Search papers, labs, and topics across Lattice.
This paper reformulates safe remediation in IT operations as a risk-constrained intervention decision problem, utilizing a Constrained Markov Decision Process (CMDP) to maximize repair success while controlling for a bounded false remediation rate (FRR). By introducing a three-dimensional risk decomposition and a context-adaptive human-in-the-loop (HITL) gate, the authors provide a more interpretable and responsive safety interface for operators. Experiments demonstrate that this approach significantly reduces FRR by 39% and improves repair success by 2.5 points, while also decreasing on-call escalation load by 17% compared to traditional methods.
Reducing false remediation rates by 39% while enhancing repair success reveals a new paradigm for safer automated interventions in IT operations.
In modern IT operations (IT-Ops), the cost of an incorrect repair often exceeds the cost of no action at all. Yet existing automated remediation systems are designed to generate actions rather than to decide whether intervention is warranted, leaving safety as an afterthought enforced by manual approval. This paper makes three contributions to close this gap: (i) we reformulate safe remediation as a risk-constrained intervention decision problem and cast it as a Constrained Markov Decision Process (CMDP), in which the agent maximizes repair success subject to a bounded false remediation rate (FRR); (ii) we introduce a three-dimensional risk decomposition comprising blast radius, reversibility, and epistemic uncertainty, providing operators with an interpretable per-action safety interface; and (iii) we design a context-adaptive human-in-the-loop (HITL) gate that turns escalation from a binary failsafe into a bandwidth-aware control layer responsive to on-call load and business criticality. The full policy is learned offline from historical incident logs, enabling explicit control of the expected FRR. Experiments on the Train Ticket microservice benchmark with Chaos Mesh fault injection and an RCAEval-aligned fault taxonomy show that our framework reduces FRR by 39% while improving repair success by 2.5 points over a strong runbook baseline, and reduces on-call escalation load by 17% relative to a fixed-threshold variant.
