REVIEW 6 cited by
Making Network Configuration Human Friendly
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
This paper explores opportunities to utilize Large Language Models (LLMs) to make network configuration human-friendly, simplifying the configuration of network devices and minimizing errors. We examine the effectiveness of these models in translating high-level policies and requirements (i.e., specified in natural language) into low-level network APIs, which requires understanding the hardware and protocols. More specifically, we propose NETBUDDY for generating network configurations from scratch and modifying them at runtime. NETBUDDY splits the generation of network configurations into fine-grained steps and relies on self-healing code-generation approaches to better take advantage of the full potential of LLMs. We first thoroughly examine the challenges of using these models to produce a fully functional & correct configuration, and then evaluate the feasibility of realizing NETBUDDY by building a proof-of-concept solution using GPT-4 to translate a set of high-level requirements into P4 and BGP configurations and run them using the Kathar\'a network emulator.
Forward citations
Cited by 6 Pith papers
-
Automating Conflict-Aware ACL Configurations with Natural Language Intents
Xumi automates the full ACL configuration pipeline from natural language intents, reporting 90-98% rule translation accuracy, 3.33x more accurate conflict detection than overlap baselines, and about 40% fewer rule add...
-
Multi-User SLNR-Based Precoding With Gold Nanoparticles in Vehicular VLC Systems
Gold-nanoparticle decorrelation of LED channels plus optimized RGB ratios improves multi-user vehicular visible light communication rate and secrecy.
-
LLM-Based Config Synthesis requires Disambiguation
LLM-based incremental config synthesis needs user disambiguation of insertion placement; Clarify uses differential questions and binary search to resolve it.
-
FastRAG: Retrieval Augmented Generation for Semi-structured Data
FastRAG extracts entities from semi-structured network data by using an LLM to generate JSON schemas and Python parsers from sampled chunks, then answers queries with combined knowledge-graph and text search.
-
Mapping the Landscape of Generative AI in Network Monitoring and Management
A structured taxonomy of 189 works applying generative AI to network monitoring and management, grouped into traffic generation, classification, intrusion detection, log analysis, and digital assistance.
-
MoE$^2$: Optimizing Collaborative Inference for Edge Large Language Models
MoE2 trains a gating network once on all edge LLMs, then selects a resource-feasible subset and a per-prompt top-k of experts to fuse token probabilities under latency and energy budgets.
Discussion (0). Continue with ORCID to comment.