eess.SYNov 16, 2026

Implicit-Reasoning-Enabled Elastic Semantic Communications for AI-Agent Networks

Authors: Kaiwen Yu, Gang Wu, Jiancun Fan, Saviour Zammit

Organizations: National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu 611731, China · Tianfu Jiangxi Laboratory, Chengdu, China · School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China · Department of Communications and Computer Engineering, University of Malta, MSD 2080 Msida, Malta

Abstract

AI-agent networks introduce new communication demands driven by proactive interactions and autonomous task execution. Existing adaptive semantic communication schemes primarily adjust semantic representations and resource configurations within predefined processing scales and capability sets, which may be insufficient for evolving task requirements. To address this gap, we introduce elastic semantic communications (ESC), a task-driven framework that extends semantic adaptation to the runtime execution and participation of task-supporting capabilities. ESC comprises two complementary dimensions: vertical elasticity adjusts the execution intensity of existing capabilities, while horizontal elasticity reconfigures the participating capability set. The framework connects these dimensions through the expected marginal value of additional information and computation. To realize ESC, we propose an implicit-reasoning-enabled device--edge mechanism that supports variable-depth local inference through shared-parameter state updates and edge-side continuation through wireless transfer of intermediate reasoning states. Experiments on Sudoku-Extreme demonstrate that the benefits of additional inference depend on wireless conditions, while task-aware edge invocation can preserve task accuracy with substantially lower state-transfer overhead.

Figures & tables

Explore similar work

May 7, 2026

SANEmerg: An Emergent Communication Framework for Semantic-aware Agentic AI Networking

Future networking systems are envisioned to become part of an agentic AI-native ecosystem in which a vast number of heterogeneous and specialized AI agents cooperate seamlessly to fulfill complex user requirements in real time. However, traditional networking paradigms are characterized by a rigid decoupling of communication and computation, which often leads to significant inefficiencies in large-scale agentic AI networking (AgentNet) systems. Emergent communication offers a novel solution by enabling autonomous agents that support task-specific signaling protocols for information exchange and collaborative coordination. In this paper, we consider a multi-agent emergent communication framework, tailored for semantic-aware AgentNet systems in which the user's semantic intent can be automatically detected, inferred, and linked to a set of sub-tasks to be assigned to a set of agents. We investigate how communication and signaling protocols can emerge among collaborative agents with computationally bounded intelligence under stringent bandwidth constraints. Our proposed framework, called SANEmerg, is designed to facilitate the emergence of communication for collaborative task fulfillment while adhering to the physical limits of AgentNet. SANEmerg incorporates a bandwidth-adaptable importance-filter that dynamically prioritizes the transmission of higher-contribution message dimensions, ensuring robust performance in bandwidth-limited environments. Furthermore, SANEmerg integrates a complexity-regularizer grounded in the Minimum Description Length (MDL) principle to facilitate the emergence of computationally bounded signaling. Evaluated via an AgentNet prototype and extensive experimentation, SANEmerg demonstrates significant performance improvements over state-of-the-art solutions, achieving superior task accuracy while significantly reducing bandwidth and computational overhead.
Oct 6, 2026

Agentic Semantic Sensing for Resource-Adaptive AI-RAN

Semantic sensing (SemS) acquires task-relevant information rather than reconstructing complete physical information. Existing SemS formulations typically operate open loop: sensing configurations and observation schedules are fixed before inference and cannot respond to evolving task-level evidence. We propose Agentic SemS, a closed-loop framework for AI-enabled radio access networks (AI-RANs) that controls sensing within a communication-feasible profile set. A profile-conditioned causal Transformer updates the semantic belief from streaming observations, while key-value caching enables efficient state updates across profile changes without repeatedly processing the complete history. A semantic utility network estimates the task-level benefit of acquiring the next observation block under each feasible profile after accounting for sensing cost. The resulting continuation utilities jointly support next-profile selection and semantic early exit, adapting sensing configuration and duration to evolving evidence. The expected semantic gain is further related to conditional mutual information, providing a value-of-information interpretation of continued online sensing. Experiments on Widar3.0 with six emulated sensing profiles show that, in comparison with full-sequence High, the resource-efficient Agentic setting reduces normalized cumulative sensing cost by 25.33% while achieving 85.79% Macro-F1. At the same utility checkpoint, semantic early exit provides a further 12.35% cost reduction over adaptive sensing without early exit, with a 0.97-percentage-point Macro-F1 decrease.
Nov 17, 2026

Semantic Communication via Analog RF Computing: When the Radio Computes the Meaning

Semantic communication (SC) systems transmit continuous latent representations of meaning, but computing the semantic encoder at resource-constrained edge devices incurs substantial energy and memory costs. To address this challenge, we propose an end-to-end SC framework that executes the semantic encoder in the client's RF receiver front end using analog RF computing. A base station (BS) broadcasts encoder weights as RF waveforms, while each edge device reuses its receiver's passive mixer to compute semantic latents at ultra-low energy. These latents are transmitted over the uplink for network-side task inference. We show that analog computing noise across encoder layers and channel noise affecting transmitted latents admit a unified mathematical model. We define a task-posterior semantic distortion metric and derive its second-order decomposition into per-client, per-stage semantic sensitivities. Using this decomposition, we obtain a closed-form semantic-aware water-filling allocation of the total client energy budget across clients, encoder layers, and uplinks, assigning tighter accuracy targets to semantically sensitive stages. This allocation induces a broadcast beamforming problem that accounts for client-specific, per-layer accuracy requirements. We further refine the allocation through stochastic optimization and jointly design it with multi-task noise-aware training of the shared semantic model. MNIST simulations show that, at matched total client energy, the proposed allocation reduces network semantic distortion by 9.2%-19.2% compared with uniform precision and 5.1%-13.1% compared with client-blind allocation. Noise-aware co-design yields a further 46% reduction.