Papers › WebSailor: Navigating Super-human Reasoning for Web Agent

WebSailor: Navigating Super-human Reasoning for Web Agent

3 Jul 2025arXiv:2507.02592archive 2025-07-28

Kuan Li, Zhongwang Zhang, Huifeng Yin, Liwen Zhang, Litu Ou, Jialong Wu, Wenbiao Yin, Baixuan Li, Zhengwei Tao, Xinyu Wang, Weizhou Shen, Junkai Zhang, Dingchu Zhang, Xixi Wu, Yong Jiang, Ming Yan, Pengjun Xie, Fei Huang, Jingren Zhou

Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as BrowseComp, a feat previously unattainable. We posit that their success hinges on a sophisticated reasoning pattern absent in open-source models: the ability to systematically reduce extreme uncertainty when navigating vast information landscapes. Based on this insight, we introduce WebSailor, a complete post-training methodology designed to instill this crucial capability. Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation, RFT cold start, and an efficient agentic RL training algorithm, Duplicating Sampling Policy Optimization (DUPO). With this integrated pipeline, WebSailor significantly outperforms all opensource agents in complex information-seeking tasks, matching proprietary agents' performance and closing the capability gap.

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 22 code samples harvested from 2 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 10 ran (7 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 10 samples from 1 repository, 6 ran (1 with no instrument failure; 5 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 on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

alibaba-nlp/webagent officialmentioned in papermentioned on GitHubApache-2.0Syntology: 12 samples, 10 ran (3 instrument-failed) · 2 unverified report
SnailDev/github-hot-hub mentioned on GitHubpytorchMITSyntology: not harvested report
alibaba-nlp/webwalker mentioned on GitHubApache-2.0Syntology: 10 samples, 6 ran (5 instrument-failed) · 4 unverified report
kun-g/Scraping-Github-trending mentioned on GitHubtfSyntology: not harvested 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

22 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 6 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 · violated contract
8ran · our draft was wrong
7ran
6unverified

Licence: 6 of the 22 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 of them, 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 2 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”. For 2 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.

alibaba-nlp/webagent official repository 12 samples, 10 ran (3 instrument-failed) · 2 unverified
call_llm in 14 papers WebAgent/NestBrowse/utils.py ran Apache-2.0 (permissive) · cc601f60e63e7a5c · report fixture: returned coroutine · level recorded 2026-09-25
call_llm in 14 papers WebAgent/ParallelMuse/functionality_specified_partial_rollout.py ran Apache-2.0 (permissive) · ffcb6da25872786e · report fixture: signature sem:Semaphore/0/?, messages:list/1/dict · returned coroutine · level recorded 2026-09-25
call_resum_server WebAgent/WebResummer/src/summary_utils.py ran fingerprinted Apache-2.0 (permissive) · 8605222f211cb27e · report fixture: signature query:str/0/str, max_retries:int/0/int · returned str · level recorded 2026-09-25
call_tool WebAgent/NestBrowse/infer_async_nestbrowse.py ran Apache-2.0 (permissive) · df838ce4c63f0ea4 · report fixture: returned coroutine · level recorded 2026-09-25
call_tool WebAgent/ParallelMuse/functionality_specified_partial_rollout.py ran Apache-2.0 (permissive) · c517da931a712d31 · report fixture: signature sem:dict/0/?, tool_name:str/0/str, tool_args:dict/0/? · returned coroutine · level recorded 2026-09-25
cluster_by_question WebAgent/ParallelMuse/compressed_reasoning_aggregation.py ran · our draft was wrong Apache-2.0 (permissive) · ef0eff9da9ccbda2 · report fixture: signature dataset:list/1/dict · returned list · level recorded 2026-09-25
count_tokens in 39 papers WebAgent/NestBrowse/utils.py ran Apache-2.0 (permissive) · 23aacba017665d93 · report fixture: signature text:str/0/str, tokenizer:MockTokenizer/0/? · returned int · level recorded 2026-09-25
extract_tags WebAgent/AgentFold/infer.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 6f7ac5ce08066791 · report fixture: signature text:str/0/str, tag:str/0/str · returned str · level recorded 2026-09-25
get_llm_response in 8 papers WebAgent/ParallelMuse/compressed_reasoning_aggregation.py ran Apache-2.0 (permissive) · f78af907d3807fbc · report fixture: signature messages:list/1/dict, max_tokens:int/0/int · returned coroutine · level recorded 2026-09-25
read_jsonl in 136 papers WebAgent/NestBrowse/utils.py ran · our draft was wrong Apache-2.0 (permissive) · ecb8ee265d233ddd · report fixture: signature file_path:str/0/str · returned list · level recorded 2026-09-25
get_llm_response_nonstream WebAgent/AgentFold/infer.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · c06aada9aaf8d772 · report
single_round_statistics WebAgent/WebResummer/src/evaluate.py unverified Apache-2.0 (permissive) · d903fce78a4ff441 · report
alibaba-nlp/webwalker community (archive-listed) 10 samples, 6 ran (5 instrument-failed) · 4 unverified
clean_markdown WebAgent/WebWalker/src/utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · c2e42aa986785080 · report fixture: signature res:str/0/str · returned str · level recorded 2026-09-25
extract_response in 7 papers evaluation/evaluate_hle_official.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · a4ee90a1bd5be041 · report fixture: signature messages:dict/0/? · returned tuple · level recorded 2026-09-25
is_correct_judgement evaluation/evaluate_deepsearch_official.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · 11c85a122a8418ae · report fixture: signature judgement:str/0/str · returned bool · level recorded 2026-09-25
load_jsonl in 179 papers evaluation/evaluate_hle_official.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · e587e0fad56e82f2 · report fixture: signature fp:str/0/str · returned list · level recorded 2026-09-25
process_single_round evaluation/evaluate_deepsearch_official.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · d9c80590a339f019 · report fixture: signature input_file:str/0/str · returned list · level recorded 2026-09-25
process_url WebAgent/WebWalker/src/utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · d48b7faf85d5ebcb · report fixture: signature url:str/0/str, sub_url:str/0/str · returned str · level recorded 2026-09-25
call_llm_judge evaluation/evaluate_deepsearch_official.py unverified Apache-2.0 (permissive) · 09d32bbfdc4d6cf2 · report
extract_answer in 112 papers evaluation/evaluate_hle_official.py unverified Apache-2.0 (permissive) · 079a31f347eec894 · report
gemini_api WebAgent/WebWalker/src/rag_system.py unverified Apache-2.0 (permissive) · e6b851ca45ef45b8 · report
o1_api WebAgent/WebWalker/src/rag_system.py unverified Apache-2.0 (permissive) · 149cf8d65d996603 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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