Thank you for visiting! I'm Long, a fourth-year CS Ph.D. student at the National University of Singapore, advised by Professors Min-Yen Kan, Kenji Kawaguchi, Nancy F. Chen. I also collaborate closely with Prof. Shafiq Joty from Salesforce AI Research. My research builds AI agents that self-improve at test time, enabling autonomous optimization, verification, and correction of their own behaviors:

  1. Multimodal & Long-Horizon Self-Improvement Agents: scaling closed-loop test-time self-improvement for complex visual reasoning and multimodal synthesis [A²RD (preprint), VISTA (CVPR'26)].
  2. Agentic Discovery & Self-Adaptation: designing test-time scaling algorithms and multi-agent architectures that iteratively discover new solutions and refine prompts, reasoning trajectories, and model outputs [SpecEvo (preprint), adv-ICL (ACL'24 Oral), Multi-expert Prompting (EMNLP'24), LongGuide (ACL'25)].
  3. Metacognition, Evaluation & Safety of Agents: diagnosing failure modes, biases, and unintended side effects of foundation models and self-evolving agents [SWE-MISBEHAVIOR (preprint), NLPromptEval (ACL'25), FormatBias (NAACL'25), xCodeEval (ACL'24), ChartQA (ACL'22)].

During my PhD, I spent a wonderful year in the Bay Area interning at Google Cloud AI Research and Amazon Core Search. I am fortunate to have received the NUS Computing Dean's Graduate Research Excellence Award, the DAAD AInet Fellowship, the NUS Computing Research Achievement Award, and the TMLR Certification. I received my B.Sc. in Mathematics (Statistics) and Computer Science from Nanyang Technological University in 2023, where I won the SPMS Outstanding Undergraduate Award (Outstanding Achievement).

Please contact me via email for collaborations!

News

Selected Publications

For the full list of my publications: Google Scholar

  1. Do Xuan Long, Yale Song, Min-Yen Kan, Tomas Pfister, Long T. Le. A²RD: Agentic Autoregressive Diffusion for Long Video Consistency. arXiv preprint, 2026. Featured by Google Research.
  2. Do Xuan Long, Xingchen Wan, Hootan Nakhost, Chen-Yu Lee, Tomas Pfister, Sercan Ö. Arık. VISTA: A Test-Time Self-Improving Video Generation Agent. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. Adopted by Google DeepMind and YouTube Media.
  3. Do Xuan Long, Duy Dinh, Ngoc-Hai Nguyen, Kenji Kawaguchi, Nancy F. Chen, Shafiq Joty, Min-Yen Kan. What Makes a Good Natural Language Prompt? Annual Meeting of the Association for Computational Linguistics (ACL), 2025
  4. Zixuan Ke, Fangkai Jiao, Yifei Ming, Xuan-Phi Nguyen, Austin Xu, Do Xuan Long, Minzhi Li, Chengwei Qin, Peifeng Wang, Silvio Savarese, Caiming Xiong, Shafiq Joty. A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems. Transactions on Machine Learning Research (TMLR), 2025 (Survey Certification)
  5. Do Xuan Long, Yen Duong, Anh Tuan Luu, Kenji Kawaguchi, Min-Yen Kan, Nancy F. Chen. Multi-expert Prompting Improves Safety, Reliability, and Usefulness of Large Language Models. Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
  6. Do Xuan Long*, Yiran Zhao*, Hannah Brown*, Yuxi Xie, James Xu Zhao, Nancy F. Chen, Kenji Kawaguchi, Michael Qizhe Xie, Junxian He. Prompt Optimization via Adversarial In-Context Learning. Annual Meeting of the Association for Computational Linguistics (ACL), 2024 (Oral)
  7. Mohammad Abdullah Matin Khan*, M Saiful Bari*, Do Xuan Long, Weishi Wang, Md Rizwan Parvez, Shafiq Joty. xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval. Annual Meeting of the Association for Computational Linguistics (ACL), 2024
  8. Ahmed Masry*, Parsa Kavehzadeh*, Do Xuan Long, Enamul Hoque, Shafiq Joty. UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning. Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023
  9. Ahmed Masry, Do Xuan Long, Jia Qing Tan, Shafiq Joty, Enamul Hoque. ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning. Findings of the Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2022

Papers done by students I have mentored or collaborated with closely.

  1. Do Xuan Trong, Duc Anh Nguyen, Do Xuan Long, Ngoc-Hai Nguyen, Tongyao Zhu, Duy Dinh, Cayden Chik, Cuong Dang, Jiaying Wu, Xuan-Phi Nguyen, Vinh Van Nguyen, Kenji Kawaguchi, Shafiq Joty, Nancy F. Chen, Min-Yen Kan. SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents. arXiv preprint, 2026
  2. Ha Minh Hieu, Tongyao Zhu, Do Xuan Long, Min-Yen Kan. SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery. arXiv preprint, 2026
  3. Vu Duc Anh, Nhat M Hoang, Do Xuan Long, Cong-Duy Nguyen, Ponhvoan Srey, Luu Anh Tuan. Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs. Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP Findings), 2026
  4. Nhat M Hoang, Do Xuan Long, Cong-Duy Nguyen, Min-Yen Kan, Luu Anh Tuan. A Comparative Analysis of Contextual Representation Flow in State-Space and Transformer Architectures. arXiv preprint, 2025
  5. Nhat M Hoang*, Do Xuan Long*, Duc Anh Do, Duc Anh Vu, Luu Anh Tuan. ToXCL: A Unified Framework for Toxic Speech Detection and Explanation. Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024

Educations

  1. Ph.D. in Computer Science (Aug. 2023 - Present)
    National University of Singapore (NUS), 21 Lower Kent Ridge Rd, Singapore
    Advised by Min-Yen Kan, Kenji Kawaguchi, Nancy Chen
  2. B.Sc. in Mathematical and Computer Sciences (Aug. 2019 - Jul. 2023)
    Nanyang Technological University, Singapore (NTU), 50 Nanyang Ave, Singapore
    Advised by Shafiq Joty, Double Major, Honours, Highest Distinction

Selected Research Experiences

  1. Student Researcher (Jan. 2026 - Jul. 2026)
    Google Cloud AI Research, San Francisco Bay Area, California, United States
    Hosted by Long T. Le and Yale Song
  2. Applied Scientist Intern (Aug. 2025 - Nov. 2025)
    Amazon Core Search, San Francisco Bay Area, California, United States
    Hosted by Hsiang-Fu Yu
  3. Student Researcher (May 2025 - Jul. 2025)
    Google Cloud AI Research, San Francisco Bay Area, California, United States
    Hosted by Xingchen Wan and Sercan Ö. Arik
  4. NTU President Research Scholar (Jul. 2021 - Jul. 2023)
    Natural Language Processing group at NTU (NTU-NLP), Singapore
    Under FYP-URECA programme, advised by Prof. Shafiq Rayhan Joty
  5. Research Intern (Dec. 2021 - Jan. 2023)
    Institute for Infocomm Research, A*STAR, Singapore
    Advised by Bowei Zou and Nancy F. Chen

Academic Services

Area Chair

  • Conferences: ARR Oct 2026 (NAACL 2027), ARR May 2026 (EMNLP/AACL 2026)

Reviewer

  • Journals: ACM Computing Surveys (2026), IEEE IJCV (2026), IEEE TIP (2025), IEEE TPAMI (2025), IEEE/ACM TASLP (2023-2022)
  • Conferences: ICLR (2027-2024), NeurIPS (2026-2025), AAAI (2027), AAMAS (2027), ACL (2026-2024), EMNLP (2026-2024), NAACL (2025-2024), EACL (2026), ACL RR (2026-2022). I have multiple ARR Great Reviews in 2024, 2025, 2026.
© Last Updated: October 2026