WebSailor: Navigating Super-human Reasoning for Web Agent
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915370472833024 |
|---|---|
| author | Li, Kuan Zhang, Zhongwang Yin, Huifeng Zhang, Liwen Ou, Litu Wu, Jialong Yin, Wenbiao Li, Baixuan Tao, Zhengwei Wang, Xinyu Shen, Weizhou Zhang, Junkai Zhang, Dingchu Wu, Xixi Jiang, Yong Yan, Ming Xie, Pengjun Huang, Fei Zhou, Jingren |
| author_facet | Li, Kuan Zhang, Zhongwang Yin, Huifeng Zhang, Liwen Ou, Litu Wu, Jialong Yin, Wenbiao Li, Baixuan Tao, Zhengwei Wang, Xinyu Shen, Weizhou Zhang, Junkai Zhang, Dingchu Wu, Xixi Jiang, Yong Yan, Ming Xie, Pengjun Huang, Fei Zhou, Jingren |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02592 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WebSailor: Navigating Super-human Reasoning for Web Agent Li, Kuan Zhang, Zhongwang Yin, Huifeng Zhang, Liwen Ou, Litu Wu, Jialong Yin, Wenbiao Li, Baixuan Tao, Zhengwei Wang, Xinyu Shen, Weizhou Zhang, Junkai Zhang, Dingchu Wu, Xixi Jiang, Yong Yan, Ming Xie, Pengjun Huang, Fei Zhou, Jingren Computation and Language Artificial Intelligence 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. |
| title | WebSailor: Navigating Super-human Reasoning for Web Agent |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2507.02592 |