FLTRNN: Faithful Long-Horizon Task Planning for Robotics with Large Language Models

Recent planning methods based on Large Lan- guage Models typically employ the In-Context Learning paradigm. Complex long-horizon planning tasks require more context(including instructions and demonstrations) to guaran- tee that the generated plan can be executed correctly. However, in such conditions, LLMs may overlook(unfaithful) the rules in the given context, resulting in the generated plans being invalid or even leading to dangerous actions. In this paper, we investigate the faithfulness of LLMs for complex long-horizon tasks. Inspired by human intelligence, we introduce a novel framework named FLTRNN. FLTRNN employs a language- based RNN structure to integrate task decomposition and mem- ory management into LLM planning inference, which could effectively improve the faithfulness of LLMs and make the plan- ner more reliable. We conducted experiments in VirtualHome household tasks. Results show that our model significantly im- proves faithfulness and success rates for complex long-horizon tasks. Website at https://tannl.github.io/FLTRNN.github.io/