Guest Lecture on LLM Agents
Invited two-hour guest lecture on LLM agents at McGill University.
Imene Kerboua
I’m Imene (pronounced /iman/), I’m currently a second year PhD Student at INSA Lyon and Esker. My work focuses on NLP and Agents for Web navigation.
I worked as a Data Scientist for almost 2 years before starting my PhD, I worked with an amazing team and learned a lot about software development.
I enjoy NLP related subjects and open-source, I worked on the MTEB extension to French, and MMTEB the scaling of MTEB to multiple languages especally low-ressource ones.
Aside from research, I enjoy hiking, reading interesting books and painting.
Teaching
AI Agents
Introduction to AI Agents, specificaly to LLM agents.
Course detailsCloud Computing
Introduction to Cloud Computing using Azure.
Course detailsObject Oriented Programming with Python
Object Oriented Programming with Python for Master’s students: classes, inheritance, and writing maintainable Python.
Advanced SQL
Advanced SQL for Master’s students: complex queries, joins, window functions and query optimisation.
Projects
FocusAgent
Simple yet effective ways of trimming the large context of web agents: a small retriever model reads the page and keeps only the lines that matter, so the acting model sees a much smaller observation — and never reads pruned prompt-injection content.
VisitMMTEB
Scaling MTEB to many languages, with a focus on low-resource ones.
VisitMTEB French
Extension of the Massive Text Embedding Benchmark to French.
VisitPublications
Does The Way You Plan Matter? An Empirical Study of Planning Representations for LLM Web Agents
WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents
FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents
LineRetriever: Planning-Aware Observation Reduction for Web Agents
Maintaining MTEB: Towards Long Term Usability and Reproducibility of Embedding Benchmarks
MTEB-FR : une expérience à large échelle pour l'apprentissage de représentation en français
MTEB-French: Resources for French Sentence Embedding Evaluation and Analysis
Resume
Work experience
AI PhD Student·Esker
May 2023 – present
- CIFRE partnership with LIRIS and INSA Lyon.
- Working on autonomous web agents and embeddings evaluation.
Teacher Assistant·Université Lumière Lyon 2
September 2024 – February 2026
- Cloud Computing with Azure (Master's).
- MLOps with Azure (Master's).
Visiting Researcher·Mila – Quebec AI Institute
August 2025 – November 2025
- Research visit in Montréal, Canada.
Lecturer·Groupe GEMA
October 2022 – January 2023
- Part-time Master's classes, alongside the Data Scientist role at Cygogn.
- Object Oriented Programming with Python, advanced SQL and NLP.
Data Scientist·Cygogn
September 2021 – April 2023
- Model development and deployment on AWS.
- BI and data engineering.
Data Scientist NLP·Once For All France
March 2021 – September 2021
- Developed models for email classification.
Frontend Web Developer·SFR Business
June 2020 – September 2020
- Developed an app for data visualization using Symfony and ReactJS.
Machine Learning Researcher·LRIA Lab, USTHB
February 2019 – June 2019
- Conception and implementation of a hybrid recommender system based on deep learning.
Education
Ph.D in Machine Learning·INSA Lyon
December 2023 – December 2026
M.S. in Computer Science, Data Mining·Université Lumière Lyon 2
September 2019 – September 2021
B.S. in Information Systems and Software Engineering·USTHB
September 2016 – July 2019