In a distributed Internet of Agents (IoA) without centralized routing control, routing tasks to capability-matched executors is challenging because destinations are not predetermined and agents have bounded local service views. Discover-then-forward approaches, by contrast, select an executor before network forwarding and therefore do not directly support reselection when additional candidates become visible downstream. We introduce Semantic Potential Field Routing (SPFR), a distributed IoA routing algorithm that integrates executor discovery and reselection into hop-by-hop forwarding. SPFR represents each executor visible in a local semantic forwarding information base (FIB) as a task-conditioned semantic potential source, with utility setting its strength and hop distance inducing exponential attenuation. At each hop, the forwarding agent recomputes these potentials, reselects the dominant executor, and forwards the task one hop toward it. Under task-consistent frozen-FIB conditions, we prove loop freedom and finite-hop termination and derive an explicit additive error bound under bounded visibility relative to the full-visibility objective. Extensive simulations on real-world topologies show that SPFR approaches the realized utility of distributed utility-greedy routing and request-triggered global discovery while using fewer forwarding hops and substantially fewer request-triggered messages, and remains robust under network and service dynamics.
Yeguang Qin, Liang-Qi Peng, Fengxiao Tang et al.· 0 citations
Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) systems provide flexible computing services for resource-constrained devices, but malicious jamming attacks introduce dynamic channel conditions and resource competition, making joint trajectory and resource optimization challenging. This paper investigates this problem in multi-UAV MEC systems under jamming, aiming to minimize delay and energy consumption while ensuring anti-jamming robustness. The problem is formulated as a decentralized partially observable Markov decision process (Dec-POMDP). However, traditional multi-agent reinforcement learning (MARL) approaches struggle with high exploration costs and low sampling efficiency in high-dimensional hybrid action spaces. To overcome these limitations, we propose an LLM-guided MARL framework instantiated with the multi-agent deep deterministic policy gradient (MADDPG), which leverages LLM-generated semantic trajectory prompts to dynamically constrain exploration within the continuous action space, effectively compressing the policy search space and accelerating convergence. Simulation results demonstrate that the proposed method achieves $3.4\times $ to $5\times $ faster convergence over hierarchical MADDPG, MADDPG, and independent soft actor-critic (ISAC) baselines, significantly reducing training costs while maintaining superior performance and anti-jamming robustness.
Yeguang Qin, Jie Tang, Fengxiao Tang et al.· IEEE Transactions on Communi...· 0 citations
