AutoS$^2$earch: Unlocking the Reasoning Potential of Large Models for Web-based Source Search
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917945388564480 |
|---|---|
| author | Zhu, Zhengqiu Ji, Yatai Huang, Jiaheng Zhao, Yong Qiu, Sihang Ju, Rusheng |
| author_facet | Zhu, Zhengqiu Ji, Yatai Huang, Jiaheng Zhao, Yong Qiu, Sihang Ju, Rusheng |
| contents | Web-based management systems have been widely used in risk control and industrial safety. However, effectively integrating source search capabilities into these systems, to enable decision-makers to locate and address the hazard (e.g., gas leak detection) remains a challenge. While prior efforts have explored using web crowdsourcing and AI algorithms for source search decision support, these approaches suffer from overheads in recruiting human participants and slow response times in time-sensitive situations. To address this, we introduce AutoS$^2$earch, a novel framework leveraging large models for zero-shot source search in web applications. AutoS$^2$earch operates on a simplified visual environment projected through a web-based display, utilizing a chain-of-thought prompt designed to emulate human reasoning. The multi-modal large language model (MLLMs) dynamically converts visual observations into language descriptions, enabling the LLM to perform linguistic reasoning on four directional choices. Extensive experiments demonstrate that AutoS$^2$earch achieves performance nearly equivalent to human-AI collaborative source search while eliminating dependency on crowdsourced labor. Our work offers valuable insights in using web engineering to design such autonomous systems in other industrial applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09913 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AutoS$^2$earch: Unlocking the Reasoning Potential of Large Models for Web-based Source Search Zhu, Zhengqiu Ji, Yatai Huang, Jiaheng Zhao, Yong Qiu, Sihang Ju, Rusheng Artificial Intelligence Human-Computer Interaction Web-based management systems have been widely used in risk control and industrial safety. However, effectively integrating source search capabilities into these systems, to enable decision-makers to locate and address the hazard (e.g., gas leak detection) remains a challenge. While prior efforts have explored using web crowdsourcing and AI algorithms for source search decision support, these approaches suffer from overheads in recruiting human participants and slow response times in time-sensitive situations. To address this, we introduce AutoS$^2$earch, a novel framework leveraging large models for zero-shot source search in web applications. AutoS$^2$earch operates on a simplified visual environment projected through a web-based display, utilizing a chain-of-thought prompt designed to emulate human reasoning. The multi-modal large language model (MLLMs) dynamically converts visual observations into language descriptions, enabling the LLM to perform linguistic reasoning on four directional choices. Extensive experiments demonstrate that AutoS$^2$earch achieves performance nearly equivalent to human-AI collaborative source search while eliminating dependency on crowdsourced labor. Our work offers valuable insights in using web engineering to design such autonomous systems in other industrial applications. |
| title | AutoS$^2$earch: Unlocking the Reasoning Potential of Large Models for Web-based Source Search |
| topic | Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2502.09913 |