Home
Hey, I’m Bohan Yao. I’m currently a Master’s student at New York University Courant studying computer science. Previously, I obtained my Bachelor’s in computer science and mathematical statistics at the University of Washington. I previously interned at ServiceNow throughout 2024-2026, where I worked on LLM post-training, multimodal agentic reasoning systems, and self-evolving agentic systems.
I work on natural language processing (NLP) research, and my primary research interest is in developing agentic systems that can complete complex tasks requiring long-horizon planning, accurately navigate noisy environments, and jointly reason about many different data modalities. I have worked on research involving tool-augmented LLM frameworks and multimodal agentic reasoning systems.
I am currently searching for Fall 2028 PhD positions for multimodal agentic systems. Please reach out if you have any opportunities/information.
Publications
- Hybrid Retriever Evolution for Multimodal Document Reasoning Agents
Bohan Yao, Shiva Krishna Reddy Malay, Vikas Yadav
PDF - ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems
Bohan Yao, Shiva Krishna Reddy Malay, Vikas Yadav
The 5th Workshop on Mathematical Reasoning and AI @ NeurIPS (2025)
PDF - Diverse Multi-tool Aggregation with Large Language Models for Enhanced Math Reasoning
Bohan Yao, Vikas Yadav
EMNLP Findings (2025) & The 5th Workshop on Mathematical Reasoning and AI @ NeurIPS (2025)
PDF
Contact
I am interested in collaborating on agentic systems, LLM reasoning, and AI for science research. If you have any interesting projects you think I would be a good fit for or want to talk for any other reasons, please reach out via email.
