Howdy! I’m Weijia Zhang

Research

My research interests center on LLM agents, especially next-generation AI agents that bridge virtual and physical worlds through socially intelligent, tool-agnostic, and ethically grounded architectures.

• Multimodal agents: memory, reasoning, tool use, and multi-agent systems
• Conversational AI: anthropomorphism and social intelligence
• Post-training: agent SFT and RL

News

• 2026.05: 🎉🎓 Graduated from UIUC in Math + Computer Science with the 2026 C.W. Gear Outstanding Undergraduate Student award! 🏆
• 2026.01: 🎉👑 Paper on bias inheritance was accepted to ACL 2026 as an Oral! 📄✨
• 2025.10: 🚀 SeeingEye was released as an arXiv preprint and is under review at EMNLP 2026! 👀📝
• 2025.07: 🎉 Joined Microsoft Research Asia as a research intern! 🔬💼

Gamedev

Beyond research, I am a passoinate indie game developer, feel free to check my game work on the game page. I am also willing to discuss the future of AI X Game.

Education

Yale University

M.S. in Computer Science

2026-08 - 2028-05

Thesis Track with Full Scholarship

University of Illinois Urbana-Champaign

B.S. in Computer Science and Mathematics

2022-08 - 2026-05

2026 C.W. Gear Outstanding Undergraduate Student, one of two annual recipients

GPA: 3.7/4.0

Work Experience

TikTok

Research Scientist Intern, Multimodal LLMs/Agents

Jun 2026 - Present

Researching self-evolving multimodal agents for content moderation.

• Designed a self-evolving content-moderation agent framework centered on a ReAct agent that autonomously analyzes individual videos using specialized tools for frame sampling, ASR/OCR, metadata extraction, originality scoring, and watermark/celebrity detection; integrated multimodal evidence with policy-grounded reasoning to produce structured moderation decisions.
• Built a self-evolution loop where a Reflector aggregates Solver failures into root-cause attribution reports and an Evolver adds, revises, or merges case-relevant skills to refine the Solver, improving the overall F1 score by 15.5%.

Microsoft

Research Scientist Intern

Jul 2025 - Sep 2025

Conducted LLM research for Microsoft 365 Excel Copilot, focusing on spreadsheet text analysis and Office.js code generation.

• Developed the TextAnalysisSFT data pipeline for Excel Copilot's TextAnalysis API: mined 2,000+ real-world examples from Kaggle, filtered text-heavy spreadsheets, generated user queries and Office.js programs, and validated executions with SheetEngine.
• The resulting dataset improved Office Scripts code-generation accuracy by 15%.

Reborn Network

AI Engineer

May 2023 - Jul 2023

Built real-time role-playing agent systems in Unity VR.

• Developed a role-playing agent Unity VR game enabling agents to interact through text, voice, and VR actions in real time with under 1s latency.
• Introduced RAG and vector databases to strengthen long-term agent memory, improving dialogue coherence score from 2/5 to 4/5.
• Designed a reusable character-card framework, enabling a UGC ecosystem and reducing character persona configuration time by 300%.

Tencent, WeChat Group

Software Engineer

Aug 2024 - Sep 2024

Built performance analysis tooling for WeChat Mini Programs and Unity memory profiling.

• Developed a cross-platform Android and iOS hardware performance analysis tool for WeChat Mini Programs, supporting 200+ partner teams in identifying performance bottlenecks.
• Built a Unity Mono Memory Profiler that discovered 40+ hidden memory allocation points, reducing memory-leak-related crash rate by 120%.