Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Anthony Z., Wang, Xinhe, Sansom, Jacob, Fu, Yao, Choi, Jongwook, Sohn, Sungryull, Kim, Jaekyeom, Lee, Honglak
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2411.13826
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917843642089472
author Liu, Anthony Z.
Wang, Xinhe
Sansom, Jacob
Fu, Yao
Choi, Jongwook
Sohn, Sungryull
Kim, Jaekyeom
Lee, Honglak
author_facet Liu, Anthony Z.
Wang, Xinhe
Sansom, Jacob
Fu, Yao
Choi, Jongwook
Sohn, Sungryull
Kim, Jaekyeom
Lee, Honglak
contents Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making, but often struggle with complex, long-horizon planning tasks. Recent techniques have sought to structure LLM outputs using control flow and other code-adjacent techniques to improve planning performance. These techniques include using variables (to track important information) and functions (to divide complex tasks into smaller re-usable sub-tasks). However, purely code-based approaches can be error-prone and insufficient for handling ambiguous or unstructured data. To address these challenges, we propose REPL-Plan, an LLM planning approach that is fully code-expressive (it can utilize all the benefits of code) while also being dynamic (it can flexibly adapt from errors and use the LLM for fuzzy situations). In REPL-Plan, an LLM solves tasks by interacting with a Read-Eval-Print Loop (REPL), which iteratively executes and evaluates code, similar to language shells or interactive code notebooks, allowing the model to flexibly correct errors and handle tasks dynamically. We demonstrate that REPL-Plan achieves strong results across various planning domains compared to previous methods.
format Preprint
id arxiv_https___arxiv_org_abs_2411_13826
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Interactive and Expressive Code-Augmented Planning with Large Language Models
Liu, Anthony Z.
Wang, Xinhe
Sansom, Jacob
Fu, Yao
Choi, Jongwook
Sohn, Sungryull
Kim, Jaekyeom
Lee, Honglak
Computation and Language
Machine Learning
Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making, but often struggle with complex, long-horizon planning tasks. Recent techniques have sought to structure LLM outputs using control flow and other code-adjacent techniques to improve planning performance. These techniques include using variables (to track important information) and functions (to divide complex tasks into smaller re-usable sub-tasks). However, purely code-based approaches can be error-prone and insufficient for handling ambiguous or unstructured data. To address these challenges, we propose REPL-Plan, an LLM planning approach that is fully code-expressive (it can utilize all the benefits of code) while also being dynamic (it can flexibly adapt from errors and use the LLM for fuzzy situations). In REPL-Plan, an LLM solves tasks by interacting with a Read-Eval-Print Loop (REPL), which iteratively executes and evaluates code, similar to language shells or interactive code notebooks, allowing the model to flexibly correct errors and handle tasks dynamically. We demonstrate that REPL-Plan achieves strong results across various planning domains compared to previous methods.
title Interactive and Expressive Code-Augmented Planning with Large Language Models
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2411.13826