Portrait de Maxime Gasse

Maxime Gasse

Membre industriel associé
Professeur associé, Polytechnique Montréal, Département de génie informatique et génie logiciel
Chercheur scientifique principal, ServiceNow
Sujets de recherche
Agent basé sur un LLM
Apprentissage par renforcement
Causalité
Modèles probabilistes

Biographie

Je suis chercheur principal chez ServiceNow à Montréal, où je fais de la recherche à l'intersection de l'inférence causale et de l'apprentissage par renforcement. Je suis professeur adjoint à Polytechnique Montréal et membre associé de Mila – Institut québécois d’intelligence artificielle.

Je suis fasciné par la question de l'intelligence artificielle : pouvons-nous construire des machines qui pensent? Je crois humblement que nos tentatives de concevoir des machines pensantes peuvent être un chemin vers une compréhension fondamentale de l'intelligence et de nous-mêmes.

Étudiants actuels

Maîtrise recherche - Polytechnique
Co-superviseur⋅e :

Publications

Fine-Tuning Web Agents: It Works, But It's Trickier Than You Think
Massimo Caccia
Megh Thakkar
Léo Boisvert
Thibault Le Sellier de Chezelles
Alexandre Piché
Alexandre Lacoste
Recent advancements in large language models (LLMs) have sparked interest in developing autonomous web agents capable of performing digital … (voir plus)tasks through web interfaces in a human-like manner. However, even the strongest closed-source models often struggle to achieve robust results on several benchmarks, while a notable performance gap exists between them and open-source counterparts. This study investigates the potential of fine-tuning to enhance the performance of a smaller, lower-performing but cost-efficient LLM by leveraging successful traces from stronger LLMs, referred to as experts. We outline a comprehensive pipeline for data collection, filtering, and supervised fine-tuning and explore various behavior cloning parameters. Our experiments provide key insights into the challenges of fine-tuning LLMs into web agents on benchmarks like MiniWoB and WorkArena. Notably, we find that the fine-tuned agents' ability to predict expert trajectories does not consistently lead to improved downstream task performance. This raises issues such as off-policy bias and the loss of reasoning abilities during fine-tuning. We discuss potential solutions to these challenges and make both the codebase and a dataset of 140M tokens open-source for the community to build upon.
AgentMerge: Enhancing Generalization in Fine-Tuned LLM Agents
Megh Thakkar
Léo Boisvert
Thibault Le Sellier de Chezelles
Alexandre Piché
Alexandre Lacoste
Massimo Caccia
WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
Léo Boisvert
Megh Thakkar
Massimo Caccia
Thibault Le Sellier de Chezelles
Alexandre Lacoste
The ability of large language models (LLMs) to mimic human-like intelligence has led to a surge in LLM-based autonomous agents. Though recen… (voir plus)t LLMs seem capable of planning and reasoning given user instructions, their effectiveness in applying these capabilities for autonomous task solving remains underexplored. This is especially true in enterprise settings, where automated agents hold the promise of a high impact. To fill this gap, we propose WorkArena++, a novel benchmark consisting of 682 tasks corresponding to realistic workflows routinely performed by knowledge workers. WorkArena++ is designed to evaluate the planning, problem-solving, logical/arithmetic reasoning, retrieval, and contextual understanding abilities of web agents. Our empirical studies across state-of-the-art LLMs and vision-language models (VLMs), as well as human workers, reveal several challenges for such models to serve as useful assistants in the workplace. In addition to the benchmark, we provide a mechanism to effortlessly generate thousands of ground-truth observation/action traces, which can be used for fine-tuning existing models. Overall, we expect this work to serve as a useful resource to help the community progress toward capable autonomous agents. The benchmark can be found at https://github.com/ServiceNow/WorkArena/tree/workarena-plus-plus.
Deep Learning in Ultrasound Localization Microscopy: Applications and Perspectives.
Brice Rauby
Paul Xing
Jean Provost
Ultrasound Localization Microscopy (ULM) is a novel super-resolution imaging technique that can image the vasculature in vivo at depth with … (voir plus)resolution far beyond the conventional limit of diffraction. By relying on the localization and tracking of clinically approved microbubbles injected in the blood stream, ULM can provide not only anatomical visualization but also hemodynamic quantification of the microvasculature of different tissues. Various deep-learning approaches have been proposed to address challenges in ULM including denoising, improving microbubble localization, estimating blood flow velocity or performing aberration correction. Proposed deep learning methods often outperform their conventional counterparts by improving image quality and reducing processing time. In addition, their robustness to high concentrations of microbubbles can lead to reduced acquisition times in ULM, addressing a major hindrance to ULM clinical application. Herein, we propose a comprehensive review of the diversity of deep learning applications in ULM focusing on approaches assuming a sparse microbubbles distribution. We first provide an overview of how existing studies vary in the constitution of their datasets or in the tasks targeted by deep learning model. We also take a deeper look into the numerous approaches that have been proposed to improve the localization of microbubbles since they differ highly in their formulation of the optimization problem, their evaluation, or their network architectures. We finally discuss the current limitations and challenges of these methods, as well as the promises and potential of deep learning for ULM in the future.
WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
Massimo Caccia
Issam Hadj Laradji
Manuel Del Verme
Tom Marty
Léo Boisvert
Megh Thakkar
David Vazquez
Alexandre Lacoste
WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
Massimo Caccia
Issam Hadj Laradji
Manuel Del Verme
Tom Marty
Léo Boisvert
Megh Thakkar
David Vazquez
Alexandre Lacoste
We study the use of large language model-based agents for interacting with software via web browsers. Unlike prior work, we focus on measuri… (voir plus)ng the agents' ability to perform tasks that span the typical daily work of knowledge workers utilizing enterprise software systems. To this end, we propose WorkArena, a remote-hosted benchmark of 29 tasks based on the widely-used ServiceNow platform. We also introduce BrowserGym, an environment for the design and evaluation of such agents, offering a rich set of actions as well as multimodal observations. Our empirical evaluation reveals that while current agents show promise on WorkArena, there remains a considerable gap towards achieving full task automation. Notably, our analysis uncovers a significant performance disparity between open and closed-source LLMs, highlighting a critical area for future exploration and development in the field.
WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
Massimo Caccia
Issam Hadj Laradji
Manuel Del Verme
Tom Marty
Léo Boisvert
Megh Thakkar
David Vazquez
Alexandre Lacoste
We study the use of large language model-based agents for interacting with software via web browsers. Unlike prior work, we focus on measuri… (voir plus)ng the agents' ability to perform tasks that span the typical daily work of knowledge workers utilizing enterprise software systems. To this end, we propose WorkArena, a remote-hosted benchmark of 29 tasks based on the widely-used ServiceNow platform. We also introduce BrowserGym, an environment for the design and evaluation of such agents, offering a rich set of actions as well as multimodal observations. Our empirical evaluation reveals that while current agents show promise on WorkArena, there remains a considerable gap towards achieving full task automation. Notably, our analysis uncovers a significant performance disparity between open and closed-source LLMs, highlighting a critical area for future exploration and development in the field.
Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy
Brice Rauby
Paul Xing
Jonathan Por'ee
Jean Provost
The Unsolved Challenges of LLMs as Generalist Web Agents: A Case Study
Rim Assouel
Tom Marty
Massimo Caccia
Issam Hadj Laradji
Sai Rajeswar
Hector Palacios
David Vazquez
Alexandre Lacoste
Using Confounded Data in Latent Model-Based Reinforcement Learning
Damien GRASSET
Guillaume Gaudron
Pierre-Yves Oudeyer
Lookback for Learning to Branch
Prateek Gupta
Elias Boutros Khalil
Didier Chételat
Andrea Lodi
M. Pawan Kumar
The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights
Simon Bowly
Jonas Charfreitag
Didier Chételat
Antonia Chmiela
Justin Dumouchelle
Ambros Gleixner
Aleksandr Kazachkov
Elias Boutros Khalil
Paweł Lichocki
Andrea Lodi
Miles Lubin
Chris J. Maddison
Christopher Morris
D. Papageorgiou
Augustin Parjadis
Sebastian Pokutta
Antoine Prouvost … (voir 22 de plus)
Lara Scavuzzo
Giulia Zarpellon
Linxin Yangm
Sha Lai
Akang Wang
Xiaodong Luo
Xiang Zhou
Haohan Huang
Sheng Cheng Shao
Yuanming Zhu
Dong Dong Zhang
Tao Manh Quan
Zixuan Cao
Yang Xu
Zhewei Huang
Shuchang Zhou
C. Binbin
He Minggui
Haoren Ren Hao
Zhang Zhiyu
An Zhiwu
Mao Kun
Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused … (voir plus)on solving problem instances in isolation, ignoring that they often stem from related data distributions in practice. However, recent years have seen a surge of interest in using machine learning as a new approach for solving combinatorial problems, either directly as solvers or by enhancing exact solvers. Based on this context, the ML4CO aims at improving state-of-the-art combinatorial optimization solvers by replacing key heuristic components. The competition featured three challenging tasks: finding the best feasible solution, producing the tightest optimality certificate, and giving an appropriate solver configuration. Three realistic datasets were considered: balanced item placement, workload apportionment, and maritime inventory routing. This last dataset was kept anonymous for the contestants.