ProRAC: A Neuro-symbolic Method for Reasoning about Actions with LLM-based Progression
This addresses reasoning challenges in AI for domains requiring action-based logic, but it is incremental as it builds on existing neuro-symbolic and LLM methods.
The paper tackles reasoning about actions and change (RAC) problems by proposing ProRAC, a neuro-symbolic framework that uses LLMs to extract elements, execute actions progressively, and evaluate queries, achieving strong performance across various benchmarks, domains, LLM backbones, and task types.
In this paper, we propose ProRAC (Progression-based Reasoning about Actions and Change), a neuro-symbolic framework that leverages LLMs to tackle RAC problems. ProRAC extracts fundamental RAC elements including actions and questions from the problem, progressively executes each action to derive the final state, and then evaluates the query against the progressed state to arrive at an answer. We evaluate ProRAC on several RAC benchmarks, and the results demonstrate that our approach achieves strong performance across different benchmarks, domains, LLM backbones, and types of RAC tasks.