open-world-learning

This paper proposes a unified uncertainty-aware probabilistic framework for continual new intent discovery under an evolving label space, using adaptive β-VAE and multi-signal decision mechanisms to enable controlled label expansion while mitigating catastrophic forgetting. Experiments demonstrate high novelty precision and stable adaptation with limited forgetting.

This paper proposes an explainable LLM agent layer placed downstream of an open-world learning pipeline for oil well anomaly detection, using the Qwen3.5-397B-A17B model to provide natural-language justifications and novelty naming on the 3W dataset.