What's the Plan? Evaluating and Developing Planning-Aware Techniques for Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917673325035520 |
|---|---|
| author | Hirsch, Eran Uziel, Guy Anaby-Tavor, Ateret |
| author_facet | Hirsch, Eran Uziel, Guy Anaby-Tavor, Ateret |
| contents | Planning is a fundamental task in artificial intelligence that involves finding a sequence of actions that achieve a specified goal in a given environment. Large language models (LLMs) are increasingly used for applications that require planning capabilities, such as web or embodied agents. In line with recent studies, we demonstrate through experimentation that LLMs lack necessary skills required for planning. Based on these observations, we advocate for the potential of a hybrid approach that combines LLMs with classical planning methodology. Then, we introduce SimPlan, a novel hybrid-method, and evaluate its performance in a new challenging setup. Our extensive experiments across various planning domains demonstrate that SimPlan significantly outperforms existing LLM-based planners. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11489 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | What's the Plan? Evaluating and Developing Planning-Aware Techniques for Language Models Hirsch, Eran Uziel, Guy Anaby-Tavor, Ateret Computation and Language Planning is a fundamental task in artificial intelligence that involves finding a sequence of actions that achieve a specified goal in a given environment. Large language models (LLMs) are increasingly used for applications that require planning capabilities, such as web or embodied agents. In line with recent studies, we demonstrate through experimentation that LLMs lack necessary skills required for planning. Based on these observations, we advocate for the potential of a hybrid approach that combines LLMs with classical planning methodology. Then, we introduce SimPlan, a novel hybrid-method, and evaluate its performance in a new challenging setup. Our extensive experiments across various planning domains demonstrate that SimPlan significantly outperforms existing LLM-based planners. |
| title | What's the Plan? Evaluating and Developing Planning-Aware Techniques for Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.11489 |