Ask more, know better: Reinforce-Learned Prompt Questions for Decision Making with Large Language Models

arXiv:2310.18127v2 Announce Type: replace
Abstract: Large language models (LLMs) demonstrate their promise in tackling complicated practical challenges by combining action-based policies with chain of thought (CoT) reasoning. Having high-quality prompts on hand, however, is vital to the framework's effectiveness. Currently, these prompts are handcrafted utilising extensive human labor, resulting in CoT policies that frequently fail to generalise. Human intervention is also required to develop grounding functions that ensure low-level controllers appropriately process CoT reasoning. In this paper, we propose a …

abstract arxiv chain of thought challenges cs.ai cs.cl cs.lg decision decision making framework language language models large language large language models llms making practical prompt prompts quality questions reasoning reinforce thought type vital