Vision Language Models for Optimization-Driven Intent Processing in Autonomous Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ahmed, Tasnim, Zhu, Yifan, Choudhury, Salimur
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915737944195072
author Ahmed, Tasnim
Zhu, Yifan
Choudhury, Salimur
author_facet Ahmed, Tasnim
Zhu, Yifan
Choudhury, Salimur
contents Intent-Based Networking (IBN) allows operators to specify high-level network goals rather than low-level configurations. While recent work demonstrates that large language models can automate configuration tasks, a distinct class of intents requires generating optimization code to compute provably optimal solutions for traffic engineering, routing, and resource allocation. Current systems assume text-based intent expression, requiring operators to enumerate topologies and parameters in prose. Network practitioners naturally reason about structure through diagrams, yet whether Vision-Language Models (VLMs) can process annotated network sketches into correct optimization code remains unexplored. We present IntentOpt, a benchmark of 85 optimization problems across 17 categories, evaluating four VLMs (GPT-5-Mini, Claude-Haiku-4.5, Gemini-2.5-Flash, Llama-3.2-11B-Vision) under three prompting strategies on multimodal versus text-only inputs. Our evaluation shows that visual parameter extraction reduces execution success by 12-21 percentage points (pp), with GPT-5-Mini dropping from 93% to 72%. Program-of-thought prompting decreases performance by up to 13 pp, and open-source models lag behind closed-source ones, with Llama-3.2-11B-Vision reaching 18% compared to 75% for GPT-5-Mini. These results establish baseline capabilities and limitations of current VLMs for optimization code generation within an IBN system. We also demonstrate practical feasibility through a case study that deploys VLM-generated code to network testbed infrastructure using Model Context Protocol.
format Preprint
id arxiv_https___arxiv_org_abs_2601_12744
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Vision Language Models for Optimization-Driven Intent Processing in Autonomous Networks
Ahmed, Tasnim
Zhu, Yifan
Choudhury, Salimur
Artificial Intelligence
Networking and Internet Architecture
Software Engineering
Intent-Based Networking (IBN) allows operators to specify high-level network goals rather than low-level configurations. While recent work demonstrates that large language models can automate configuration tasks, a distinct class of intents requires generating optimization code to compute provably optimal solutions for traffic engineering, routing, and resource allocation. Current systems assume text-based intent expression, requiring operators to enumerate topologies and parameters in prose. Network practitioners naturally reason about structure through diagrams, yet whether Vision-Language Models (VLMs) can process annotated network sketches into correct optimization code remains unexplored. We present IntentOpt, a benchmark of 85 optimization problems across 17 categories, evaluating four VLMs (GPT-5-Mini, Claude-Haiku-4.5, Gemini-2.5-Flash, Llama-3.2-11B-Vision) under three prompting strategies on multimodal versus text-only inputs. Our evaluation shows that visual parameter extraction reduces execution success by 12-21 percentage points (pp), with GPT-5-Mini dropping from 93% to 72%. Program-of-thought prompting decreases performance by up to 13 pp, and open-source models lag behind closed-source ones, with Llama-3.2-11B-Vision reaching 18% compared to 75% for GPT-5-Mini. These results establish baseline capabilities and limitations of current VLMs for optimization code generation within an IBN system. We also demonstrate practical feasibility through a case study that deploys VLM-generated code to network testbed infrastructure using Model Context Protocol.
title Vision Language Models for Optimization-Driven Intent Processing in Autonomous Networks
topic Artificial Intelligence
Networking and Internet Architecture
Software Engineering
url https://arxiv.org/abs/2601.12744