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

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)

Ant Colony Sampling with GFlowNets for Combinatorial Optimization

Minsu Kim

Sanghyeok Choi

Jiwoo Son

Hyeon-Seob Kim

Jinkyoo Park

Yoshua Bengio

2024-03-11

ArXiv (preprint)

Improving and Generalizing Flow-Based Generative Models with Minibatch Optimal Transport

Alexander Tong

Nikolay Malkin

Guillaume Huguet

Yanlei Zhang

Jarrid Rector-Brooks

Kilian FATRAS

Guy Wolf

Yoshua Bengio

Continuous normalizing flows (CNFs) are an attractive generative modeling technique, but they have been held back by limitations in their si… (see more)mulation-based maximum likelihood training. We introduce the generalized \textit{conditional flow matching} (CFM) technique, a family of simulation-free training objectives for CNFs. CFM features a stable regression objective like that used to train the stochastic flow in diffusion models but enjoys the efficient inference of deterministic flow models. In contrast to both diffusion models and prior CNF training algorithms, CFM does not require the source distribution to be Gaussian or require evaluation of its density. A variant of our objective is optimal transport CFM (OT-CFM), which creates simpler flows that are more stable to train and lead to faster inference, as evaluated in our experiments. Furthermore, OT-CFM is the first method to compute dynamic OT in a simulation-free way. Training CNFs with CFM improves results on a variety of conditional and unconditional generation tasks, such as inferring single cell dynamics, unsupervised image translation, and Schrödinger bridge inference.

2024-03-11

TMLR (accepted)

IntentGPT: Few-shot Intent Discovery with Large Language Models

Juan A. Rodriguez

Nicholas Botzer

David Vazquez

Chris Pal

Marco Pedersoli

Issam Hadj Laradji

2024-03-11

ICLR.cc/2024/Workshop/LLMAgents (poster)

Investigating Robot Influence on Human Behaviour By Leveraging Entrainment Effects

Lixiao Zhu

AJung Moon

2024-03-11

Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction (published)

Language-guided Skill Learning with Temporal Variational Inference

Haotian Fu

Pratyusha Sharma

Elias Stengel-Eskin

George Konidaris

Nicolas Le Roux

Marc-Alexandre Côté

Xingdi Yuan

We present an algorithm for skill discovery from expert demonstrations. The algorithm first utilizes Large Language Models (LLMs) to propose… (see more) an initial segmentation of the trajectories. Following that, a hierarchical variational inference framework incorporates the LLM-generated segmentation information to discover reusable skills by merging trajectory segments. To further control the trade-off between compression and reusability, we introduce a novel auxiliary objective based on the Minimum Description Length principle that helps guide this skill discovery process. We test our system on BabyAI, a grid world navigation environment, as well as ALFRED, a household simulation environment.Our results demonstrate that agents equipped with our method can discover skills that help accelerate learning and outperform baseline skill learning approaches on new long-horizon tasks.

2024-03-11

ICLR.cc/2024/Workshop/LLMAgents (poster)

Perspectives on Robotic Systems for the Visually Impaired

Christopher Yee Wong

Rahatul Amin Ananto

Tanaka Akiyama

Joseph Paul Nemargut

AJung Moon

2024-03-11

Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction (published)

Prioritizing Safeguarding Over Autonomy: Risks of LLM Agents for Science

Xiangru Tang

Qiao Jin

Kunlun Zhu

Tongxin Yuan

Yichi Zhang

Wangchunshu Zhou

Meng Qu

Yilun Zhao

Jian Tang

Zhuosheng Zhang

Arman Cohan

Zhiyong Lu

Mark Gerstein

2024-03-11

ICLR.cc/2024/Workshop/LLMAgents (poster)

Stealing Part of a Production Language Model

Nicholas Carlini

Daniel Paleka

Krishnamurthy Dvijotham

Thomas Steinke

Jonathan Hayase

A. Feder Cooper

Katherine Lee

Matthew Jagielski

Milad Nasr

Arthur Conmy

Eric Wallace

David Rolnick

Florian Tramèr

2024-03-11

ArXiv (preprint)

Stochastic gradient descent-based inference for dynamic network models with attractors

Hancong Pan

Xiaojing Zhu

Cantay Caliskan

Dino P. Christenson

Konstantinos Spiliopoulos

Dylan Walker

Eric Kolaczyk

2024-03-11

ArXiv (preprint)

WebLINX: Real-World Website Navigation with Multi-Turn Dialogue

Xing Han Lu

Zdeněk Kasner

Siva Reddy

We propose the problem of conversational web navigation, where a digital agent controls a web browser and follows user instructions to solve… (see more) real-world tasks in a multi-turn dialogue fashion. To support this problem, we introduce WEBLINX - a large-scale benchmark of 100K interactions across 2300 expert demonstrations of conversational web navigation. Our benchmark covers a broad range of patterns on over 150 real-world websites and can be used to train and evaluate agents in diverse scenarios. Due to the magnitude of information present, Large Language Models (LLMs) cannot process entire web pages in real-time. To solve this bottleneck, we design a retrieval-inspired model that efficiently prunes HTML pages by ranking relevant elements. We use the selected elements, along with screenshots and action history, to assess a variety of models for their ability to replicate human behavior when navigating the web. Our experiments span from small text-only to proprietary multimodal LLMs. We find that smaller finetuned decoders surpass the best zero-shot LLMs (including GPT-4V), but also larger finetuned multimodal models which were explicitly pretrained on screenshots. However, all finetuned models struggle to generalize to unseen websites. Our findings highlight the need for large multimodal models that can generalize to novel settings. Our code, data and models are available for research: https://mcgill-nlp.github.io/weblinx

2024-03-11

ICLR.cc/2024/Workshop/LLMAgents (poster)