STRIDE: A Systematic Framework for Selecting AI Modalities -- Agentic AI, AI Assistants, or LLM Calls

2025-12-01

AI Summary

AI modality selection lacks systematic, decision-theoretic foundations, leading to suboptimal deployment choices among stateless LLM calls, guided assistants, and autonomous agentic AI. Method: This paper proposes STRIDE—a framework that quantifies agent suitability via task dynamism attribution and reflexive requirement analysis—enabling cost-effectiveness–driven optimal modality selection. Contribution/Results: STRIDE shifts agent deployment from default practice to quantified design, introducing structured task decomposition, dynamic attribute identification, and self-reflective requirement modeling—the first such integration. Evaluated on 30 real-world tasks, it achieves 92% modality selection accuracy, reduces redundant agent deployments by 45%, and lowers computational resource costs by 37%. Validated over six months by domain experts, STRIDE demonstrates practical applicability and operational value.

Technology Category

• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

The rapid shift from stateless large language models (LLMs) to autonomous, goal-driven agents raises a central question: When is agentic AI truly necessary? While agents enable multi-step reasoning, persistent memory, and tool orchestration, deploying them indiscriminately leads to higher cost, complexity, and risk. We present STRIDE (Systematic Task Reasoning Intelligence Deployment Evaluator), a framework that provides principled recommendations for selecting between three modalities: (i) direct LLM calls, (ii) guided AI assistants, and (iii) fully autonomous agentic AI. STRIDE integrates structured task decomposition, dynamism attribution, and self-reflection requirement analysis to produce an Agentic Suitability Score, ensuring that full agentic autonomy is reserved for tasks with inherent dynamism or evolving context. Evaluated across 30 real-world tasks spanning SRE, compliance, and enterprise automation, STRIDE achieved 92% accuracy in modality selection, reduced unnecessary agent deployments by 45%, and cut resource costs by 37%. Expert validation over six months in SRE and compliance domains confirmed its practical utility, with domain specialists agreeing that STRIDE effectively distinguishes between tasks requiring simple LLM calls, guided assistants, or full agentic autonomy. This work reframes agent adoption as a necessity-driven design decision, ensuring autonomy is applied only when its benefits justify the costs.

Problem

• Selecting appropriate AI modalities for tasks
• Reducing unnecessary agent deployments and costs
• Distinguishing tasks needing simple vs. agentic AI

Innovation

• Framework STRIDE selects AI modalities systematically
• Integrates task decomposition and dynamism attribution analysis
• Reduces unnecessary agent deployments and resource costs