Carnegie Mellon University & University of Porto
I am a PhD candidate in Software Engineering at Carnegie Mellon University and the University of Porto (CMU Portugal dual degree), graduating in August 2026.
The goal of my research is to make software development more accessible and trustworthy through agentic LLM systems, paired with the evaluation methodology needed to know whether they actually work. I work towards this goal across three threads:
- Visual interfaces to code — agentic systems that turn hand-drawn sketches into runnable code and code into visual documentation (SPLASH'23, ICSE'25);
- Evaluation methodology — LLM-as-judge metrics validated against human evaluation, and reference-free frameworks for scoring generated artifacts (ASE'26);
- Developer studies — controlled experiments on how developers work with AI assistants inside the IDE (ICSE'25).
Open to Research Scientist / Research Engineer roles in AI for software engineering, agents, and reasoning.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Carnegie Mellon UniversitySchool of Computer Science
Ph.D. in Software Engineering (CMU Portugal)Aug. 2021 - Aug. 2026 -
University of PortoPh.D. in Computer Science (CMU Portugal)
Dual DegreeAug. 2021 - Aug. 2026with Rui Abreu -
University of MinhoB.Sc. + M.Sc. in Computer Science (Intelligent Systems & Data Science)Sep. 2015 - Aug. 2021
Honors & Awards
-
CMU Portugal Fellowship2021 - 2026
-
Huawei Scholarship — Top Students in Portugal (top 1%)2023
-
FCT Research Fellowships (×2)2018 - 2021
News
Selected Publications (view all )
VisDocSketcher: Towards Scalable Visual Documentation with Agentic Systems
Luís F. Gomes, Xin Zhou, David Lo, Rui Abreu
Submitted to International Conference on Software Engineering (ICSE) 2026 Under Review
An agentic LLM system that generates high-level visual documentation from source code, paired with AutoSketchEval — a reference-free evaluation framework (inspired by autoencoder reconstruction) that scores diagram quality with no ground truth, reaching AUC > 0.87 across 1,000 Jupyter notebooks.
VisDocSketcher: Towards Scalable Visual Documentation with Agentic Systems
Luís F. Gomes, Xin Zhou, David Lo, Rui Abreu
Submitted to International Conference on Software Engineering (ICSE) 2026 Under Review
An agentic LLM system that generates high-level visual documentation from source code, paired with AutoSketchEval — a reference-free evaluation framework (inspired by autoencoder reconstruction) that scores diagram quality with no ground truth, reaching AUC > 0.87 across 1,000 Jupyter notebooks.
An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks
Xin Zhou, Kisub Kim, Ting Zhang, Martin Weyssow, Luís F. Gomes, Guang Yang, David Lo
International Conference on Automated Software Engineering (ASE) 2026
A study of LLM-as-judge metrics for software engineering tasks, calibrated to bridge the gap with human evaluation across a range of SE benchmarks.
An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks
Xin Zhou, Kisub Kim, Ting Zhang, Martin Weyssow, Luís F. Gomes, Guang Yang, David Lo
International Conference on Automated Software Engineering (ASE) 2026
A study of LLM-as-judge metrics for software engineering tasks, calibrated to bridge the gap with human evaluation across a range of SE benchmarks.
An Exploratory Study of ML Sketches and Visual Code Assistants
Luís F. Gomes, Jonathan Aldrich, Rui Abreu, Vincent Hellendoorn
International Conference on Software Engineering (ICSE) 2025
A VSCode assistant that turns hand-drawn ML workflow sketches into runnable Jupyter notebooks (79% structural accuracy, 49% reduction in coding), with a 19-participant developer study and an automated LLM-as-judge pipeline benchmarking sketch-to-code across GPT-4o, Gemini Pro, and Claude.
An Exploratory Study of ML Sketches and Visual Code Assistants
Luís F. Gomes, Jonathan Aldrich, Rui Abreu, Vincent Hellendoorn
International Conference on Software Engineering (ICSE) 2025
A VSCode assistant that turns hand-drawn ML workflow sketches into runnable Jupyter notebooks (79% structural accuracy, 49% reduction in coding), with a 19-participant developer study and an automated LLM-as-judge pipeline benchmarking sketch-to-code across GPT-4o, Gemini Pro, and Claude.