Yaoning Yu

Yaoning Yu

Master student at Uchicago

Yaoning Yu’s Personal Page

I’m Yaoning Yu, a Data Scientist & AI Engineer at Ekohe while conducting research with Dr. Haohan Wang at UIUC (University of Illinois Urbana-Champaign) Dream Lab. Previously, I earned my Bachelor’s degree in Mathematics from the University of Washington (UW) and Masters from Uchicago. During my time at UW, I worked with George Manucharyan in topics of Ocean Dynamics, mainly responsible for utilizing ML strategies to solve unknown deep ocean activities. I also worked with Dr. Yuan Tian at the UCLA Security Lab on LLM security.

Research Interest

My research interests lie in Machine Learning, LLM-based Multi-Agent Systems (MAS), Multimodal Large Language Models, and AI Security. Additionally, I’m eager to explore other emerging fields(or any related areas) and apply these advances, especially in embodied AI, to solve real-world problems and deliver tangible and meaningful value to communities.

Current Projects

  • Brainz: A knowledge graph and LLM-agent platform developed at Ekohe. Brainz connects multi-source project data such as GitHub, GitLab, Google Drive, and other collaboration tools, then builds a dynamic knowledge graph to help teams learn from past experience, retrieve relevant context, and reason across projects using LLMs. Contact me for a demo request or interested in using it!
  • ThreadBench: A benchmark for evaluating the realism of LLM-based agentic simulations of real-world online discussions. Threadbench focuses on measuring how closely simulated discussions match real human discussions across linguistic, semantic, emotional, structural, and behavioral dimensions, with applications in social simulation.
  • Heelo: An agent-native infrastructure platform that enables AI agents to reliably execute real-world tasks. Heelo introduces Agent-Native Primitives (paper at: https://arxiv.org/pdf/2611.07461), which encapsulate tools, code, and knowledge into reusable, intelligent units. It dynamically composes task-specific agent harnesses, coordinates execution across resources, and continuously improves reliability through feedback and verification.
  • TopCited: An AI search visibility and Generative Engine Optimization (GEO) platform that helps businesses understand and improve how they are discovered, cited, and recommended by AI systems such as ChatGPT and Gemini. TopCited combines AI visibility monitoring, competitive analysis, content optimization, and agent-driven execution to help brands become more discoverable in AI-generated answers.

Services

  • Reviewer: NeurIPS, ICLR 2026

</div>