FELA: A Multi-Agent Evolutionary System for Feature Engineering of Industrial Event Log Data

2025-10-29

AI Summary

Industrial event logs exhibit high dimensionality, heterogeneity, strong temporal dependencies, and complex structural patterns. Existing automated feature engineering methods suffer from poor interpretability, inflexible operational workflows, and limited generalizability. To address these challenges, this paper proposes a large language model (LLM)-based multi-agent evolutionary system comprising four specialized agents—Idea, Code, Critic, and Evaluation—integrated with reinforcement learning and genetic algorithms. Supported by a dual-memory knowledge base and an insight-guided mechanism, the system enables closed-loop iteration across feature ideation, code generation, logical validation, and feedback-driven optimization. The approach significantly enhances feature interpretability and domain relevance, demonstrably improves downstream model performance on real-world industrial datasets, and substantially reduces manual feature engineering effort.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Multiagent Systems: Modeling other Agents
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Event log data, recording fine-grained user actions and system events, represent one of the most valuable assets for modern digital services. However, the complexity and heterogeneity of industrial event logs--characterized by large scale, high dimensionality, diverse data types, and intricate temporal or relational structures--make feature engineering extremely challenging. Existing automatic feature engineering approaches, such as AutoML or genetic methods, often suffer from limited explainability, rigid predefined operations, and poor adaptability to complicated heterogeneous data. In this paper, we propose FELA (Feature Engineering LLM Agents), a multi-agent evolutionary system that autonomously extracts meaningful and high-performing features from complex industrial event log data. FELA integrates the reasoning and coding capabilities of large language models (LLMs) with an insight-guided self-evolution paradigm. Specifically, FELA employs specialized agents--Idea Agents, Code Agents, and Critic Agents--to collaboratively generate, validate, and implement novel feature ideas. An Evaluation Agent summarizes feedback and updates a hierarchical knowledge base and dual-memory system to enable continual improvement. Moreover, FELA introduces an agentic evolution algorithm, combining reinforcement learning and genetic algorithm principles to balance exploration and exploitation across the idea space. Extensive experiments on real industrial datasets demonstrate that FELA can generate explainable, domain-relevant features that significantly improve model performance while reducing manual effort. Our results highlight the potential of LLM-based multi-agent systems as a general framework for automated, interpretable, and adaptive feature engineering in complex real-world environments.

Problem

• Automating feature engineering for complex industrial event logs
• Overcoming limitations of rigid predefined operations in AutoML
• Generating explainable features from heterogeneous temporal data structures

Innovation

• Multi-agent system uses LLMs for feature generation
• Evolution algorithm balances exploration and exploitation
• Self-evolving knowledge base enables continuous improvement