DRIP: Decompositional reasoning for Robust and Iterative Planning with LLM Agent

ICLR 2026 Conference Submission14859 Authors

Keywords: LLM Agent, Planning, Backward reasonig

TL;DR: We proposed a human-inspired LLM planning framework that decomposes complex tasks into preconditions and subtasks, demonstrating superior robustness compared to existing methods and advancing real-world applicability of LLM-based planning.

Abstract: Research on LLM agents has shown remarkable progress, particularly in planning methods that leverage the reasoning capabilities of LLMs. However, challenges such as robustness and efficiency remain in LLM-based planning, with robustness, in particular, posing a significant barrier to real-world applications. In this study, we propose a framework that incorporates human reasoning abilities into planning. Specifically, this framework mimics the human ability to break down complex problems into simpler problems, enabling the decomposition of complex tasks into preconditions and subsequently deriving subtasks. The results of our evaluation experiments demonstrated that this human-like capability can be effectively applied to planning. Furthermore, the proposed framework exhibited superior robustness, offering new perspectives for LLM-based planning methods.

Primary Area: applications to robotics, autonomy, planning

Submission Number: 14859