Papers › OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration,...

OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization

25 Oct 2024arXiv:2410.19609archive 2025-07-28

Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Hongming Zhang, Tianqing Fang, Zhenzhong Lan, Dong Yu

The rapid development of large language and multimodal models has sparked significant interest in using proprietary models, such as GPT-4o, to develop autonomous agents capable of handling real-world scenarios like web navigation. Although recent open-source efforts have tried to equip agents with the ability to explore environments and continuously improve over time, they are building text-only agents in synthetic environments where the reward signals are clearly defined. Such agents struggle to generalize to realistic settings that require multimodal perception abilities and lack ground-truth signals. In this paper, we introduce an open-source framework designed to facilitate the development of multimodal web agent that can autonomously conduct real-world exploration and improve itself. We first train the base model with imitation learning to gain the basic abilities. We then let the agent explore the open web and collect feedback on its trajectories. After that, it further improves its policy by learning from well-performing trajectories judged by another general-purpose model. This exploration-feedback-optimization cycle can continue for several iterations. Experimental results show that our web agent successfully improves itself after each iteration, demonstrating strong performance across multiple test sets.

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 13 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 11 ran (7 with no instrument failure; 4 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 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

minorjerry/openwebvoyager officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 13 samples, 11 ran (4 instrument-failed) · 2 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

13 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 2 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.

4ran · our draft was wrong
7ran
2unverified

Licence: 1 of the 13 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from minorjerry/openwebvoyager. “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”. For 4 samples that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.

minorjerry/openwebvoyager official repository 13 samples, 11 ran (4 instrument-failed) · 2 unverified
auto_eval_by_gpt4v WebVoyager/evaluation/auto_eval.py ran Apache-2.0 (permissive) · 14332c7648933696 · report fixture: returned list · level recorded 2026-09-26
auto_eval_by_gpt4v WebVoyager/evaluation/auto_eval_mind2web.py ran Apache-2.0 (permissive) · 5d024d97ebd11a83 · report fixture: returned list · level recorded 2026-09-26
call_gpt4v_api WebVoyager/exploration_feedback.py ran Apache-2.0 (permissive) · f5d342831b3e7322 · report fixture: returned tuple · level recorded 2026-09-26
encode_image in 131 papers WebVoyager/utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · f41cb1a19b154297 · report fixture: signature image_path:str/0/str · returned str · level recorded 2026-09-22
fetch_browser_info WebVoyager/utils_webarena.py ran · our draft was wrong Apache-2.0 (permissive) · aee0ef39f44bd495 · report fixture: signature browser:MockBrowser/0/? · returned dict · level recorded 2026-09-26
filter_acc_tree WebVoyager/utils_localhost.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b02176aa1edc7a15 · report fixture: signature acc_tree:str/0/str · returned str · level recorded 2026-09-26
format_msg_acctree_and_screenshot WebVoyager/exploration_feedback.py ran Apache-2.0 (permissive) · 00f48fae7d0dc8db · report fixture: signature it:int/0/int, init_msg:str/0/str, pdf_obs:NoneType/0/?, warn_obs:str/0/str, ac_tree:str/0/str, web_img_b64:str/0/str · returned dict · level recorded 2026-09-26
get_bounding_client_rect WebVoyager/utils_webarena.py ran · our draft was wrong Apache-2.0 (permissive) · 040b32129bf67f60 · report fixture: returned dict · level recorded 2026-09-25
get_element_in_viewport_ratio WebVoyager/utils_webarena.py ran Apache-2.0 (permissive) · 0b27cebef7f8500d · report fixture: signature elem_left_bound:float/0/float, elem_top_bound:float/0/float, width:float/0/float, height:float/0/float, config:dict/0/? · returned float · level recorded 2026-09-25
omit_history_last_n_steps WebVoyager/utils_localhost.py ran Apache-2.0 (permissive) · 50bc5428c8a966fb · report fixture: signature history:list/1/dict, n_steps:int/0/int · returned list · level recorded 2026-09-26
retry_with_exponential_backoff in 11 papers WebVoyager/utils_localhost.py ran Apache-2.0 (permissive) · b84fb0440ded170d · report fixture: signature initial_delay:float/0/float, exponential_base:float/0/float, jitter:bool/0/bool, max_retries:int/0/int · returned function · level recorded 2026-09-26
get_web_element_rect WebVoyager/utils.py unverified Apache-2.0 (permissive) · 8e6a8a69a2462339 · report
resize_image in 74 papers WebVoyager/utils.py unverified Apache-2.0 (permissive) · e63c4f0834fe9c79 · report

Tasks

Imitation Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASE

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