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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2507.02592")

Code

Syntology Ran 0 of 22 code samples harvested from 2 repositories linked to this paper; 22 have no recorded run.

By repository: official repository: 12 samples from 1 repository, 0 ran; community (archive-listed): 10 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

alibaba-nlp/webagent officialmentioned in papermentioned on GitHubApache-2.0 report
SnailDev/github-hot-hub mentioned on GitHubpytorchMIT report
alibaba-nlp/webwalker mentioned on GitHubApache-2.0 report
kun-g/Scraping-Github-trending mentioned on GitHubtf 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; 0 ran; 0 honoured the contract we drafted; 22 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

22unverified

Licence: 0 of the 22 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

call_llm alibaba-nlp/webagent/WebAgent/NestBrowse/utils.py official repository unverified Apache-2.0 (permissive) · cc601f60e63e7a5c · report
call_llm alibaba-nlp/webagent/WebAgent/ParallelMuse/functionality_specified_partial_rollout.py official repository unverified Apache-2.0 (permissive) · ffcb6da25872786e · report
call_resum_server alibaba-nlp/webagent/WebAgent/WebResummer/src/summary_utils.py official repository unverified Apache-2.0 (permissive) · 8605222f211cb27e · report
call_tool alibaba-nlp/webagent/WebAgent/NestBrowse/infer_async_nestbrowse.py official repository unverified Apache-2.0 (permissive) · df838ce4c63f0ea4 · report
call_tool alibaba-nlp/webagent/WebAgent/ParallelMuse/functionality_specified_partial_rollout.py official repository unverified Apache-2.0 (permissive) · c517da931a712d31 · report
cluster_by_question alibaba-nlp/webagent/WebAgent/ParallelMuse/compressed_reasoning_aggregation.py official repository unverified Apache-2.0 (permissive) · ef0eff9da9ccbda2 · report
count_tokens alibaba-nlp/webagent/WebAgent/NestBrowse/utils.py official repository unverified Apache-2.0 (permissive) · 23aacba017665d93 · report
extract_tags alibaba-nlp/webagent/WebAgent/AgentFold/infer.py official repository unverified Apache-2.0 (permissive) · 6f7ac5ce08066791 · report
get_llm_response alibaba-nlp/webagent/WebAgent/ParallelMuse/compressed_reasoning_aggregation.py official repository unverified Apache-2.0 (permissive) · f78af907d3807fbc · report
get_llm_response_nonstream alibaba-nlp/webagent/WebAgent/AgentFold/infer.py official repository unverified Apache-2.0 (permissive) · c06aada9aaf8d772 · report
read_jsonl alibaba-nlp/webagent/WebAgent/NestBrowse/utils.py official repository unverified Apache-2.0 (permissive) · ecb8ee265d233ddd · report
single_round_statistics alibaba-nlp/webagent/WebAgent/WebResummer/src/evaluate.py official repository unverified Apache-2.0 (permissive) · d903fce78a4ff441 · report
call_llm_judge alibaba-nlp/webwalker/evaluation/evaluate_deepsearch_official.py community (archive-listed) unverified Apache-2.0 (permissive) · 09d32bbfdc4d6cf2 · report
clean_markdown alibaba-nlp/webwalker/WebAgent/WebWalker/src/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · c2e42aa986785080 · report
extract_answer alibaba-nlp/webwalker/evaluation/evaluate_hle_official.py community (archive-listed) unverified Apache-2.0 (permissive) · 079a31f347eec894 · report
extract_response alibaba-nlp/webwalker/evaluation/evaluate_hle_official.py community (archive-listed) unverified Apache-2.0 (permissive) · a4ee90a1bd5be041 · report
gemini_api alibaba-nlp/webwalker/WebAgent/WebWalker/src/rag_system.py community (archive-listed) unverified Apache-2.0 (permissive) · e6b851ca45ef45b8 · report
is_correct_judgement alibaba-nlp/webwalker/evaluation/evaluate_deepsearch_official.py community (archive-listed) unverified Apache-2.0 (permissive) · 11c85a122a8418ae · report
load_jsonl alibaba-nlp/webwalker/evaluation/evaluate_hle_official.py community (archive-listed) unverified Apache-2.0 (permissive) · e587e0fad56e82f2 · report
o1_api alibaba-nlp/webwalker/WebAgent/WebWalker/src/rag_system.py community (archive-listed) unverified Apache-2.0 (permissive) · 149cf8d65d996603 · report
process_single_round alibaba-nlp/webwalker/evaluation/evaluate_deepsearch_official.py community (archive-listed) unverified Apache-2.0 (permissive) · d9c80590a339f019 · report
process_url alibaba-nlp/webwalker/WebAgent/WebWalker/src/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · d48b7faf85d5ebcb · 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