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

2026-03-06

AI Summary

This work addresses the challenges of high latency, excessive energy consumption, and error accumulation in multi-round task execution on resource-constrained mobile agents—such as edge robots and drones—operating under intermittent connectivity. The authors propose a knowledge-driven lightweight inference framework that leverages the DIKW (Data-Information-Knowledge-Wisdom) hierarchy to construct categorized representations of observations, trajectories, and cross-task knowledge. A compact knowledge packet synchronization mechanism is designed and integrated into on-device large-model inference. The study reveals a non-monotonic relationship between knowledge exposure and system performance, enabling an effective trade-off between inference acceleration and failure risk. Experiments in drone scenarios demonstrate that even small-scale knowledge packets enable a 3B-parameter onboard model to achieve 100% task reliability, with significantly lower inference costs compared to purely local inference or cloud-based replanning approaches.

Technology Category

• Multiagent Systems: Modeling other Agents
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Mobile Agentic AI
• Resource-constrained Platforms
• Intermittent Connectivity
• On-device Reasoning
• Knowledge-driven Reasoning

Innovation

• knowledge-driven reasoning
• mobile agentic AI
• SWAP-C constraints
• intermittent connectivity
• cross-task knowledge