Conditional Multi-Stage Failure Recovery for Embodied Agents
This addresses failure recovery for embodied agents, which is an incremental improvement in a domain-specific area.
The paper tackles the problem of execution failures in embodied agents performing complex tasks by introducing a conditional multistage failure recovery framework using zero-shot chain prompting, achieving state-of-the-art performance with an 11.5% improvement over a baseline and 19% over the strongest existing model on the TfD benchmark.
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%.