Towards Building General Purpose Embedding Models for Industry 4.0 Agents
In this work we focus on improving language models' understanding for asset maintenance to guide the engineer's decisions and minimize asset downtime. Given a set of tasks expressed in natural language for Industry 4.0 domain, each associated with queries related to a specific asset, we want to recommend relevant items and generalize to queries of similar assets. A task may involve identifying relevant sensors given a query about an asset's failure mode. Our approach begins with gathering a qualitative, expert-vetted knowledge base to construct nine asset-specific task datasets. To create more contextually informed embeddings, we augment the input tasks using Large Language Models (LLMs), providing concise descriptions of the entities involved in the queries. This embedding model is then integrated with a Reasoning and Acting agent (ReAct), which serves as a powerful tool for answering complex user queries that require multi-step reasoning, planning, and knowledge inference. Through ablation studies, we demonstrate that: (a) LLM query augmentation improves the quality of embeddings, (b) Contrastive loss and other methods that avoid in-batch negatives are superior for datasets with queries related to many items, and (c) It is crucial to balance positive and negative in-batch samples. After training and testing on our dataset, we observe a substantial improvement: HIT@1 increases by +54.2%, MAP@100 by +50.1%, and NDCG@10 by +54.7%, averaged across all tasks and models. Additionally, we empirically demonstrate the model's planning and tool invocation capabilities when answering complex questions related to industrial asset maintenance, showcasing its effectiveness in supporting Subject Matter Experts (SMEs) in their day-to-day operations.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents
With the rise of large language models (LLMs), LLM agents capable of autonomous reasoning, planning, and executing complex tasks have become a frontier in artificial intelligence. However, how to translate the research o…
CAZSL: Zero-Shot Regression for Pushing Models by Generalizing Through Context
Learning accurate models of the physical world is required for a lot of robotic manipulation tasks. However, during manipulation, robots are expected to interact with unknown workpieces so that building predictive models…
Meta-LearningregressionZero-Shot LearningDataset: Rare Event Classification in Multivariate Time Series
A real-world dataset is provided from a pulp-and-paper manufacturing industry. The dataset comes from a multivariate time series process. The data contains a rare event of paper break that commonly occurs in the industry…
ClassificationGeneral ClassificationTime SeriesTime Series AnalysisA Resourceful Reframing of Behavior Trees
Designers of autonomous agents, whether in physical or virtual environments, need to express nondeterminisim, failure, and parallelism in behaviors, as well as accounting for synchronous coordination between agents. Beha…
Vocal Bursts Type PredictionAgents All the Way Down; A Methodology for Building Custom AI Agents from Substrate to Production
Custom AI agents areagents that live inside their own application, talk to their own data and tools, enforce their own security boundaries, and carry their own brand and audit trail. What separates them from the general-…