Graph-enhanced Large Language Models in Asynchronous Plan Reasoning

Autor:	Lin, Fangru, La Malfa, Emanuele, Hofmann, Valentin, Yang, Elle Michelle, Cohn, Anthony, Pierrehumbert, Janet B.
Rok vydání:	2024
Předmět:	Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Planning is a fundamental property of human intelligence. Reasoning about asynchronous plans is challenging since it requires sequential and parallel planning to optimize time costs. Can large language models (LLMs) succeed at this task? Here, we present the first large-scale study investigating this question. We find that a representative set of closed and open-source LLMs, including GPT-4 and LLaMA-2, behave poorly when not supplied with illustrations about the task-solving process in our benchmark AsyncHow. We propose a novel technique called Plan Like a Graph (PLaG) that combines graphs with natural language prompts and achieves state-of-the-art results. We show that although PLaG can boost model performance, LLMs still suffer from drastic degradation when task complexity increases, highlighting the limits of utilizing LLMs for simulating digital devices. We see our study as an exciting step towards using LLMs as efficient autonomous agents. Our code and data are available at https://github.com/fangru-lin/graph-llm-asynchow-plan. Comment: Accepted at ICML-2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.02805 Zobrazit plný text záznamu View this record from Arxiv