2 papers
cs.LG2026
StateLinFormer: Stateful Training Enhancing Long-term Memory in Navigation
Zhiyuan Chen, Yuxuan Zhong, Fan Wang +4
Effective navigation intelligence relies on long-term memory to support both immediate generalization and sustained adaptation. However, existing approaches face a dilemma: modular…
cs.LG2026
MetaKube: An Experience-Aware LLM Framework for Kubernetes Failure Diagnosis
Wei Sun, Ting Wang, Xinran Tian +4
Existing LLM-based Kubernetes diagnostic systems cannot learn from operational experience, operating on static knowledge bases without improving from past resolutions. We present M…