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

STRIDE: A Systematic Framework for Selecting AI Modalities—Agentic AI, AI Assistants, or LLM Calls Shubhi Asthana1, Bing Zhang1, Chad DeLuca1, Ruchi Mahindru2, Hima Patel3 1IBM Research – Almaden, CA, USA 2IBM Research – Yorktown, NY, USA 3IBM Research – India {sasthan, delucac}@us.ibm.com, bing.zhang@ibm.com, rmahindr@us.ibm.com, himapatel@in.ibm.com 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 Evalua- tor), 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, dy- namism 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 un- necessary 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 au- tonomy. This work reframes agent adoption as a necessity-driven design decision, ensuring autonomy is applied only when its benefits justify the costs. 1 Introduction Recent advances have transformed AI from simple stateless LLM calls to sophisticated autonomous agents, enabling richer reasoning, tool use, and adaptive workflows. While this progression unlocks significant value in domains such as site reliability engineering (SRE), compliance, and automation, it also introduces substantial trade-offs in cost, complexity, and risk. A central design challenge emerges: when agents are truly necessary, and when are simpler alternatives sufficient? We distinguish three modalities: (i) LLM calls, providing single-turn inference without memory or tools, which is ideal for straightforward query-response scenarios; (ii) AI assistants, which handle guided multi-step workflows with short-term context and limited tool access that is suitable for structured processes requiring human oversight; and (iii) Agentic AI, which autonomously decomposes tasks, orchestrates tools, and adapts with minimal oversight, which is necessary for complex, dynamic environments requiring independent decision-making. Table 1 contrasts these modalities. Current practice often overuses agentic AI, deploying autonomous systems even when simpler modalities would suffice. This tendency leads to unnecessary cost, complexity, and risk, particularly 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: LAW - Bridging Language, Agent, and World Models. arXiv:2512.02228v1 [cs.AI] 1 Dec 2025 Table 1: Comparison of AI Modalities Attribute LLM Call AI Assistant Agentic AI Reasoning Depth Shallow Medium Deep Tool Needs Single Single/Multiple Multiple State Needs None Ephemeral Persistent Risk Profile Low Medium High Use Case Example Exchange rate lookup Summarize meeting notes Plan 5-day travel itinerary in enterprise contexts where reliability and governance are critical. A principled framework for deciding when agents are truly necessary has been missing, leaving design-time choices largely intuition-driven rather than evidence-based. While agentic AI unlocks transformative value in domains like SRE, compliance verification, and complex automation, deploying it indiscriminately carries risks: • Overengineering: using agents for simple queries wastes compute and developer effort. • Security & compliance risks: uncontrolled tool use and API calls may leak sensitive data. • System instability: recursive loops and unbounded workflows degrade reliability. We propose STRIDE, a novel framework for necessity assessment at design time: systematically deciding whether a given task should be solved with an LLM call, an AI assistant, or agentic AI. STRIDE analyzes task descriptions across four integrated analytical dimensions: • Structured Task Decomposition: Tasks are decomposed into a directed acyclic graph (DAG) of subtasks, systematically breaking down objectives to reveal inherent complexity, interdependencies, and sequential reasoning requirements that distinguish simple queries from multi-step challenges. • Dynamic Reasoning and Tool-Interaction Scoring: STRIDE quantifies reasoning depth together with tool dependencies, external data access, and API requirements, identifying when sophisti

…(Full text truncated)…

This content is AI-processed based on ArXiv data.