A Self-Defining Operator for Distributed Applications

A self-defining operator (SDO) that distills resolved incidents into reusable playbooks and telemetry-triggered detectors cut resolution time by 52% on recurring faults across 11 open-source microservice applications, according to an arXiv paper submitted 10 October 2026 by Shihang Li and revised 14 October 2026. The SDO runs detectors continuously and invokes LLMs only when a detector fires, so token cost scales with incident count rather than operational time. The system is open source at github.com/self-defining-systems/sdo.

Computer Science Distributed, Parallel, and Cluster Computing Submitted on 10 Oct 2026 v1 https://arxiv.org/abs/2610.14547v1 , last revised 14 Oct 2026 this version, v2 Title:A Self-Defining Operator for Distributed Applications View PDF https://arxiv.org/pdf/2610.14547 HTML experimental https://arxiv.org/html/2610.14547v2 Abstract:To operate distributed applications with high availability, operators must rapidly diagnose and mitigate any incident. LLM-based agents can help, but unlike experienced human operators they do not improve as they handle more incidents. Each investigation starts from scratch, re-deriving likely causes and re-testing hypotheses even when a similar fault was resolved in the past. We present a self-defining operator SDO that improves with time by updating its operational behavior and memory. When SDO resolves an incident, it distills that experience into playbooks, which describe reusable diagnostic instructions for future incidents with similar faults, and detectors, scripts that take application telemetry as input and output relevant playbook s . SDO continuously runs the detectors and invokes LLMs only when one fires, so its token cost scales with incident count rather than with operational time. Across 11 open-source microservice applications, SDO cuts resolution time by 52% on recurring faults while keeping per-incident cost low. SDO is open source at this https URL https://github.com/self-defining-systems/sdo . Submission history From: Shihang Li view email https://arxiv.org/show-email/87beba35/2610.14547 Sat, 10 Oct 2026 04:08:13 UTC 2,590 KB \ v1\ https://arxiv.org/abs/2610.14547v1 v2 Wed, 14 Oct 2026 06:00:51 UTC 2,590 KB Additional Features References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .