Managing complex FA workflows with LLM-based reasoning and acting agents
Managing complex FA workflows with LLM-based reasoning and acting agents
Tuesday, November 18, 2025: 2:10 PM
1 (Pasadena Convention Center)
Summary:
Failure Analysis (FA) is a highly intricate and knowledge-intensive process. The integration of AI components within the computational infrastructure of FA labs has the potential to automate various tasks, including detecting non-conformities in images, retrieving analogous cases from diverse data sources, and generating reports from annotated images. However, as the number of deployed AI models increases, the challenge lies in orchestrating these components into cohesive and efficient workflows, seamlessly integrating with the FA process. This paper investigates designing and implementing a Large Language Model (LLM)-based Planning Agent (LPA) to assist FA engineers in solving their analysis cases. The LPA integrates LLMs with advanced planning capabilities and external tool utilization, enabling autonomous processing of complex queries, retrieval of relevant data from external systems, and generation of human-readable responses. Evaluation results demonstrate the agent’s operational effectiveness and reliability in supporting FA tasks.
Failure Analysis (FA) is a highly intricate and knowledge-intensive process. The integration of AI components within the computational infrastructure of FA labs has the potential to automate various tasks, including detecting non-conformities in images, retrieving analogous cases from diverse data sources, and generating reports from annotated images. However, as the number of deployed AI models increases, the challenge lies in orchestrating these components into cohesive and efficient workflows, seamlessly integrating with the FA process. This paper investigates designing and implementing a Large Language Model (LLM)-based Planning Agent (LPA) to assist FA engineers in solving their analysis cases. The LPA integrates LLMs with advanced planning capabilities and external tool utilization, enabling autonomous processing of complex queries, retrieval of relevant data from external systems, and generation of human-readable responses. Evaluation results demonstrate the agent’s operational effectiveness and reliability in supporting FA tasks.