|国家预印本平台
首页|Conditional Multi-Stage Failure Recovery for Embodied Agents

Conditional Multi-Stage Failure Recovery for Embodied Agents

Conditional Multi-Stage Failure Recovery for Embodied Agents

来源:Arxiv_logoArxiv
英文摘要

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%.

Youmna Farag、Svetlana Stoyanchev、Mohan Li、Simon Keizer、Rama Doddipatla

计算技术、计算机技术

Youmna Farag,Svetlana Stoyanchev,Mohan Li,Simon Keizer,Rama Doddipatla.Conditional Multi-Stage Failure Recovery for Embodied Agents[EB/OL].(2025-07-08)[2025-07-19].https://arxiv.org/abs/2507.06016.点此复制

评论