
Qile Jiang developed the Automated Academic Research Assistant feature for the ContextualAI/examples repository, delivering an end-to-end research automation workflow. Leveraging Python, CrewAI, and the ArXiv API, Qile designed a multi-agent system that automates academic paper discovery, processing, and knowledge extraction. The system coordinates contextual AI tools to build a queryable knowledge base from retrieved papers, enabling users to ask questions and receive answers grounded in academic literature. This work demonstrates depth in multi-agent orchestration and retrieval-augmented generation, addressing the challenge of automating complex research tasks. The feature was delivered in one month, reflecting focused engineering and technical execution.

In August 2025, delivered the Automated Academic Research Assistant feature in ContextualAI/examples, implementing a CrewAI-based multi-agent system that automates academic research from paper discovery to knowledge extraction using ArXiv and contextual AI tools, with a queryable knowledge base to answer questions.
In August 2025, delivered the Automated Academic Research Assistant feature in ContextualAI/examples, implementing a CrewAI-based multi-agent system that automates academic research from paper discovery to knowledge extraction using ArXiv and contextual AI tools, with a queryable knowledge base to answer questions.
Overview of all repositories you've contributed to across your timeline