Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey
- URL: http://arxiv.org/abs/2510.00078v1
- Date: Tue, 30 Sep 2025 02:37:52 GMT
- Title: Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey
- Authors: Sicong Liu, Weiye Wu, Xiangrui Xu, Teng Li, Bowen Pang, Bin Guo, Zhiwen Yu,
- Abstract summary: Foundation models have reshaped AI by unifying fragmented architectures into scalable backbones with multimodal reasoning and contextual adaptation.<n>With FMs as their cognitive core, agents transcend rule-based behaviors to achieve autonomy, generalization, and self-reflection.<n>This survey provides the first systematic characterization of adaptive, resource-efficient agentic AI systems.
- Score: 11.537225726120495
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Foundation models have reshaped AI by unifying fragmented architectures into scalable backbones with multimodal reasoning and contextual adaptation. In parallel, the long-standing notion of AI agents, defined by the sensing-decision-action loop, is entering a new paradigm: with FMs as their cognitive core, agents transcend rule-based behaviors to achieve autonomy, generalization, and self-reflection. This dual shift is reinforced by real-world demands such as autonomous driving, robotics, virtual assistants, and GUI agents, as well as ecosystem advances in embedded hardware, edge computing, mobile deployment platforms, and communication protocols that together enable large-scale deployment. Yet this convergence collides with reality: while applications demand long-term adaptability and real-time interaction, mobile and edge deployments remain constrained by memory, energy, bandwidth, and latency. This creates a fundamental tension between the growing complexity of FMs and the limited resources of deployment environments. This survey provides the first systematic characterization of adaptive, resource-efficient agentic AI systems. We summarize enabling techniques into elastic inference, test-time adaptation, dynamic multimodal integration, and agentic AI applications, and identify open challenges in balancing accuracy-latency-communication trade-offs and sustaining robustness under distribution shifts. We further highlight future opportunities in algorithm-system co-design, cognitive adaptation, and collaborative edge deployment. By mapping FM structures, cognition, and hardware resources, this work establishes a unified perspective toward scalable, adaptive, and resource-efficient agentic AI. We believe this survey can help readers to understand the connections between enabling technologies while promoting further discussions on the fusion of agentic intelligence and intelligent agents.
Related papers
- Agentic Wireless Communication for 6G: Intent-Aware and Continuously Evolving Physical-Layer Intelligence [22.740040535858327]
Large language models (LLMs) provide a promising foundation for intent-aware network agents.<n>This paper investigates agentic AI for the 6G physical layer and its realization pathways.<n>We present a case study of an intent-driven link decision agent, termed AgenCom, which adaptively constructs communication links under diverse user preferences.
arXiv Detail & Related papers (2026-02-19T05:36:27Z) - Communications-Incentivized Collaborative Reasoning in NetGPT through Agentic Reinforcement Learning [12.904732640630014]
We propose a unified agentic NetGPT framework for AI-native xG networks.<n>A NetGPT core can either perform autonomous reasoning or delegate sub-tasks to domain-specialized agents via agentic communication.<n>The framework establishes clear responsibilities and interoperable, enabling scalable, distributed intelligence across the network.
arXiv Detail & Related papers (2026-01-31T15:07:11Z) - Towards 6G Native-AI Edge Networks: A Semantic-Aware and Agentic Intelligence Paradigm [85.7583231789615]
6G positions intelligence as a native network capability, transforming the design of radio access networks (RANs)<n>Within this vision, Semantic-native communication and agentic intelligence are expected to play central roles.<n>Agentic intelligence endows distributed RAN entities with goal-driven autonomy, reasoning, planning, and multi-agent collaboration.
arXiv Detail & Related papers (2025-12-04T03:09:33Z) - Pinching Antennas Meet AI in Next-Generation Wireless Networks [95.7524555556776]
Next-generation (NG) wireless networks must embrace innate intelligence in support of emerging applications.<n>This article explores the "win-win" cooperation between AI and Pinching antennas (PAs)
arXiv Detail & Related papers (2025-11-03T21:32:00Z) - Semantic-Driven AI Agent Communications: Challenges and Solutions [25.74271088658268]
This article proposes a semantic-driven AI agent communication framework and develops three enabling techniques.<n>First, semantic adaptation transmission applies fine-tuning with real or generative samples to efficiently adapt models to varying environments.<n>Second, semantic lightweight transmission incorporates pruning, quantization, and perception-aware sampling to reduce model complexity and alleviate computational burden on edge agents.<n>Third, semantic self-evolution control employs distributed hierarchical decision-making to optimize multi-dimensional resources, enabling robust multi-agent collaboration in dynamic environments.
arXiv Detail & Related papers (2025-10-01T00:52:37Z) - A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence [87.08051686357206]
Large Language Models (LLMs) have demonstrated strong capabilities but remain fundamentally static.<n>As LLMs are increasingly deployed in open-ended, interactive environments, this static nature has become a critical bottleneck.<n>This survey provides the first systematic and comprehensive review of self-evolving agents.
arXiv Detail & Related papers (2025-07-28T17:59:05Z) - Agentic Web: Weaving the Next Web with AI Agents [109.13815627467514]
The emergence of AI agents powered by large language models (LLMs) marks a pivotal shift toward the Agentic Web.<n>In this paradigm, agents interact directly with one another to plan, coordinate, and execute complex tasks on behalf of users.<n>We present a structured framework for understanding and building the Agentic Web.
arXiv Detail & Related papers (2025-07-28T17:58:12Z) - AI Flow: Perspectives, Scenarios, and Approaches [51.38621621775711]
We introduce AI Flow, a framework that integrates cutting-edge IT and CT advancements.<n>First, device-edge-cloud framework serves as the foundation, which integrates end devices, edge servers, and cloud clusters.<n>Second, we introduce the concept of familial models, which refers to a series of different-sized models with aligned hidden features.<n>Third, connectivity- and interaction-based intelligence emergence is a novel paradigm of AI Flow.
arXiv Detail & Related papers (2025-06-14T12:43:07Z) - AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges [3.7414278978078204]
This review critically distinguishes between AI Agents and Agentic AI, offering a structured, conceptual taxonomy, application mapping, and analysis of opportunities and challenges to clarify their divergent design philosophies and capabilities.
arXiv Detail & Related papers (2025-05-15T16:21:33Z) - Internet of Agents: Fundamentals, Applications, and Challenges [66.44234034282421]
We introduce the Internet of Agents (IoA) as a foundational framework that enables seamless interconnection, dynamic discovery, and collaborative orchestration among heterogeneous agents at scale.<n>We analyze the key operational enablers of IoA, including capability notification and discovery, adaptive communication protocols, dynamic task matching, consensus and conflict-resolution mechanisms, and incentive models.
arXiv Detail & Related papers (2025-05-12T02:04:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.