KC-Agent: A Dual-Process Cognitive Architecture for Efficient ML Model Improvement
2026-08-03 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors introduce KC-Agent, a system that helps keep machine learning models accurate when the data they see changes over time. It uses two parts: one that quickly recognizes patterns based on past successful updates, and another that carefully improves the model step-by-step. By combining these, KC-Agent works faster and better than other similar methods when tested on various datasets, including real-world NASA data. The system also safely manages changes to avoid mistakes during updates. Overall, the authors show it is a practical and effective way to handle changing data in machine learning.
Data DriftMachine Learning Model UpdateCognitive ArchitectureSystem 1 and System 2Pattern RecognitionIncremental LearningAtomic ChangesRollback MechanismNASA Turbofan DatasetAutomated Machine Learning (AutoML)
Authors
Gusseppe Bravo-Rocca, Jordi Guitart, Ajay Dholakia, David Ellison, Puneet Jain
Abstract
Data drift poses significant challenges for machine learning systems in production, requiring continuous model updates to maintain performance. We present KC-Agent, a dual-process cognitive architecture for automated ML model improvement that combines fast pattern recognition (System 1) with deliberate incremental updates (System 2). Our approach implements structured memory systems enabling System 1 to leverage successful solutions previously discovered by System 2, achieving efficient pattern-based responses without costly re-computation. KC-Agent incorporates atomic change principles and rollback capabilities to ensure reliable, verifiable updates in production environments. We evaluate our method on five datasets including real-world NASA turbofan data with authentic temporal degradation and synthetic datasets with controlled drift scenarios. KC-Agent achieves state-of-the-art performance (76.8% accuracy) while maintaining optimal efficiency (13.2s execution time), outperforming established cognitive architectures: CodeAct (+2.4%), Tree of Thoughts (+3.6%), ReAct (+8.0%), and Reflexion (+8.9%). Consensus evaluation by a panel of state-of-the-art LLMs confirms superior strategic efficacy (8.33/10 Smartness score), significantly outperforming baseline agents. The knowledge consolidation mechanism delivers 91% speedup over the slow variant while maintaining higher accuracy. Our approach demonstrates both theoretical foundations and practical viability for cognitive-inspired automated ML improvement systems capable of handling complex real-world data drift scenarios.