I am a 4th year CS Ph.D. candidate at the LAUNCH Lab, University of Michigan – Ann Arbor, advised by Prof. Lu Wang. I obtained my Bachelor’s degree from Peking University, advised by Prof. Xiaojun Wan.

I work on LLM reasoning and agents.

News

• 2026-05: Excited to start a Research Scientist internship at Meta!
• 2026-05: Thrilled to receive ICML 2026 Silver Reviewer Award!
• 2026-04: AdaMEM, which focuses on test-time adaptive agent memory, has been accepted to ICML 2026.
• 2026-04: ThinkLogit, which focuses on inference-time compute for long reasoning, has been accepted to ACL Findings 2026. See you in San Diego!
• 2026-01: MLE-Ideator, which focuses on reinforcement learning for MLE agent, has been accepted to EACL 2026.

Selected Publications

• AdaMEM: Test-Time Adaptive Memory for Language Agents
  Yunxiang Zhang, Yiheng Li, Ali Payani, Lu Wang
  ICML 2026 [paper] [code] [project page]
• Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
  Yunxiang Zhang, Muhammad Khalifa, Lechen Zhang, Xin Liu, Ayoung Lee, Xinliang Frederick Zhang, Farima Fatahi Bayat, Lu Wang
  Findings of ACL 2026 [paper] [code]
• Learning to Ideate for Machine Learning Engineering Agents
  Yunxiang Zhang, Kang Zhou, Zhichao Xu, Kiran Ramnath, Yun Zhou, Sangmin Woo, Haibo Ding, Lin Lee Cheong
  EACL 2026 [paper]
• MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?
  Yunxiang Zhang, Muhammad Khalifa, Shitanshu Bhushan, Grant D Murphy, Lajanugen Logeswaran, Jaekyeom Kim, Moontae Lee, Honglak Lee, Lu Wang
  NeurIPS 2025 Datasets and Benchmarks Track [paper] [project page] [code]
• Small Language Models Need Strong Verifiers to Self-Correct Reasoning
  Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim, Moontae Lee, Honglak Lee, Lu Wang
  Findings of ACL 2024 [paper] [code] [project page]
• Merging Generated and Retrieved Knowledge for Open-Domain QA
  Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang
  EMNLP 2023 [paper] [code]
• SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoning
  Yunxiang Zhang, Xiaojun Wan
  NeurIPS 2023 Datasets and Benchmarks Track [paper] [data]
• MOVER: Mask, Over-generate and Rank for Hyperbole Generation
  Yunxiang Zhang, Xiaojun Wan
  NAACL 2022 [paper] [code]
• Interpreting the Robustness of Neural NLP Models to Textual Perturbations
  Yunxiang Zhang, Liangming Pan, Samson Tan, Min-Yen Kan
  Findings of ACL 2022 [paper]
• BiRdQA: A Bilingual Dataset for Question Answering on Tricky Riddles
  Yunxiang Zhang, Xiaojun Wan
  AAAI 2022 [paper] [data]

Services

Co-Organizer, 1st Workshop on Test-Time Scaling and Reasoning Models, COLM 2025

Student Volunteer, ACL 2024

Reviewer: TMLR, ICML (2025-26), AISTATS (2025), ICLR (2025-26), NeurIPS (2024-25), ACL Rolling Review (2024-26), COLM (2024, 2026), EMNLP (2022-24), ACL (2023), CoNLL (2023-24), ACM Computing Surveys