Lajanugen Logeswaran

I am a Research Scientist at LG AI Research, where I work on building AI agents that can reason, plan, and act in digital environments. My recent work focuses on scalable training and evaluation for GUI agents, visual grounding, and improving the planning and reasoning capabilities of large language models and vision-language models.

I received my PhD in Computer Science from the University of Michigan. During my PhD, I worked on representation learning, learning from limited supervision, language grounding, and structured reasoning. Broadly, I am interested in building models that connect language, perception, knowledge, and action.

Professional Experience

• Research Scientist, LG AI Research, Ann ArborJul 2021–Present
• Research Intern, Facebook AI Research, New YorkMay 2019–Aug 2019
• Research Intern, Google Research, SeattleMay 2018–Jan 2019
• Research Intern, Google Brain, Mountain ViewFeb 2017–Jun 2017

Education

• PhD, Computer Science & Engineering
  University of Michigan
  Advisor: Honglak Lee2015–2021
• BSc, Electronic & Telecommunication Engineering
  University of Moratuwa, Sri Lanka2009–2014

Selected Publications

For a complete list of publications, please see my Google Scholar profile.

Agent training: data and environments

• ScreenTutor: Learning Computer-Use Agents from Unlabeled Tutorial Videos
  Yeda Song, Ryan Kwon, Ruijie Chen, Jaekyeom Kim, Lajanugen Logeswaran, Tiange Luo, Sungryull Sohn, Honglak Lee
  COLM 2026 Lifelong Agents Workshop

• Scaling Web Agent Training through Automatic Data Generation and Fine-grained Evaluation
  Lajanugen Logeswaran, Jaekyeom Kim, Sungryull Sohn, Creighton Glasscock, Honglak Lee
  COLM 2025

• Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents
  Yunseok Jang*, Yeda Song*, Sungryull Sohn, Lajanugen Logeswaran, Tiange Luo, Dong-Ki Kim, Kyunghoon Bae, Honglak Lee
  CVPR 2025

Evaluation, verification and reward modeling

• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation
  Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim, Sungryull Sohn, Yunxiang Zhang, Moontae Lee, Hao Peng, Lu Wang, Honglak Lee
  EMNLP Findings 2026

• Process Reward Models That Think
  Muhammad Khalifa, Rishabh Agarwal, Lajanugen Logeswaran, Jaekyeom Kim, Hao Peng, Moontae Lee, Honglak Lee, Lu Wang
  TMLR 2026

• 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

• Small Language Models Need Strong Verifiers to Self-Correct Reasoning
  Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim, Moontae Lee, Honglak Lee, Lu Wang
  ACL Findings 2024

Planning, reasoning and grounding

• Visual Test-time Scaling for GUI Agent Grounding
  Tiange Luo, Lajanugen Logeswaran, Justin Johnson, Honglak Lee
  ICCV 2025 Spotlight

• AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
  Yao Fu, Dong-Ki Kim, Jaekyeom Kim, Sungryull Sohn, Lajanugen Logeswaran, Kyunghoon Bae, Honglak Lee
  NeurIPS 2024

• Few-shot Subgoal Planning with Language Models
  Lajanugen Logeswaran, Yao Fu, Moontae Lee, Honglak Lee
  NAACL 2022

Unsupervised and few-shot learning

• Zero-Shot Entity Linking by Reading Entity Descriptions
  Lajanugen Logeswaran, Ming-Wei Chang, Kenton Lee, Kristina Toutanova, Jacob Devlin, Honglak Lee
  ACL 2019 Best Paper Nomination

• Content Preserving Text Generation with Attribute Controls
  Lajanugen Logeswaran, Honglak Lee, Samy Bengio
  NeurIPS 2018

• An Efficient Framework for Learning Sentence Representations
  Lajanugen Logeswaran, Honglak Lee
  ICLR 2018

Awards & Honors

• Social Impact Award, NAACL2024
• Best Paper Nomination, ACL2019
• Bronze Medal, 50th International Mathematical Olympiad2009
• Gold Medal, Sri Lankan Mathematics Olympiad2007