The talk entitled “Knowledge Graphs + AI: The Evolution of Automated GitHub Issue Resolution“, will be presented by Prof. He Ye on November 17th, at 14:30, in room B008, moderated by Prof. Alexandra Mendes (DEI).
Abstract:
“AI coding agents are becoming increasingly capable, achieving strong results on benchmarks such as SWE-bench. However, most still struggle with real-world challenges such as issue reproduction, precise context retrieval from large codebases, and the high cost of LLMs. In this talk, I will introduce our recent code agent, Prometheus — a knowledge graph-powered, multi-agent system designed to tackle GitHub issues in practice. Prometheus transforms entire repositories into a unified knowledge graph stored in Neo4j for scalable and structured reasoning. This enables precise, cross-language context retrieval, allowing large language models to generate accurate and efficient fixes. Prometheus delivers robust performance, resolving diverse issues across seven programming languages. I will show how combining LLMs with knowledge graphs can advance automated issue resolution beyond today’s benchmark-driven limits. We have recently transitioned this research into an off-the-shelf product that helps industry resolve software issues automatically.”
About the Speaker:
He Ye is an Assistant Professor at University College London. She previously worked as a Postdoctoral Researcher at Carnegie Mellon University and received her PhD from KTH Royal Institute of Technology. Her research centers on developing the next generation of code agents to automate software engineering tasks, with a focus on codebase context retrieval, automated issue resolution, and code agent memory construction. Beyond academia, she is the co-founder of EuniAI, a startup committed to turning research into real-world solutions that help developers address practical software challenges.