Portrait of Maxime Gasse

Maxime Gasse

Associate Industry Member
Adjunct Professor, Polytechnique Montréal, Department of Computer Engineering and Software Engineering
Senior Research Scientist, ServiceNow
Website
Google Scholar
LinkedIn
X

Biography

I am a senior research scientist at ServiceNow in Montréal, where I do research at the intersection of causal inference and reinforcement learning. I am an adjunct professor at Polytechnique Montréal (courtesy appointment) and an associate industry member of Mila – Quebec Artificial Intelligence Institute.

I am fascinated by the question of AI: can we build machines that think? I humbly believe that our attempts at designing thinking machines can be a path towards a fundamental understanding of intelligence and of ourselves. Currently, I am interested in questioning if and how ideas from the field of causality can help in the design of autonomous learning agents. I am looking for motivated interns with strong technical skills and a background in reinforcement learning and/or causality.

Current Students

Brice Rauby
PhD - Polytechnique Montréal
brice.rauby@mila.quebec

Publications

WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
Alexandre Drouin
Maxime Gasse
Massimo Caccia
Issam Hadj Laradji
Manuel Del Verme
Tom Marty
Léo Boisvert
Megh Thakkar
Quentin Cappart
David Vazquez
Nicolas Chapados
Alexandre Lacoste
2024-05-01
ICML.cc/2024/Conference (poster)
doi.org
openreview.net
WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
Alexandre Drouin
Maxime Gasse
Massimo Caccia
Issam Hadj Laradji
Manuel Del Verme
Tom Marty
Léo Boisvert
Megh Thakkar
Quentin Cappart
David Vazquez
Nicolas Chapados
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… (see more)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.
2024-03-12
ArXiv (preprint)
doi.org
arxiv.org
WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
Alexandre Drouin
Maxime Gasse
Massimo Caccia
Issam Hadj Laradji
Manuel Del Verme
Tom Marty
Léo Boisvert
Megh Thakkar
Quentin Cappart
David Vazquez
Nicolas Chapados
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… (see more)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.
2024-03-11
ICLR.cc/2024/Workshop/LLMAgents (poster)
doi.org
openreview.net
Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy
Brice Rauby
Paul Xing
Jonathan Por'ee
Maxime Gasse
Jean Provost
2024-02-14
ArXiv (preprint)
doi.org
arxiv.org
The Unsolved Challenges of LLMs as Generalist Web Agents: A Case Study
Rim Assouel
Tom Marty
Massimo Caccia
Issam Hadj Laradji
Alexandre Drouin
Sai Rajeswar
Hector Palacios
Quentin Cappart
David Vazquez
Nicolas Chapados
Maxime Gasse
Alexandre Lacoste
2023-11-07
NeurIPS.cc/2023/Workshop/FMDM (published)
openreview.net
openreview.net
Using Confounded Data in Latent Model-Based Reinforcement Learning
Maxime Gasse
Damien GRASSET
Guillaume Gaudron
Pierre-Yves Oudeyer
2023-08-14
TMLR (accepted)
openreview.net
openreview.net
Lookback for Learning to Branch
Prateek Gupta
Elias Boutros Khalil
Didier Chételat
Maxime Gasse
Yoshua Bengio
Andrea Lodi
M. Pawan Kumar
2022-10-10
TMLR (accepted)
doi.org
openreview.net
On generalized surrogate duality in mixed-integer nonlinear programming
Benjamin Muller
Gonzalo Munoz
Maxime Gasse
Ambros Gleixner
Andrea Lodi
Felipe Serrano
2021-07-17
Mathematical Programming (published)
doi.org
arxiv.org
The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights
Maxime Gasse
Simon Bowly
Quentin Cappart
Jonas Charfreitag
Laurent Charlin
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 … (see 22 more)
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 … (see more)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.
2021-01-01
NeurIPS (Competition and Demos) (published)
doi.org
arxiv.org
On the Effectiveness of Two-Step Learning for Latent-Variable Models
Cem (Yusuf) Subakan
Maxime Gasse
Laurent Charlin
Latent-variable generative models offer a principled solution for modeling and sampling from complex probability distributions. Implementing… (see more) a joint training objective with a complex prior, however, can be a tedious task, as one is typically required to derive and code a specific cost function for each new type of prior distribution. In this work, we propose a general framework for learning latent variable generative models in a two-step fashion. In the first step of the framework, we train an autoencoder, and in the second step we fit a prior model on the resulting latent distribution. This two-step approach offers a convenient alternative to joint training, as it allows for a straightforward combination of existing models without the hustle of deriving new cost functions, and the need for coding the joint training objectives. Through a set of experiments, we demonstrate that two-step learning results in performances similar to joint training, and in some cases even results in more accurate modeling.
2020-01-01
2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP) (published)
doi.org
On generalized surrogate duality in mixed-integer nonlinear programming
Benjamin Muller
Gonzalo Munoz
Maxime Gasse
Ambros Gleixner
Andrea Lodi
Felipe Serrano
2019-12-01
ArXiv (preprint)
doi.org
arxiv.org
Exact Combinatorial Optimization with Graph Convolutional Neural Networks
Maxime Gasse
Didier Chételat
Nicola Ferroni
Laurent Charlin
Andrea Lodi
Combinatorial optimization problems are typically tackled by the branch-and-bound paradigm. We propose a new graph convolutional neural netw… (see more)ork model for learning branch-and-bound variable selection policies, which leverages the natural variable-constraint bipartite graph representation of mixed-integer linear programs. We train our model via imitation learning from the strong branching expert rule, and demonstrate on a series of hard problems that our approach produces policies that improve upon state-of-the-art machine-learning methods for branching and generalize to instances significantly larger than seen during training. Moreover, we improve for the first time over expert-designed branching rules implemented in a state-of-the-art solver on large problems. Code for reproducing all the experiments can be found at this https URL.
2019-01-01
NeurIPS (published)
arxiv.org
arxiv.org