Peter Baile Chen



© 22-25 Peter Baile Chen
Last update: 12/11/2025
profile

Hi! I am Peter (陳百樂), a PhD student at MIT CSAIL. My research lies at the intersection of data systems and natural language processing. I am fortunate to work with Mike Cafarella, Mike Stonebraker, Sam Madden, Dan Roth, and Jacob Andreas. I graduated from the University of Pennsylvania with a BSE degree. At Penn, I had the chance to work with Zack Ives, Sebastian Angel, and Vincent Liu. I am currently supported by Google PhD Fellowship in collaboration with MIT. I was previously supported by the Croucher scholarship.

Advancing AI requires far more than simply building smarter language models. On their own, models face clear limits: they do not naturally optimize solution strategies under real-world constraints like latency or cost, they struggle to reuse knowledge across tasks, and they often execute plans inefficiently, especially when coordinating across multiple models and external tools. My research focuses on designing system and software infrastructure that surrounds and augments language models, enabling AI to optimize for practical, multi-objective goals such as accuracy, efficiency, and budget.

Optimizable AI System (OAISYS): A unified system for optimizing AI performance

Offline knowledge manager enables online planner to draw on experiences and knowledge from previously completed tasks or from offline-built corpus enhancements.

→

Online planner helps models derive optimal solution plans for complex tasks, guided by real-life criteria such as accuracy and efficiency.

←

Executor enables online planner to execute optimal solution plans based on available LLM tools.

My research also involves building datasets and benchmarks that evaluate AI performance, including Beaver for enterprise Text-to-SQL and MDCR for multi-document conditional reasoning.

News