KPI2KVI: A Multi Agent Workflow for Calculating Key Value Indicators from Service Descriptions
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
Key Value Indicators (KVIs) provide a decision oriented view of a service by summarizing how operational performance translates into stakeholder value, risk, and outcomes. However, in many domains KVIs are difficult to compute in practice because they require selecting relevant KVI categories, defining measurable Key Performance Indicators (KPIs), collecting KPI values, and applying consistent calculation logic, all of which is typically performed manually and inconsistently from unstructured service documentation. This paper presents KPI2KVI, a tool that transforms a natural language service description into computed KVI estimates by orchestrating a deterministic multi agent workflow powered by Large Language Models (LLMs) that (i) elicits missing service context, (ii) extracts and finalizes relevant KVI categories from a taxonomy, (iii) generates service specific KPIs with units and descriptions, (iv) collects KPI values through an interactive dialogue and also supports intelligent estimation for KPI values that are unavailable, and (v) computes interval valued KVI outputs (minimum, exact, maximum) with traceable explanations for each KVI code. Simulations with representative service descriptions demonstrate that KPI2KVI consistently produces a complete end to end mapping from description to KVI intervals and provides transparent calculation narratives that support post hoc auditing and interactive advisory queries.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 8 of its 24 references that are in the map. First posted on arXiv 31 Mar 2026.
Builds on
8 of 24 references.
References · 8
- 2024ADROIT6G DAI-driven Open and Programmable Architecture for 6G Networkscited by 2
- 2025Service Registration, Indexing, Discovery & Selection; An Architectural Survey Toward a GenAI-Driven Futurecited by 2
- 2023Near-optimal Cloud-Network Integrated Resource Allocation for Latency-Sensitive B5Gcited by 1
- 2025Sustainability in Telecommunication Networks and Key Value Indicators: a Surveycited by 1
- 2025Semantic-Aware Dynamic and Distributed Power Allocation: a Multi-UAV Area Coverage Use Casecited by 1
- 2025A Novel Multiple Access Scheme for Heterogeneous Wireless Communications using Symmetry-aware Continual Deep Reinforcement Learningcited by 1
- 2025Deep Learning Based Service Composition in Integrated Aerial-Terrestrial Networkscited by 1
- 2025Adaptive Multiple Access and Service Placement for Generative Diffusion Modelscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026ATLAS: Dual-Horizon Diagnostic Evaluation for Industrial Tool-Use Agents
- 2026SAGE: A Service Agent Graph-guided Evaluation Benchmark
- 2026Business Utility of Large Language Models as Exploratory Data Analysis Agents
- 2026CirrusBench: Evaluating LLM-based Agents Beyond Correctness in Real-World Cloud Service Environments
- 2026WorkflowPerturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics
- 2026Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflows
- 2026Salesforce Koa: An Enterprise Language Model for Agentic Tool Use
- 2026MicroAgent: Context-Augmented Multi-Agent Framework for Automatic Microservice Decomposition