受生物自愈启发，实现分布式系统故障自修复。
Bio-inspired Agentic Self-healing Framework for Resilient Distributed Computing Continuum Systems
- 用语言模型驱动的智能体模拟生物修复四阶段，自动处理故障。
- 在数十秒内完成自愈，仅需10%以上代理CPU资源。
- 适合高动态、异构的物联网与云协同系统使用。
人类生物系统通过持续检测损伤、协调针对性响应并自我修复维持生命。受此启发，本文提出ReCiSt框架，用于提升分布式计算连续体系统（DCCS）的韧性。现代DCCS融合从资源受限的物联网设备到高性能云基础设施的异构算力，其复杂性、移动性及动态运行条件易引发频繁故障，破坏服务连续性。亟需可扩展、自适应、自调控的韧性策略。ReCiSt将生物修复的止血、炎症、增殖和重塑四个阶段重构为计算层的隔离、诊断、元认知与知识层，由语言模型（LM）驱动的智能体在各层实现故障隔离、因果诊断、自适应恢复与长期知识沉淀。这些智能体能解析异构日志、推断根本原因、优化推理路径，并以最小人工干预重配置资源。在公开故障数据集上，使用多种语言模型评估了ReCiSt框架，因缺乏相似基线方法，未进行对比。结果表明，无论采用何种语言模型，系统均能在数十秒内完成自愈，且代理CPU使用率不低于10%，表现出对不确定性的深入分析能力以及实现韧性所需的微智能体数量。
原文摘要 · Abstract (English)
Human biological systems sustain life through extraordinary resilience, continually detecting damage, orchestrating targeted responses, and restoring function through self-healing. Inspired by these capabilities, this paper introduces ReCiSt, a bio-inspired agentic self-healing framework designed to achieve resilience in Distributed Computing Continuum Systems (DCCS). Modern DCCS integrate heterogeneous computing resources, ranging from resource-constrained IoT devices to high-performance cloud infrastructures, and their inherent complexity, mobility, and dynamic operating conditions expose them to frequent faults that disrupt service continuity. These challenges underscore the need for scalable, adaptive, and self-regulated resilience strategies. ReCiSt reconstructs the biological phases of Hemostasis, Inflammation, Proliferation, and Remodeling into the computational layers Containment, Diagnosis, Meta-Cognitive, and Knowledge for DCCS. These four layers perform autonomous fault isolation, causal diagnosis, adaptive recovery, and long-term knowledge consolidation through Language Model (LM)-powered agents. These agents interpret heterogeneous logs, infer root causes, refine reasoning pathways, and reconfigure resources with minimal human intervention. The proposed ReCiSt framework is evaluated on public fault datasets using multiple LMs, and no baseline comparison is included due to the scarcity of similar approaches. Nevertheless, our results, evaluated under different LMs, confirm ReCiSt's self-healing capabilities within tens of seconds with minimum of 10% of agent CPU usage. Our results also demonstrated depth of analysis to over come uncertainties and amount of micro-agents invoked to achieve resilience.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。