Bootstrapping Human-Like Planning via LLMs
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_ | 1866918502115311616 |
|---|---|
| author | Porfirio, David Hsiao, Vincent Fine-Morris, Morgan Smith, Leslie Hiatt, Laura M. |
| author_facet | Porfirio, David Hsiao, Vincent Fine-Morris, Morgan Smith, Leslie Hiatt, Laura M. |
| contents | Robot end users increasingly require accessible means of specifying tasks for robots to perform. Two common end-user programming paradigms include drag-and-drop interfaces and natural language programming. Although natural language interfaces harness an intuitive form of human communication, drag-and-drop interfaces enable users to meticulously and precisely dictate the key actions of the robot's task. In this paper, we investigate the degree to which both approaches can be combined. Specifically, we construct a large language model (LLM)-based pipeline that accepts natural language as input and produces human-like action sequences as output, specified at a level of granularity that a human would produce. We then compare these generated action sequences to another dataset of hand-specified action sequences. Although our results reveal that larger models tend to outperform smaller ones in the production of human-like action sequences, smaller models nonetheless achieve satisfactory performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_22604 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bootstrapping Human-Like Planning via LLMs Porfirio, David Hsiao, Vincent Fine-Morris, Morgan Smith, Leslie Hiatt, Laura M. Artificial Intelligence Human-Computer Interaction Robotics Robot end users increasingly require accessible means of specifying tasks for robots to perform. Two common end-user programming paradigms include drag-and-drop interfaces and natural language programming. Although natural language interfaces harness an intuitive form of human communication, drag-and-drop interfaces enable users to meticulously and precisely dictate the key actions of the robot's task. In this paper, we investigate the degree to which both approaches can be combined. Specifically, we construct a large language model (LLM)-based pipeline that accepts natural language as input and produces human-like action sequences as output, specified at a level of granularity that a human would produce. We then compare these generated action sequences to another dataset of hand-specified action sequences. Although our results reveal that larger models tend to outperform smaller ones in the production of human-like action sequences, smaller models nonetheless achieve satisfactory performance. |
| title | Bootstrapping Human-Like Planning via LLMs |
| topic | Artificial Intelligence Human-Computer Interaction Robotics |
| url | https://arxiv.org/abs/2506.22604 |