While NSAI has made significant progress in recent years, there are still several challenges and open research questions. Some future directions for NSAI research include:
Pure neural or pure symbolic methods fail; NeSy excels in these domains: While NSAI has made significant progress in recent
Pure LLMs fail at formal reasoning. The new frontier is where the LLM acts as a semantic parser and a symbolic solver (e.g., Z3, Prolog, SQL engine) executes the reasoning. While NSAI has made significant progress in recent
Graph neural networks + symbolic structures While NSAI has made significant progress in recent