用视觉语言模型从网络草图生成优化代码，提升智能网络配置效率
Vision Language Models for Optimization-Driven Intent Processing in Autonomous Networks
- 基于网络草图和文本描述，让VLM生成可验证最优的网络优化代码
- 视觉输入使代码执行成功率下降12-21个百分点，闭源模型表现显著优于开源
- 首次构建覆盖17类问题的基准数据集，适合网络自动化与AI协同设计研究者
意图驱动网络（IBN）允许运营商以高层目标代替低层配置。现有工作表明大语言模型可自动化配置任务，但一类特定意图需生成优化代码以实现流量工程、路由和资源分配的可证明最优解。当前系统依赖文本表达意图，要求操作员以自然语言枚举拓扑与参数。网络实践者习惯通过图表理解结构，但视觉语言模型（VLMs）能否将标注的网络草图转化为正确优化代码尚无研究。本文提出IntentOpt基准，涵盖17类共85个优化问题，评估四种VLM（GPT-5-Mini、Claude-Haiku-4.5、Gemini-2.5-Flash、Llama-3.2-11B-Vision）在三种提示策略下对多模态与纯文本输入的表现。结果表明，视觉参数提取导致执行成功率下降12-21个百分点，如GPT-5-Mini从93%降至72%；思维链提示使性能最多下降13个百分点；开源模型显著落后，Llama-3.2-11B-Vision仅达18%，而GPT-5-Mini达75%。这些结果确立了当前VLM在IBN中生成优化代码的能力与局限。案例研究还证明了通过模型上下文协议将VLM生成代码部署至网络测试床的可行性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。