The BrowserGym Ecosystem for Web Agent Research
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909516045484032 |
|---|---|
| author | De Chezelles, Thibault Le Sellier Gasse, Maxime Drouin, Alexandre Caccia, Massimo Boisvert, Léo Thakkar, Megh Marty, Tom Assouel, Rim Shayegan, Sahar Omidi Jang, Lawrence Keunho Lù, Xing Han Yoran, Ori Kong, Dehan Xu, Frank F. Reddy, Siva Cappart, Quentin Neubig, Graham Salakhutdinov, Ruslan Chapados, Nicolas Lacoste, Alexandre |
| author_facet | De Chezelles, Thibault Le Sellier Gasse, Maxime Drouin, Alexandre Caccia, Massimo Boisvert, Léo Thakkar, Megh Marty, Tom Assouel, Rim Shayegan, Sahar Omidi Jang, Lawrence Keunho Lù, Xing Han Yoran, Ori Kong, Dehan Xu, Frank F. Reddy, Siva Cappart, Quentin Neubig, Graham Salakhutdinov, Ruslan Chapados, Nicolas Lacoste, Alexandre |
| contents | The BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents, particularly those leveraging automation and Large Language Models (LLMs). 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 action spaces, 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. 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_05467 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The BrowserGym Ecosystem for Web Agent Research De Chezelles, Thibault Le Sellier Gasse, Maxime Drouin, Alexandre Caccia, Massimo Boisvert, Léo Thakkar, Megh Marty, Tom Assouel, Rim Shayegan, Sahar Omidi Jang, Lawrence Keunho Lù, Xing Han Yoran, Ori Kong, Dehan Xu, Frank F. Reddy, Siva Cappart, Quentin Neubig, Graham Salakhutdinov, Ruslan Chapados, Nicolas Lacoste, Alexandre Machine Learning Artificial Intelligence Software Engineering The BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents, particularly those leveraging automation and Large Language Models (LLMs). 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 action spaces, 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. 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. |
| title | The BrowserGym Ecosystem for Web Agent Research |
| topic | Machine Learning Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2412.05467 |