# Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Model

arXiv: https://arxiv.org/abs/2607.01595 · HTML: https://mlsanity.com/paper/2607.01595/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 22 of 22)

- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [ComposerX: Multi-Agent Symbolic Music Composition with LLMs](https://mlsanity.com/paper/2404.18081/) (2024)
- [Advances in APPFL: A Comprehensive and Extensible Federated Learning Framework](https://mlsanity.com/paper/2409.11585/) (2024)
- [GUI Agents for Continual Game Generation](https://mlsanity.com/paper/2605.28258/) (2026)
- [Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies](https://mlsanity.com/paper/2508.10523/) (2025)
- [MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systems](https://mlsanity.com/paper/2605.25002/) (2026)
- [HADES: Hardware Accelerated Decoding for Efficient Speculation in Large Language Models](https://mlsanity.com/paper/2412.19925/) (2024)
- [T-GAE: Transferable Graph Autoencoder for Network Alignment](https://mlsanity.com/paper/2310.03272/) (2023)
- [GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation](https://mlsanity.com/paper/2410.08475/) (2024)
- [Adaptive Fault Tolerance Mechanisms of Large Language Models in Cloud Computing Environments](https://mlsanity.com/paper/2503.12228/) (2025)
- [Research on Large Language Model Cross-Cloud Privacy Protection and Collaborative Training based on Federated Learning](https://mlsanity.com/paper/2503.12226/) (2025)
- [Cloud-Based AI Systems: Leveraging Large Language Models for Intelligent Fault Detection and Autonomous Self-Healing](https://mlsanity.com/paper/2505.11743/) (2025)
- [STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning](https://mlsanity.com/paper/2606.15866/) (2026)
- [Towards Foundation-model-based Multiagent System to Accelerate AI for Social Impact](https://mlsanity.com/paper/2412.07880/) (2024)
- [Cross-Cloud Data Privacy Protection: Optimizing Collaborative Mechanisms of AI Systems by Integrating Federated Learning and LLMs](https://mlsanity.com/paper/2505.13292/) (2025)
- [Designing Large Foundation Models for Efficient Training and Inference: A Survey](https://mlsanity.com/paper/2409.01990/) (2024)
- [A Stochastic GDA Method With Backtracking For Solving Nonconvex Concave Minimax Problems](https://mlsanity.com/paper/2403.07806/) (2024)
- [Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering Systems](https://mlsanity.com/paper/2503.15454/) (2025)
- [AGDA+: Proximal Alternating Gradient Descent Ascent Method with a Nonmonotone Adaptive Step-Size Search for Nonconvex Minimax Problems](https://mlsanity.com/paper/2406.14371/) (2024)
- [GraphSnapShot: Caching Local Structure for Fast Graph Learning](https://mlsanity.com/paper/2406.17918/) (2024)
- [From Critique to Clarity: A Pathway to Faithful and Personalized Code Explanations with Large Language Models](https://mlsanity.com/paper/2501.14731/) (2024)

## Abstract (arXiv)

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.