adi Asija, Daniel Khashabi, Nicholas Andrews.
  COLM, 2025

• Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback
  Dongwei Jiang, Alvin Zhang, Andrew Wang, Nicholas Andrews, Daniel Khashabi.
  NeurIPS, 2025

• Learning Extrapolative Sequence Transformations from Markov Chains
  Sophia Hager, Aleem Khan, Andrew Wang, Nicholas Andrews.
  ICML, 2025

• RATIONALYST: Pre-training Process-Supervision for Improving Reasoning
  Dongwei Jiang, Guoxuan Wang, Yining Lu, Andrew Wang, Jingyu Zhang, Chuyu Liu, Benjamin Van Durme, Daniel Khashabi.
  ACL (main), 2025

• AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies
  Xiao Ye,* Andrew Wang,* Jacob Choi, Yining Lu, Shreya Sharma, Lingfeng Shen, Vijay Tiyyala, Nicholas Andrews, Daniel Khashabi.
  EMNLP (main), 2024

• Learning to Generate Text in Arbitrary Writing Styles
  Aleem Khan, Andrew Wang, Sophia Hager, Nicholas Andrews.
  Arxiv preprint, 2023

• Can Authorship Representation Learning Capture Stylistic Features?
  Andrew Wang,* Cristina Aggazzotti,* Rebecca Kotula, Rafael Rivera-Soto, Marcus Bishop, and Nicholas Andrews.
  TACL, 2023

* equal contribution

Talks

• 2024 JSALT (Annual Frederick Jelinek Memorial Summer Workshop)
  AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies

• EMNLP 2023
  Can Authorship Representation Learning Capture Stylistic Features?

Updated 2025/09/20