Maxime Gasse — accepted AI-conference papers

2024

WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks

Léo Boisvert, Megh Thakkar, Maxime Gasse, Massimo Caccia, Thibault Le Sellier de Chezelles, Quentin Cappart +3

NeurIPS 2024poster

The ability of large language models (LLMs) to mimic human-like intelligence has led to a surge in LLM-based autonomous agents. Though recent LLMs seem capable of planning and reasoning given user instructions, their effectiveness in applying these capabilities for autonomous task solving remains u…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2024

WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?

Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam H. Laradji, Manuel Del Verme, Tom Marty +3

ICML 2024poster

We study the use of large language model-based agents for interacting with software via web browsers. Unlike prior work, we focus on measuring the agents' ability to perform tasks that span the typical daily work of knowledge workers utilizing enterprise software systems. To this end, we propose Wor…

Cited by 61 Source ↗PDF ↗Scholar ↗

2022

Learning to Branch with Tree MDPs

Lara Scavuzzo, Feng Yang Chen, Didier Chételat, Maxime Gasse, Andrea Lodi, Neil Yorke-Smith +1

NeurIPS 2022accept

State-of-the-art Mixed Integer Linear Programming (MILP) solvers combine systematic tree search with a plethora of hard-coded heuristics, such as branching rules. While approaches to learn branching strategies have received increasing attention and have shown very promising results, most of the lite…

Cited by 70 Source ↗PDF ↗code ↗Scholar ↗

2020

Hybrid Models for Learning to Branch

Prateek Gupta, Maxime Gasse, Elias Khalil, Pawan Mudigonda, Andrea Lodi, Yoshua Bengio

NeurIPS 2020poster

A recent Graph Neural Network (GNN) approach for learning to branch has been shown to successfully reduce the running time of branch-and-bound algorithms for Mixed Integer Linear Programming (MILP). While the GNN relies on a GPU for inference, MILP solvers are purely CPU-based. This severely limits…

Cited by 181 Source ↗PDF ↗code ↗Scholar ↗

2019

Exact Combinatorial Optimization with Graph Convolutional Neural Networks

Maxime Gasse, Didier Chetelat, Nicola Ferroni, Laurent Charlin, Andrea Lodi

NeurIPS 2019poster

Combinatorial optimization problems are typically tackled by the branch-and-bound paradigm. We propose a new graph convolutional neural network model for learning branch-and-bound variable selection policies, which leverages the natural variable-constraint bipartite graph representation of mixed-int…

Cited by 669 Source ↗PDF ↗code ↗Scholar ↗

2015

On the Optimality of Multi-Label Classification under Subset Zero-One Loss for Distributions Satisfying the Composition Property

Maxime Gasse, Alexandre Aussem, Haytham Elghazel

ICML 2015poster

The benefit of exploiting label dependence in multi-label classification is known to be closely dependent on the type of loss to be minimized. In this paper, we show that the subsets of labels that appear as irreducible factors in the factorization of the conditional distribution of the label set gi…

Cited by 19 Source ↗PDF ↗Scholar ↗