arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.05045cs.AIcs.CLcs.RO
收藏

大语言模型能否借助求解器的额外提示进行路径规划?

Can LLMs plan paths with extra hints from solvers?

Karlsruhe Institute for Technology(卡尔斯鲁厄理工学院);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Erik Wu, Sayan Mitra

AI总结:

本研究探索通过整合求解器生成的四类反馈(含视觉反馈)并结合微调,提升大语言模型的机器人路径规划能力,实验显示该方法可改善中等难度问题的求解效果,但难问题仍待突破。

摘要:

大语言模型(LLMs)在自然语言处理、数学问题求解以及程序合成相关任务中展现出了卓越的能力。然而,其在长期规划和高阶推理方面的有效性被指出存在局限且表现不稳定。本文探索了一种通过整合求解器生成的反馈来提升LLM解决经典机器人规划任务性能的方法。我们研究了四种不同的反馈提供策略,其中包括视觉反馈,采用了微调技术,并在10个标准规划问题和100个随机生成的规划问题上评估了三种不同LLM的性能。结果表明,求解器生成的反馈提升了LLM解决中等难度问题的能力,但更难的问题仍无法被解决。本研究对不同提示策略的效果以及所评估LLM的不同规划倾向进行了详细分析。

英文摘要:

Large Language Models (LLMs) have shown remarkable capabilities in natural language processing, mathematical problem solving, and tasks related to program synthesis. However, their effectiveness in long-term planning and higher-order reasoning has been noted to be limited and fragile. This paper explores an approach for enhancing LLM performance in solving a classical robotic planning task by integrating solver-generated feedback. We explore four different strategies for providing feedback, including visual feedback, we utilize fine-tuning, and we evaluate the performance of three different LLMs across a 10 standard and 100 more randomly generated planning problems. Our results suggest that the solver-generated feedback improves the LLM's ability to solve the moderately difficult problems, but the harder problems still remain out of reach. The study provides detailed analysis of the effects of the different hinting strategies and the different planning tendencies of the evaluated LLMs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑