Papers › The BrowserGym Ecosystem for Web Agent Research

The BrowserGym Ecosystem for Web Agent Research

6 Dec 2024arXiv:2412.05467archive 2025-07-28

Thibault Le Sellier De Chezelles, Maxime Gasse, Alexandre Drouin, Massimo Caccia, Léo Boisvert, Megh Thakkar, Tom Marty, Rim Assouel, Sahar Omidi Shayegan, Lawrence Keunho Jang, Xing Han Lù, Ori Yoran, Dehan Kong, Frank F. Xu, Siva Reddy, Quentin Cappart, Graham Neubig, Ruslan Salakhutdinov, Nicolas Chapados, Alexandre Lacoste

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 24 code samples harvested from 3 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 2 repositories, 15 ran (5 with no instrument failure; 10 where Syntology's instrument failed); community (archive-listed): 7 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

servicenow/agentlab officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 12 samples, 11 ran (7 instrument-failed) · 1 unverified report
servicenow/browsergym officialmentioned in papermentioned on GitHubNOASSERTIONSyntology: 5 samples, 4 ran (3 instrument-failed) · 1 unverified report
servicenow/workarena mentioned on GitHubNOASSERTIONSyntology: 7 samples, 2 ran (0 instrument-failed) · 5 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

24 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
10ran · our draft was wrong
5ran
7unverified

Licence: 24 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

servicenow/agentlab official repository 12 samples, 11 ran (7 instrument-failed) · 1 unverified
add_step_timing_to_env_info_decorator src/agentlab/benchmarks/abstract_env.py ran · our draft was wrong licence not identified · pointer only · 877887aa89d5c493 · report fixture: signature step_func:callable/0/? · returned function · level recorded 2026-09-25
clean_column_names src/agentlab/analyze/agent_xray.py ran · our draft was wrong licence not identified · pointer only · e0611388db73b85b · report fixture: signature col_list:list/1/str · returned list · level recorded 2026-09-25
display_table src/agentlab/analyze/agent_xray.py ran · our draft was wrong licence not identified · pointer only · 86d76ffec286856f · report fixture: signature df:DataFrame/0/? · returned DataFrame · level recorded 2026-09-25
draw_click_indicator src/agentlab/agents/agent_utils.py ran licence not identified · pointer only · 45c1db8f1020a60d · report fixture: signature image:Image/0/?, x:int/0/int, y:int/0/int · returned Image · level recorded 2026-09-25
draw_mouse_pointer src/agentlab/agents/agent_utils.py ran licence not identified · pointer only · 07b31c698d493662 · report fixture: signature image:Image/0/?, x:int/0/int, y:int/0/int · returned Image · level recorded 2026-09-25
find_bids_and_xy_pairs src/agentlab/analyze/overlay_utils.py ran · our draft was wrong licence not identified · pointer only · 15fde3c327650a12 · report fixture: signature args:list/1/ArgInfo · returned list · level recorded 2026-09-25
get_constants_and_variables src/agentlab/analyze/inspect_results.py ran · our draft was wrong licence not identified · pointer only · 829a15ad2e0ff974 · report fixture: signature df:DataFrame/0/?, drop_constants:bool/0/bool · returned tuple · level recorded 2026-09-25
overlay_cross src/agentlab/analyze/overlay_utils.py ran licence not identified · pointer only · d1c553ebca78057a · report fixture: signature img:Image/0/?, coord:tuple/1/float, color:str/0/str, length:int/0/int, width:int/0/int · returned Image · level recorded 2026-09-25
parse_function_calls src/agentlab/analyze/overlay_utils.py ran · honoured contract licence not identified · pointer only · 53068f77c8646667 · report fixture: signature code_string:str/0/str · returned list · level recorded 2026-09-25
pretty_yaml src/agentlab/analyze/tapes.py ran · our draft was wrong licence not identified · pointer only · 9b30bcc3faa69153 · report fixture: signature data:dict/0/? · returned str · level recorded 2026-09-25
remove_args_from_col src/agentlab/analyze/agent_xray.py ran · our draft was wrong licence not identified · pointer only · b82aafda2161d7c5 · report fixture: signature df:DataFrame/0/? · returned DataFrame · level recorded 2026-09-25
reduce_episodes src/agentlab/analyze/inspect_results.py unverified licence not identified · pointer only · aa8fc291716bf5f9 · report
servicenow/browsergym official repository 5 samples, 4 ran (3 instrument-failed) · 1 unverified
extract_data_items_from_aria browsergym/core/src/browsergym/core/observation.py ran · our draft was wrong no licence file found · pointer only · 8194ee5c0231da57 · report fixture: signature string:str/0/str, log_level:int/0/int · returned tuple · level recorded 2026-09-24
get_chatbox_classic browsergym/core/src/browsergym/core/chat.py ran · our draft was wrong no licence file found · pointer only · b938f1e73d583a18 · report fixture: signature chatbox_dir:PosixPath/0/? · returned str · level recorded 2026-09-24
get_chatbox_modern browsergym/core/src/browsergym/core/chat.py ran · our draft was wrong no licence file found · pointer only · e01ad5d24888de64 · report fixture: signature chatbox_dir:PosixPath/0/? · returned str · level recorded 2026-09-24
overlay_som browsergym/core/src/browsergym/utils/obs.py ran no licence file found · pointer only · b121272b1bd15e8b · report fixture: signature screenshot:ndarray/3/int, extra_properties:dict/0/?, fontsize:int/0/int, linewidth:int/0/int, tag_margin:int/0/int · returned ndarray · level recorded 2026-09-24
flatten_axtree_to_str browsergym/core/src/browsergym/utils/obs.py unverified no licence file found · pointer only · 567d81b57b0ac04f · report
servicenow/workarena community (archive-listed) 7 samples, 2 ran (0 instrument-failed) · 5 unverified
get_categories in 9 papers src/browsergym/workarena/api/category.py ran licence not identified · pointer only · ce62e9936fba1098 · report fixture: returned list · level recorded 2026-09-25
is_step_completed src/browsergym/workarena/install.py ran · violated contract licence not identified · pointer only · 1bf94288772744bd · report fixture: signature step_name:str/0/str · returned bool · level recorded 2026-09-25
SNowInstance src/browsergym/workarena/install.py unverified licence not identified · pointer only · 6d68d6d5030ccff9 · report
decrypt_instance_password src/browsergym/workarena/instance.py unverified licence not identified · pointer only · b924a66a3ad86b83 · report
encrypt_instance_password src/browsergym/workarena/instance.py unverified licence not identified · pointer only · 2194414c8a1dfd5d · report
fetch_instances src/browsergym/workarena/instance.py unverified licence not identified · pointer only · a9ef891d6b2d4051 · report
get_cost_center_sysid src/browsergym/workarena/api/cost_center.py unverified licence not identified · pointer only · a1798062547f9110 · report

Tasks

Benchmarking

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Fragmentation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections