让机器人像人一样灵活反思，自动修正复杂任务中的错误。
FCRF: Flexible Constructivism Reflection for Long-Horizon Robotic Task Planning with Large Language Models
- 用可变反思机制，根据任务难易动态调整纠错策略。
- 在模拟和真实环境测试中，任务完成率显著提升。
- 适合需要长期规划与自主纠错的家用机器人场景。
自主错误纠正对家用机器人可靠执行复杂长时序任务至关重要。以往工作探索了大语言模型（LLM）在任务规划中的自我反思以纠正错误，但现有方法受限于僵化的反思机制，影响效果。受人类认知适应性的启发，我们提出柔性建构主义反思框架（FCRF），一种新型导师-执行者架构，使LLM能依据任务难度灵活进行自我反思，并建设性地融合历史经验与失败教训。我们在AlfWorld仿真环境及真实世界环境中对多种家庭任务进行了评估。实验结果表明，FCRF显著提升了复杂长时序机器人任务的整体表现与自我反思灵活性。
原文摘要 · Abstract (English)
Autonomous error correction is critical for domestic robots to achieve reliable execution of complex long-horizon tasks. Prior work has explored self-reflection in Large Language Models (LLMs) for task planning error correction; however, existing methods are constrained by inflexible self-reflection mechanisms that limit their effectiveness. Motivated by these limitations and inspired by human cognitive adaptation, we propose the Flexible Constructivism Reflection Framework (FCRF), a novel Mentor-Actor architecture that enables LLMs to perform flexible self-reflection based on task difficulty, while constructively integrating historical valuable experience with failure lessons. We evaluated FCRF on diverse domestic tasks through simulation in AlfWorld and physical deployment in the real-world environment. Experimental results demonstrate that FCRF significantly improves overall performance and self-reflection flexibility in complex long-horizon robotic tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。