This is a research initiative by Intuit AI Research and focuses on techniques and methodologies that combine symbolic and sub-symbolic AI. Some of our work in this space include -
- Translate-Infer-Compile(TIC) for accurate "text to plan" using LLMs and Logical Representations
- LLM+Reasoning+Planning for supporting incomplete user queries in presence of APIs
- [20204.06] LLM+Reasoning+Planning paper accepted at ICLP 2024
- [2024.06] TIC paper accepted at NeSy 2024
In this work, 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 by using a classical planner for computing a plan. Unlike previous approaches that use LLMs for generating task PDDLs directly, our approach comprises of (a) translate: using an LLM only for generating a logically interpretable intermediate representation of natural language task description, (b) infer: deriving additional logically dependent information from the intermediate representation using a logic reasoner (currently, Answer Set Programming solver), and (c) compile: generating the target task PDDL from the base and inferred information. We observe that using an LLM to only output the intermediate representation significantly reduces LLM errors. Consequently, TIC approach achieves, for at least one LLM, high accuracy on task PDDL generation for all seven domains of our evaluation dataset.