Multi-Agent Causal Reasoning System for Error Pattern Rule Automation in Vehicles
🤖 AI Summary
This work addresses the high cost and error-proneness of manually authored diagnostic rules based on Diagnostic Trouble Code (DTC) combinations in vehicle fault diagnosis. To overcome these limitations, the authors propose CAREP, a novel multi-agent system that, for the first time, integrates multi-agent collaboration with causal reasoning to automatically generate interpretable error pattern rules from high-dimensional DTC sequences. By combining causal discovery, contextual metadata fusion, and Boolean rule synthesis, CAREP produces transparent and logically sound diagnostic rules. Evaluated on a real-world dataset comprising 29,100 DTCs and 474 ground-truth error patterns, CAREP not only outperforms large language model baselines in rule generation accuracy but also provides clear causal inference pathways, significantly enhancing both the automation and interpretability of diagnostic rule creation.
Application Category
📝 Abstract
Modern vehicles generate thousands of different discrete events known as Diagnostic Trouble Codes (DTCs). Automotive manufacturers use Boolean combinations of these codes, called error patterns (EPs), to characterize system faults and ensure vehicle safety. Yet, EP rules are still manually handcrafted by domain experts, a process that is expensive and prone to errors as vehicle complexity grows. This paper introduces CAREP (Causal Automated Reasoning for Error Patterns), a multi-agent system that automatizes the generation of EP rules from high-dimensional event sequences of DTCs. CAREP combines a causal discovery agent that identifies potential DTC-EP relations, a contextual information agent that integrates metadata and descriptions, and an orchestrator agent that synthesizes candidate boolean rules together with interpretable reasoning traces. Evaluation on a large-scale automotive dataset with over 29,100 unique DTCs and 474 error patterns demonstrates that CAREP can automatically and accurately discover the unknown EP rules, outperforming LLM-only baselines while providing transparent causal explanations. By uniting practical causal discovery and agent-based reasoning, CAREP represents a step toward fully automated fault diagnostics, enabling scalable, interpretable, and cost-efficient vehicle maintenance.
Problem
Research questions and friction points this paper is trying to address.
Diagnostic Trouble Codes
Error Patterns
Rule Automation
Vehicle Fault Diagnosis
Manual Rule Crafting
Innovation
Methods, ideas, or system contributions that make the work stand out.
multi-agent system
causal discovery
error pattern automation
interpretable reasoning
automotive diagnostics
🔎 Similar Papers
No similar papers found.
