DyRef: Dynamic Reflection Framework Via Graph-Based Complexity for Robotic Planning

Abstract

Robotic planning tasks often involve diverse complexities, which make adaptive improvement through reflection particularly challenging. Existing LLM-based approaches typically rely on fixed routines, lacking the ability to adjust to task-specific complexity and often leading to redundant reflections. To address this, we propose DyRef, a dynamic reflection framework that models tasks as a Diagnostic Graph, measures task complexity through structural factors, and routes them through a Reflection Toolkit via a learned Routing Policy network. This design enables tailored reflection strategies that reduce redundancy and improve reasoning efficiency. Experiments in AlfWorld and on real-world robotic platforms show that DyRef improves first trial success rates by 16.1%, while reducing redundant reflections by 64.4%.