Author name cluster

Maxime Gasse

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

2 author rows

TMLR Journal 2025 Journal Article

The BrowserGym Ecosystem for Web Agent Research

Thibault Le Sellier de Chezelles
Maxime Gasse
Alexandre Lacoste
Massimo Caccia
Alexandre Drouin
Léo Boisvert
Megh Thakkar
Tom Marty

The BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents, particularly those leveraging automation and Large Language Models (LLMs) for web interaction tasks. Many existing benchmarks suffer from fragmentation and inconsistent evaluation methodologies, making it challenging to achieve reliable comparisons and reproducible results. In an earlier work, Drouin et al. (2024) introduced BrowserGym which aims to solve this by providing a unified, gym-like environment with well-defined observation and actionspaces, facilitating standardized evaluation across diverse benchmarks. We propose an extended BrowserGym-based ecosystem for web agent research, which unifies existing benchmarks from the literature and includes AgentLab, a complementary framework that aids in agent creation, testing, and analysis. Our proposed ecosystem offers flexibility for integrating new benchmarks while ensuring consistent evaluation and comprehensive experiment management. This standardized approach seeks to reduce the time and complexity of developing web agents, supporting more reliable comparisons and facilitating in-depth analysis of agent behaviors, and could result in more adaptable, capable agents, ultimately accelerating innovation in LLM-driven automation. As a supporting evidence, we conduct the first large-scale, multi-benchmark web agent experiment and compare the performance of 6 state-of-the-art LLMs across 6 popular web agent benchmarks made available in BrowserGym. Among other findings, our results highlight a large discrepancy between OpenAI and Anthropic’s latests models, with Claude-3.5-Sonnet leading the way on almost all benchmarks, except on vision-related tasks where GPT-4o is superior. Despite these advancements, our results emphasize that building robust and efficient web agents remains a significant challenge, due to the inherent complexity of real-world web environments and the limitations of current models.

PDF Details

NeurIPS Conference 2024 Conference Paper

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

Léo Boisvert
Megh Thakkar
Maxime Gasse
Massimo Caccia
Thibault L. De Chezelles
Quentin Cappart
Nicolas Chapados
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 recent 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 towards capable autonomous agents. The benchmark can be found at https: //github. com/ServiceNow/WorkArena.

PDF Details DOI

ICML Conference 2024 Conference Paper

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
David Vázquez 0001
Nicolas Chapados

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 WorkArena, a remote-hosted benchmark of 33 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.

Details

TMLR Journal 2023 Journal Article

Using Confounded Data in Latent Model-Based Reinforcement Learning

Maxime Gasse
Damien GRASSET
Guillaume Gaudron
Pierre-Yves Oudeyer

In the presence of confounding, naively using off-the-shelf offline reinforcement learning (RL) algorithms leads to sub-optimal behaviour. In this work, we propose a safe method to exploit confounded offline data in model-based RL, which improves the sample-efficiency of an interactive agent that also collects online, unconfounded data. First, we import ideas from the well-established framework of $do$-calculus to express model-based RL as a causal inference problem, thus bridging the gap between the fields of RL and causality. Then, we propose a generic method for learning a causal transition model from offline and online data, which captures and corrects the confounding effect using a hidden latent variable. We prove that our method is correct and efficient, in the sense that it attains better generalization guarantees thanks to the confounded offline data (in the asymptotic case), regardless of the confounding effect (the offline expert's behaviour). We showcase our method on a series of synthetic experiments, which demonstrate that a) using confounded offline data naively degrades the sample-efficiency of an RL agent; b) using confounded offline data correctly improves sample-efficiency.

PDF Details

NeurIPS Conference 2022 Conference Paper

Learning to Branch with Tree MDPs

Lara Scavuzzo
Feng Chen
Didier Chetelat
Maxime Gasse
Andrea Lodi
Neil Yorke-Smith
Karen Aardal

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 literature focuses on learning fast approximations of the \emph{strong branching} rule. Instead, we propose to learn branching rules from scratch with Reinforcement Learning (RL). We revisit the work of Etheve et al. (2020) and propose a generalization of Markov Decisions Processes (MDP), which we call \emph{tree MDP}, that provides a more suitable formulation of the branching problem. We derive a policy gradient theorem for tree MDPs that exhibits a better credit assignment compared to its temporal counterpart. We demonstrate through computational experiments that this new framework is suitable to tackle the learning-to-branch problem in MILP, and improves the learning convergence.

PDF Details

TMLR Journal 2022 Journal Article

Lookback for Learning to Branch

Prateek Gupta
Elias Boutros Khalil
Didier Chételat
Maxime Gasse
Andrea Lodi
Yoshua Bengio
M. Pawan Kumar

The expressive and computationally inexpensive bipartite Graph Neural Networks (GNN) have been shown to be an important component of deep learning based Mixed-Integer Linear Program (MILP) solvers. Recent works have demonstrated the effectiveness of such GNNs in replacing the branching (variable selection) heuristic in branch-and-bound B&B solvers. These GNNs are trained, offline and on a collection of MILPs, to imitate a very good but computationally expensive branching heuristic, strong branching. Given that B&B results in a tree of sub-MILPs, we ask (a) whether there are strong dependencies exhibited by the target heuristic among the neighboring nodes of the B&B tree, and (b) if so, whether we can incorporate them in our training procedure. Specifically, we find that with the strong branching heuristic, a child node's best choice was often the parent's second-best choice. We call this the "lookback" phenomenon. Surprisingly, the typical branching GNN of Gasse et al. (2019) often misses this simple "answer". To imitate the target behavior more closely by incorporating the lookback phenomenon in GNNs, we propose two methods: (a) target smoothing for the standard cross-entropy loss function, and (b) adding a Parent-as-Target (PAT) Lookback regularizer term. Finally, we propose a model selection framework to incorporate harder-to-formulate objectives such as solving time in the final models. Through extensive experimentation on standard benchmark instances, we show that our proposal results in up to 22% decrease in the size of the B&B tree and up to 15% improvement in the solving times.

PDF Details

NeurIPS Conference 2020 Conference Paper

Hybrid Models for Learning to Branch

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

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 its application as many practitioners may not have access to high-end GPUs. In this work, we ask two key questions. First, in a more realistic setting where only a CPU is available, is the GNN model still competitive? Second, can we devise an alternate computationally inexpensive model that retains the predictive power of the GNN architecture? We answer the first question in the negative, and address the second question by proposing a new hybrid architecture for efficient branching on CPU machines. The proposed architecture combines the expressive power of GNNs with computationally inexpensive multi-layer perceptrons (MLP) for branching. We evaluate our methods on four classes of MILP problems, and show that they lead to up to 26% reduction in solver running time compared to state-of-the-art methods without a GPU, while extrapolating to harder problems than it was trained on. The code for this project is publicly available at https: //github. com/pg2455/Hybrid-learn2branch.

PDF Details

NeurIPS Conference 2019 Conference Paper

Exact Combinatorial Optimization with Graph Convolutional Neural Networks

Maxime Gasse
Didier Chetelat
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 network 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 https: //github. com/ds4dm/learn2branch.

PDF Details

ICML Conference 2015 Conference Paper

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

Maxime Gasse
Alexandre Aussem
Haytham Elghazel

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 given the input features play a pivotal role for multi-label classification in the context of subset Zero-One loss minimization, as they divide the learning task into simpler independent multi-class problems. We establish theoretical results to characterize and identify these irreducible label factors for any given probability distribution satisfying the Composition property. The analysis lays the foundation for generic multi-label classification and optimal feature subset selection procedures under this subclass of distributions. Our conclusions are supported by carefully designed experiments on synthetic and benchmark data.

Details