mlsanityData to 14 Oct 2026

Self-evolving network verifiers

arXiv 2608.11340 ↗First posted 11 Aug 2026cs.NI cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Symbolic network verifiers can reason about correctness across vast spaces of routing inputs and failures, but only for the protocols and features an expert has encoded by hand. Creating and maintaining a faithful model of the control plane is both difficult and never-ending, since no written source specifies perfectly what a network does: vendor implementations deviate from the RFCs, and behaviour shifts with releases. The burden of constant upkeep ultimately keeps verification out of many networks that need it. We argue that the model should instead evolve automatically to faithfully capture the actual network behaviour. To achieve that, we leverage the only source that specifies it unambiguously: the router software itself. In a counterexample-guided loop, a coding agent proposes extensions to the verifier's symbolic encoding, while a trusted oracle (e.g., emulated routers) supplies the ground-truth routing state. The agent iteratively refines the network model using each disagreement with the oracle. As early evidence, a prototype of this system taught a 3,000-line SMT-based verifier three features it did not support: OSPF areas, BGP route reflection, and L3VPN over EVPN, converging autonomously on models that match the oracle, even noticing vendor-specific behaviour. Automating model growth shifts the hard problem from writing verification systems to systematically testing them; we propose a research agenda for trusting and harnessing automatically evolved verifiers.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 5 of its 34 references that are in the map. First posted on arXiv 11 Aug 2026.

Builds on

5 of 34 references.

References · 5

  1. 2015A Theory of Formal Synthesis via Inductive Learningcited by 17
  2. 2026Event-B Agent: Towards LLM Agent for Formal Model Synthesis and Repaircited by 3
  3. 2018Control Plane Compressioncited by 1
  4. 2023Eywa: Automating Model Based Testing using LLMscited by 1
  5. 2026AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systemscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough
  2. 2026Let AI Agents Translate Networks, Not Reason About Them
  3. 2022Modular Control Plane Verification via Temporal Invariants ↗
  4. 2026Task- and Session-Level Model Routing: A Common-Interface Hybrid Evaluation of Four Open-Source Routers Across Four Benchmarks
  5. 2026Aether: Network Validation Using Agentic AI and Digital Twin
  6. 2026The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering
  7. 2026The Replay Gap: Static Evaluation of Model Switching in LLM Agents Scores the Wrong World
  8. 2026NetAgentBench: A State-Centric Benchmark for Evaluating Agentic Network Configuration