Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2512.19841 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908728830197760 |
|---|---|
| author | Bibalan, Yousef Mehrdad Far, Behrouz Moshirpour, Mohammad Ghiyasian, Bahareh |
| author_facet | Bibalan, Yousef Mehrdad Far, Behrouz Moshirpour, Mohammad Ghiyasian, Bahareh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_19841 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Multi-Agent Retrieval-Augmented Framework for Work-in-Progress Predictio Bibalan, Yousef Mehrdad Far, Behrouz Moshirpour, Mohammad Ghiyasian, Bahareh Multiagent Systems 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. |
| title | A Multi-Agent Retrieval-Augmented Framework for Work-in-Progress Predictio |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2512.19841 |