Juyong Lee

I am a PhD(/MS int.) student at KAIST, advised by Kimin Lee. I received a B.S. degree with a double major in both mathematics and computer science/engineering at POSTECH. I have an experience as an exchange student at Stanford. Recently, I am working as a research engineer (contractor via YunoJuno) at Google DeepMind.

My main research interest is to build capable and reliable AI agents, currently focusing on digital tasks (e.g., web tasks).

CV / Google Scholar / Github

Research Highlights

(*: equal contribution)

	MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control Juyong Lee, Dongyoon Hahm, June Suk Choi, W. Bradley Knox, Kimin Lee AAAI 2026 (AI Alignment Track)* project / paper / code We propose a new benchmark for evaluating the safety and helpfulness of agents, with extensive analysis of the shortcomings of frontier LLM agents in mobile device control.
	B-MoCA: Benchmarking Mobile Device Control Agents across Diverse Configurations Juyong Lee, Taywon Min, Minyong An, Dongyoon Hahm, Haeone Lee, Changyeon Kim, Kimin Lee CoLLAs 2025; ICLR 2024 Workshop: GenAI4DM (spotlight presentation) project / paper / code A novel benchmark that can serve as a unified testbed for mobile device control agents on performing practical daily tasks across diverse device configurations.
	Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents Dongjun Lee, Juyong Lee, Kyuyoung Kim, Jihoon Tack, Jinwoo Shin, Yee Whye Teh, Kimin Lee ICLR 2025 project / paper A novel framework of training a contextualization module to help the decision-making of LLM agents achieves the super-human performance in the WebShop benchmark.
	Style-Agnostic Reinforcement Learning Juyong Lee, Seokjun Ahn, Jaesik Park ECCV 2022 paper / code Reinforcement learning agents become robust to the changes in the style of the image (e.g., background color) by adapting to adversarially generated styles.

The source code is from here