TIC: Translate-Infer-Compile for accurate 'text to plan' using LLMs and logical intermediate representations

We study the problem of generating plans for given natural language planning task requests. On one hand, LLMs excel at natural language processing but do not perform well on planning. On the other hand, classical planning tools excel at planning tasks but require input in a structured language such as the Planning Domain Definition Language (PDDL). We leverage the strengths of both the techniques by using an LLM for generating the PDDL representation (task PDDL) of planning task requests followed …

cs.ai cs.cl excel intermediate language language processing llms natural natural language natural language processing planning processing study tasks text tools translate