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

TL;DR

This paper proposes 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, and casts agent design as a program search problem and solves it with a domain-adapted Monte Carlo Tree Search (MCTS) algorithm.

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.

Figures (7)

• Figure 1: System overview: from WirelessAgent (manual design) to WirelessAgent++ (automated design). Left: in WirelessAgent, a human expert iteratively designs a fixed agentic workflow through multi-round dialogue with an LLM. Right: in WirelessAgent++, an Optimizer LLM jointly searches over the workflow structure and tool-calling strategy; the resulting workflow is executed by an Executor LLM on WirelessBench, automatically producing distinct, task-adaptive workflows (e.g., Q&A, network slicing (NS), and mobile service assurance (MSA)) without manual engineering.
• Figure 2: The overall architecture of WirelessAgent++, comprising three components. Search Space: each workflow node contains fixed parameters and optimizable prompts, composed from a library of operators and domain-specific tools. Search Algorithm: an MCTS-based optimizer iterates through four phases: penalized Boltzmann probability selection, LLM-based expansion, executing evaluation, and experience backpropagation, using an advanced Optimizer LLM for expansion and a cost-efficient Executor LLM for evaluation. WirelessBench: example task-adaptive workflows automatically discovered for WCHW, WCNS, and WCMSA, each exhibiting distinct operator compositions and tool-calling patterns.
• Figure 3: Method comparison on the test dataset of the WCHW benchmark. WirelessAgent++ outperforms the AFlow and all prompting baselines.
• Figure 4: Workflow evolution of WirelessAgent++ on the validation dataset of the WCHW benchmark.
• Figure 5: WCNS case study. (a) Overall composite score comparison across methods. (b) Per-metric breakdown: WirelessAgent++ achieves $\geq$89% on all four sub-metrics. (c) Workflow evolution on the validation set showing the three-phase optimization trajectory.

Theorems & Definitions (4)

• Definition 1: Operator
• Remark 1: Two Tool-Invocation Modes
• Remark 2
• Remark 3