用大模型分阶段处理机器人任务失败，效果优于现有方法。
Conditional Multi-Stage Failure Recovery for Embodied Agents
- 基于大模型零样本链式提示，分四阶段处理任务失败。
- 在TEACH数据集上比无恢复机制基线高11.5%，领先最强模型19%。
- 适合需要高鲁棒性的智能体任务系统开发者参考。
执行复杂任务的具身智能体容易发生执行失败，亟需有效的故障恢复机制。本文提出一种条件多阶段故障恢复框架，采用零样本链式提示。该框架包含四个错误处理阶段：其中三个在任务执行期间运行，一个作为事后反思阶段。我们的方法利用大模型的推理能力，在环境上下文中分析执行挑战并制定策略性解决方案。我们在TEACH数据集的TfD基准上评估该方法，达到当前最优性能：相比无故障恢复的基线提升11.5%，超越现有最强模型19%。
原文摘要 · Abstract (English)
Embodied agents performing complex tasks are susceptible to execution failures, motivating the need for effective failure recovery mechanisms. In this work, we introduce a conditional multistage failure recovery framework that employs zero-shot chain prompting. The framework is structured into four error-handling stages, with three operating during task execution and one functioning as a post-execution reflection phase. Our approach utilises the reasoning capabilities of LLMs to analyse execution challenges within their environmental context and devise strategic solutions. We evaluate our method on the TfD benchmark of the TEACH dataset and achieve state-of-the-art performance, outperforming a baseline without error recovery by 11.5% and surpassing the strongest existing model by 19%.
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。