Search papers, labs, and topics across Lattice.
This paper introduces PASE, a novel fault self-healing framework that leverages a Planning-Aware Semantic engine to transform recovery into a neuro-symbolic program synthesis task. By integrating a Large Language Model for structured recovery plan generation and a Neural-Symbolic World Model for plan verification, PASE creates a dynamic feedback loop that enhances recovery strategies in cloud-based AI systems. Experimental results show that PASE reduces average recovery time by over 40% and improves fault detection accuracy in previously unknown scenarios, marking a significant advancement in autonomous system management.
PASE cuts cloud recovery time by over 40% while enhancing fault detection accuracy, redefining how we approach self-healing in AI systems.
As the scale and complexity of cloud-based AI systems continue to escalate, ensuring service reliability through rapid fault detection and adaptive recovery has become a critical challenge. While existing approaches integrate Large Language Models (LLMs) for semantic understanding and Deep Reinforcement Learning (DRL) for policy optimization, they often rely on sequential, loosely coupled architectures that underutilize the generative and reasoning capabilities of LLMs. In this paper, we propose a paradigm shift with PASE, a Planning-Aware Semantic self-healing engine, a novel fault self-healing framework that reconceptualizes recovery as a neuro-symbolic program synthesis task. PASE employs an LLM as a core Plan Synthesis Engine to generate structured recovery plans from a library of semantic primitives. A Neural-Symbolic World Model verifies plan feasibility through simulation, while a Meta-Prompt Optimizer, trained via DRL, learns to generate optimal prompts that guide the LLM's planning process. This tight reason-plan-verify-adapt loop enables dynamic, context-aware recovery strategy generation beyond predefined action spaces. Experiments on a real-world cloud fault injection dataset demonstrate that PASE significantly outperforms state-of-the-art methods, reducing average system recovery time by over 40% and improving fault detection accuracy in unknown fault scenarios. Our framework advances autonomous system management by unifying LLM-based reasoning with model-assisted verification and meta-learned guidance.
