no code implementations • 21 May 2024 • Sudhir Agarwal, Anu Sreepathy, David H. Alonso, Prarit Lamba
The key idea behind our proposed approach is to leverage logical reasoning and classical AI planning along with an LLM for accurately answering user queries including identification and gathering of any missing information in these queries.
no code implementations • 9 Feb 2024 • Sudhir Agarwal, Anu Sreepathy
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.
no code implementations • 12 Jan 2023 • Sudhir Agarwal, Anu Sreepathy, Lalla Mouatadid
We propose a novel scalable end-to-end pipeline that uses symbolic domain knowledge as constraints for learning a neural network for classifying unlabeled data in a weak-supervised manner.