WirelessAgent++: Automated Agentic Workflow Design and Benchmarking for Wireless Networks

2026-02-28

AI Summary

This work addresses the limitations of existing manually designed agent workflows in wireless networks, which suffer from low efficiency, poor scalability, and suboptimal performance. To overcome these challenges, the authors propose a searchable procedural workflow representation that models workflows as executable code composed of modular operators, along with a domain-adapted Monte Carlo Tree Search (MCTS) algorithm to automatically optimize workflow structures. They also introduce WirelessBench, the first standardized benchmark for wireless network tasks, encompassing knowledge reasoning, tool invocation, and multi-step decision-making. Evaluated on WCHW, WCNS, and WCMSA tasks, the proposed method achieves accuracies of 78.37%, 90.95%, and 97.07%, respectively, with a per-task search cost under \$5, outperforming state-of-the-art prompting methods by 31% and general-purpose workflow optimizers by 11.1%.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Multiagent Systems: Teamwork

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

The integration of large language models (LLMs) into wireless networks has sparked growing interest in building autonomous AI agents for wireless tasks. However, existing approaches rely heavily on manually crafted prompts and static agentic workflows, a process that is labor-intensive, unscalable, and often suboptimal. In this paper, we propose WirelessAgent++, a framework that automates the design of agentic workflows for various wireless tasks. By treating each workflow as an executable code composed of modular operators, WirelessAgent++ casts agent design as a program search problem and solves it with a domain-adapted Monte Carlo Tree Search (MCTS) algorithm. Moreover, we establish WirelessBench, a standardized multi-dimensional benchmark suite comprising Wireless Communication Homework (WCHW), Network Slicing (WCNS), and Mobile Service Assurance (WCMSA), covering knowledge reasoning, code-augmented tool use, and multi-step decision-making. Experiments demonstrate that \wap{} autonomously discovers superior workflows, achieving test scores of $78.37\%$ (WCHW), $90.95\%$ (WCNS), and $97.07\%$ (WCMSA), with a total search cost below $\$ 5$ per task. Notably, our approach outperforms state-of-the-art prompting baselines by up to $31\%$ and general-purpose workflow optimizers by $11.1\%$, validating its effectiveness in generating robust, self-evolving wireless agents. The code is available at https://github.com/jwentong/WirelessAgent-R2.

Problem

• wireless networks
• large language models
• agentic workflows
• automated design
• benchmarking

Innovation

• Automated Agentic Workflow
• Program Search
• Domain-adapted MCTS
• WirelessBench
• Modular Operators