Unveiling Disparities in Web Task Handling Between Human and Web Agent
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917660989587456 |
|---|---|
| author | Son, Kihoon Kwon, Jinhyeon Choi, DaEun Kim, Tae Soo Kim, Young-Ho Yun, Sangdoo Kim, Juho |
| author_facet | Son, Kihoon Kwon, Jinhyeon Choi, DaEun Kim, Tae Soo Kim, Young-Ho Yun, Sangdoo Kim, Juho |
| contents | With the advancement of Large-Language Models (LLMs) and Large Vision-Language Models (LVMs), agents have shown significant capabilities in various tasks, such as data analysis, gaming, or code generation. Recently, there has been a surge in research on web agents, capable of performing tasks within the web environment. However, the web poses unforeseeable scenarios, challenging the generalizability of these agents. This study investigates the disparities between human and web agents' performance in web tasks (e.g., information search) by concentrating on planning, action, and reflection aspects during task execution. We conducted a web task study with a think-aloud protocol, revealing distinct cognitive actions and operations on websites employed by humans. Comparative examination of existing agent structures and human behavior with thought processes highlighted differences in knowledge updating and ambiguity handling when performing the task. Humans demonstrated a propensity for exploring and modifying plans based on additional information and investigating reasons for failure. These findings offer insights into designing planning, reflection, and information discovery modules for web agents and designing the capturing method for implicit human knowledge in a web task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_04497 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unveiling Disparities in Web Task Handling Between Human and Web Agent Son, Kihoon Kwon, Jinhyeon Choi, DaEun Kim, Tae Soo Kim, Young-Ho Yun, Sangdoo Kim, Juho Human-Computer Interaction With the advancement of Large-Language Models (LLMs) and Large Vision-Language Models (LVMs), agents have shown significant capabilities in various tasks, such as data analysis, gaming, or code generation. Recently, there has been a surge in research on web agents, capable of performing tasks within the web environment. However, the web poses unforeseeable scenarios, challenging the generalizability of these agents. This study investigates the disparities between human and web agents' performance in web tasks (e.g., information search) by concentrating on planning, action, and reflection aspects during task execution. We conducted a web task study with a think-aloud protocol, revealing distinct cognitive actions and operations on websites employed by humans. Comparative examination of existing agent structures and human behavior with thought processes highlighted differences in knowledge updating and ambiguity handling when performing the task. Humans demonstrated a propensity for exploring and modifying plans based on additional information and investigating reasons for failure. These findings offer insights into designing planning, reflection, and information discovery modules for web agents and designing the capturing method for implicit human knowledge in a web task. |
| title | Unveiling Disparities in Web Task Handling Between Human and Web Agent |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2405.04497 |