Research

Paper

AI LLM March 06, 2026

Knowledge-driven Reasoning for Mobile Agentic AI: Concepts, Approaches, and Directions

Authors

Guangyuan Liu, Changyuan Zhao, Yinqiu Liu, Dusit Niyato, Biplab Sikdar

Abstract

Mobile agentic AI is extending autonomous capabilities to resource-constrained platforms such as edge robots and unmanned aerial vehicles (UAVs), where strict size, weight, power, and cost (SWAP-C) constraints and intermittent wireless connectivity limit both on-device computation and cloud access. Existing approaches mostly optimize per-round communication efficiency, yet mobile agents must sustain competence across a stream of tasks. We propose a knowledge-driven reasoning framework that extracts reusable decision structures from past execution, synchronizes them over bandwidth-limited links, and injects them into on-device reasoning to reduce latency, energy, and error accumulation. A DIKW-inspired taxonomy distinguishes raw observations, episode-scoped traces, and persistent cross-task knowledge, and categorizes knowledge into retrieval, structured, procedural, and parametric representations, each with a distinct tradeoff between reasoning speedup and failure risk. A key finding is that knowledge exposure is non-monotonic: too little forces costly trial-and-error replanning, while too much introduces conflicting cues and errors. A UAV case study validates the framework, where a compact knowledge pack synchronized over intermittent backhaul enables a 3B-parameter onboard model to achieve perfect mission reliability with lower reasoning cost than both knowledge-free on-device reasoning and cloud-centric replanning.

Metadata

arXiv ID: 2603.05831
Provider: ARXIV
Primary Category: cs.DC
Published: 2026-03-06
Fetched: 2026-03-09 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.05831v1</id>\n    <title>Knowledge-driven Reasoning for Mobile Agentic AI: Concepts, Approaches, and Directions</title>\n    <updated>2026-03-06T02:28:22Z</updated>\n    <link href='https://arxiv.org/abs/2603.05831v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.05831v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Mobile agentic AI is extending autonomous capabilities to resource-constrained platforms such as edge robots and unmanned aerial vehicles (UAVs), where strict size, weight, power, and cost (SWAP-C) constraints and intermittent wireless connectivity limit both on-device computation and cloud access. Existing approaches mostly optimize per-round communication efficiency, yet mobile agents must sustain competence across a stream of tasks. We propose a knowledge-driven reasoning framework that extracts reusable decision structures from past execution, synchronizes them over bandwidth-limited links, and injects them into on-device reasoning to reduce latency, energy, and error accumulation. A DIKW-inspired taxonomy distinguishes raw observations, episode-scoped traces, and persistent cross-task knowledge, and categorizes knowledge into retrieval, structured, procedural, and parametric representations, each with a distinct tradeoff between reasoning speedup and failure risk. A key finding is that knowledge exposure is non-monotonic: too little forces costly trial-and-error replanning, while too much introduces conflicting cues and errors. A UAV case study validates the framework, where a compact knowledge pack synchronized over intermittent backhaul enables a 3B-parameter onboard model to achieve perfect mission reliability with lower reasoning cost than both knowledge-free on-device reasoning and cloud-centric replanning.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.DC'/>\n    <published>2026-03-06T02:28:22Z</published>\n    <arxiv:primary_category term='cs.DC'/>\n    <author>\n      <name>Guangyuan Liu</name>\n    </author>\n    <author>\n      <name>Changyuan Zhao</name>\n    </author>\n    <author>\n      <name>Yinqiu Liu</name>\n    </author>\n    <author>\n      <name>Dusit Niyato</name>\n    </author>\n    <author>\n      <name>Biplab Sikdar</name>\n    </author>\n  </entry>"
}