Beyond State Machines: Executing Network Procedures with Agentic Tool-Calling Sequences
Purna Sai Garigipati, Onur Ayan, Kishor Chandra Joshi, Xueli An

TL;DR
This paper explores how large language models can execute network procedures via tool sequences, analyzing different approaches, their latency, correctness, and reliability limits in complex workflows.
Contribution
It introduces a systematic analysis of LLM-based network procedure execution, compares multiple approaches, and presents a new error taxonomy for failure analysis.
Findings
Approaches with encapsulated procedures reduce latency and errors.
Advanced tool-calling models maintain reliability over longer procedures.
All models show reliability degradation as procedure length increases.
Abstract
Agentic AI will be an essential enabling technology for designing future mobile communication systems, which could provide flexible and customized services, automate complex network operations, and drive autonomous decision-making across the network. This work studies how Large Language Model (LLM)-based network AI agents can be utilized to execute network procedures expressed as sequences of tool invocations. We investigate four approaches, which differ in how the agent obtains the procedure and in how execution is distributed between the agent and the underlying tools. We evaluated the latency and execution correctness across these approaches using a User Equipment (UE) IP allocation procedure as a case study. Furthermore, we conduct a stress test to examine how many sequential procedural steps an LLM agent can reliably execute before failure. Our results show that approaches relying…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
