A Multi-Agent Retrieval-Augmented Framework for Work-in-Progress Predictio

2025-12-22

AI Summary

This work addresses the problem of work-in-process (WiP) time-series forecasting in predictive process monitoring. Methodologically, it proposes the first framework integrating retrieval-augmented generation (RAG) with multi-agent collaborative reasoning: event logs are narrativized into a semantic process memory enabling dynamic historical retrieval; and three specialized agents—prediction, description, and fusion—are designed to perform interpretable, robust joint decision-making via ReAct-style reasoning. The key contribution lies in pioneering the integration of RAG and multi-agent paradigms for WiP forecasting, thereby unifying deep semantic understanding with structured logical inference. Evaluated on real-world benchmark datasets, the framework achieves a mean absolute percentage error (MAPE) of 1.50%, substantially outperforming TCN, LSTM, and persistence baselines—demonstrating significant improvements in both prediction accuracy and robustness.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Work-in-Progress (WiP) prediction is critical for predictive process monitoring, enabling accurate anticipation of workload fluctuations and optimized operational planning. This paper proposes a retrieval-augmented, multi-agent framework that combines retrieval-augmented generation (RAG) and collaborative multi-agent reasoning for WiP prediction. The narrative generation component transforms structured event logs into semantically rich natural language stories, which are embedded into a semantic vector-based process memory to facilitate dynamic retrieval of historical context during inference. The framework includes predictor agents that independently leverage retrieved historical contexts and a decision-making assistant agent that extracts high-level descriptive signals from recent events. A fusion agent then synthesizes predictions using ReAct-style reasoning over agent outputs and retrieved narratives. We evaluate our framework on two real-world benchmark datasets. Results show that the proposed retrieval-augmented multi-agent approach achieves competitive prediction accuracy, obtaining a Mean Absolute Percentage Error (MAPE) of 1.50% on one dataset, and surpassing Temporal Convolutional Networks (TCN), Long Short-Term Memory (LSTM), and persistence baselines. The results highlight improved robustness, demonstrating the effectiveness of integrating retrieval mechanisms and multi-agent reasoning in WiP prediction.

Problem

• Predicting Work-in-Progress fluctuations for operational planning
• Transforming structured event logs into natural language narratives
• Integrating retrieval-augmented generation with multi-agent reasoning for accuracy

Innovation

• Multi-agent retrieval-augmented framework for WiP prediction
• Semantic vector memory enables dynamic historical context retrieval
• ReAct-style reasoning synthesizes predictions from agent outputs