Plan of Thoughts: Heuristic-Guided Problem Solving with Large Language Models

arXiv:2404.19055v1 Announce Type: new
Abstract: While language models (LMs) offer significant capability in zero-shot reasoning tasks across a wide range of domains, they do not perform satisfactorily in problems which requires multi-step reasoning. Previous approaches to mitigate this involves breaking a larger, multi-step task into sub-tasks and asking the language model to generate proposals ("thoughts") for each sub-task and using exhaustive planning approaches such as DFS to compose a solution. In this work, we leverage this idea to introduce two …

abstract arxiv breaking capability cs.cl domains language language models large language large language models lms reasoning tasks thoughts type while zero-shot