PDDL-Based Task Decomposition in LaMMA-P and Long-Horizon Reasoning on BigBench-Hard

This report synthesises findings from 8 peer-reviewed papers addressing the following research question: How does the PDDL-based task decomposition in LaMMA-P affect long-horizon reasoning accuracy on the BigBench-Hard suite compared to chain-of-thought prompting in standalone LLMs. This review critically distinguishes between AI Agents and Agentic AI, offering a structured, conceptual taxonomy, application mapping, and analysis of opportunities and challenges to clarify their divergent design philosophies and capabilities. We begin by outlining the search. 10 claims were extracted from source literature; 10 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 9.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the PDDL-based task decomposition in LaMMA-P affect long-horizon reasoning accuracy on the BigBench-Hard suite compared to chain-of-thought prompting in standalone LLMs?

Autonomous literature synthesis. Automated review score: 9.0/10. Full text and citation available at Assignee Research.