Designing Collaborative AI Systems for Work by Valerie Chen

Abstract: Contemporary AI systems are not explicitly designed for collaboration; nevertheless, they are increasingly working alongside human co-workers across real-world sectors. This rapid shift has profound implications for the future of work and for how we build AI systems. In this talk, I present a vision for building AI co-workers that collaborate productively and reliably with humans, using software engineering as a case study. In the first part of the talk, I describe new systems and methods for measuring the collaborative capabilities of AI systems, moving beyond static benchmarks toward interactive, in-the-wild settings. In the second part, I discuss how to optimize interactions with humans via interfaces, highlighting work on proactive agents that can handle complex user contexts. I will conclude by outlining future directions for collaborative AI in an increasingly automated world.

Bio: Valerie Chen is a Machine Learning PhD student at CMU. Her work bridges machine learning, natural language processing, and human-computer interaction to advance the design of collaborative AI systems. Her research has fostered close collaborations with major engineering and financial companies, with findings cited by leading model providers and deployed in industry products. Valerie has been recognized with the Rising Stars in Data Science award, CMU Presidential Fellowship, and the NSF Graduate Research Fellowship. Her research has also received various awards, including Best Paper at a NeurIPS workshop and Oral Presentations at ICLR and AAAI.