Accede a Declaración de AccesibilidadAccede al menú principalAccede al pieAccede al contenido principal
Español

Agentic AI Researcher: Initial Experiences and Outlook

Agentic AI Researcher: Initial Experiences and Outlook

Organizado por Escuela Politécnica Superior

Christian Esteve Rothenberg

 Universidad de Campinas (UNICAMP), Brasil

  

Resumen/Abstract

 What happens when an AI system does the research itself? For this year's CNSM Agentic AI Researcher track, we gave an AI researcher one prompt and let it write a complete paper: the research question, method, simulation code, experiments, figures and text, with no human edits. The paper was accepted, and three AI reviewers scored it 78, 99 and 95. This keynote shares what we learned from that experiment. It covers what the AI did well, where it fell short, what the reviews reveal about using AI as reviewers, and who should get credit when the key idea comes from the human's prompt. It also draws on lessons from ongoing AI-assisted research practices and on my own work building a "digital brain" that gives AI assistants lasting memory and context. The talk ends with an outlook and some open questions for the research community. 

  

Curriculum ponente

 Christian Esteve Rothenberg is an Associate Professor and head of the Information & Networking Technologies Research & Innovation Group (INTRIG) at the School of Electrical and Computer Engineering (FEEC) of the University of Campinas (UNICAMP), Brazil, where he received his Ph.D. in Electrical and Computer Engineering in 2010. He holds a Telecommunication Engineering degree from the Technical University of Madrid (ETSIT–UPM), Spain, and an M.Sc. (Dipl. Ing.) in Electrical Engineering and Information Technology from the Darmstadt University of Technology (TUD), Germany (2006). From 2010 to 2013 he was a Senior Research Scientist at the CPQD R&D Center in Telecommunications, where he led pioneering SDN activities. His research spans multiple layers of distributed systems and network architectures. Much of it is done with academic and industry partners such as Ericsson, Samsung, CPQD, Padtec and RNP, and it has produced several open-source networking projects, including RouteFlow, libfluid, ofsoftswitch13 and Mininet-WiFi. He has contributed to several international patents, co-authored three books and published in top-tier venues such as SIGCOMM and INFOCOM, totaling more than 15,000 citations (h-index 40+, i10-index 100+). Since 2023, he has been the Principal Investigator of SMARTNESS (SMART Networks and Services for 2030), a FAPESP Engineering Research Center co-funded by Ericsson, with an expected duration until 2033. 

Información del evento

Fechas