Yike Jin

I am pursuing a Bachelor of Engineering (B.Eng.) at Zhejiang University, majoring in Industrial Design in the College of Computer Science & Technology.

My research interests include GUI Agents, Multimodal Large Language Models, and Lifelong Agent Learning. I am interested in how agents acquire reusable skills, organize memory, and improve through interaction.

I am seeking Ph.D. / M.S. opportunities in Computer Science for Fall 2027. Feel free to get in touch!

Email: yikejin02@gmail.com University email

GitHub+86 19905791210

News

2026 Our work on LLM sycophancy and AI-assisted decision-making appears at CHI 2026. Read the paper ↗
Dec 2025 Awarded a Kaggle silver medal in the MABe Challenge — Social Action Recognition in Mice.

Publications & Manuscripts

View all →

* Equal contribution. Work under review is labeled below.

GUIHub framework: adapter profiling builds capability vectors, target-level adaptation selects LoRA adapters, and request-time serving reuses their weighted composition for GUI actions.

GUIHub: Privacy-Preserving GUI Agent Collaboration via Capability-Driven LoRA Composition

Xuerong Liu*, Yike Jin*, Hongming Piao*, Shuguang Wang, Dapeng Wu, Ying Wei

Under review · 2026

Capability-driven collaboration among GUI agents through application-specific LoRA adapters, capability-aware routing, and expert composition. My work includes training 14 adapters and evaluating composition and retrieval baselines across IID, OOD, evolving-hub, and storage-constrained settings.

MethodMate workflow: proactive conversation guidance, paper search and review, quantitative research proposal generation, evaluation, iteration, and finalization through user–LLM collaboration.

MethodMate: Supporting Novice HCI Researchers in Designing Quantitative Research Proposals with LLMs

Zejian Li, Qi Liu, Yike Jin, Yixiang Zhou, Rongjie Mao, Pei Chen

Under review · 2026

A literature-grounded LLM system that supports quantitative research proposal design. I developed the full-stack system and contributed to formative research, workflow design, and three user studies.

LLM sycophancy study procedure: pre-task surveys, investment and speed-dating decisions with randomly assigned AI feedback conditions, and post-task workload and trust surveys.

Does Sycophancy Change Decisions? Effect of LLM Sycophancy on AI-Assisted Decision-Making

Zejian Li, Jiaman Pan, Qi Liu, Yuning Xi, Yixiang Zhou, Yike Jin, Rongjie Mao, Pei Chen

Paper ↗

CHI 2026

Investigating how opinion agreement, direct praise, and self-deprecation affect AI-assisted decisions. I contributed to the experimental platform and a mixed-design online study with 106 participants.

Research

I focus on two connected directions:

Self-evolving skill systems: the full skill lifecycle for autonomous GUI agents, from discovery and acquisition to evaluation, refinement, reuse, and composition across applications.
Parametric agent memory: storing skills, procedural knowledge, and interaction trajectories in model parameters or lightweight adapters for efficient retrieval and continual updates.

Jul 2026– In progress

Self-Evolving Skill Learning for Web Agents

Yike Jin*, Hongming Piao*, Ying Wei

Exploring a closed loop of capability-driven exploration, skill acquisition, composition, and validation, with adaptive textual, parametric, or hybrid skill representations. The framework is being evaluated on WebArena.

Education

Zhejiang University

Sep 2023 – Present · Hangzhou, China

College of Computer Science & Technology
Bachelor of Engineering (B.Eng.) · In progress

GPA: 90.94 / 100Rank: 1 / 42IELTS: 7.5GRE: Preparing

Patent

A Method and System for LLM-Based Ideation of Quantitative Research Proposals

Qi Liu, Yike Jin, Yixiang Zhou, Jiaman Pan, Zejian Li

Granted Chinese invention patent, 2026
Second-named inventor · Zhejiang University
Application No. 202610493355.1

Awards and Honors

Dec 2025 Kaggle Competition Silver MedalMABe Challenge — Social Action Recognition in Mice
2023-2024 Second-class ScholarshipZhejiang University · Academic excellence
2023-2024 NITORI International ScholarshipAwarded to 20 undergraduate students annually at Zhejiang University
2023-2024 Academic Excellent AwardZhejiang University · Academic excellence
Dec 2021 NOIP 2021, First PrizeNational Olympiad in Informatics in Provinces, Zhejiang Division
Dec 2020 NOIP 2020, Second PrizeNational Olympiad in Informatics in Provinces, Zhejiang Division
Dec 2018 NOIP 2018, Junior Group, First PrizeNational Olympiad in Informatics in Provinces, Junior Group, Zhejiang Division
2019-2021 CSP-S, Level I (2020); Level II (2021)CCF Certified Software Professional – Senior

Yike Jin 🧑‍🚀