Large Language Models Can Plan Your Travels Rigorously with Formal Verification Tools

arXiv:2404.11891v1 Announce Type: cross
Abstract: The recent advancements of Large Language Models (LLMs), with their abundant world knowledge and capabilities of tool-using and reasoning, fostered many LLM planning algorithms. However, LLMs have not shown to be able to accurately solve complex combinatorial optimization problems. In Xie et al. (2024), the authors proposed TravelPlanner, a U.S. domestic travel planning benchmark, and showed that LLMs themselves cannot make travel plans that satisfy user requirements with a best success rate of 0.6%. In …

abstract algorithms arxiv capabilities cs.ai cs.cl cs.hc however knowledge language language models large language large language models llm llms optimization planning reasoning solve tool tools travels type verification world