EUVIMEDSkopri EUVIMED
Open access · CC BY 4.0

Representing Search State to a Large Language Model: A Structured Telemetry Interface for Runtime Control of Adaptive Large Neighbourhood Search

Mehdi Raoofi, Julien Maheut, Flavio Tonelli

Systems · 2026-09-25 · 14 (10) · 1200

DOI: 10.3390/systems14101200 ↗

At a glance

Journal article in Systems, published online on 2026-09-25. Written by Mehdi Raoofi and 2 co-authors. Cited 1 times so far (Crossref); 53 references. The full text is freely available (open access, CC BY 4.0).

AstrattDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Adaptive large neighbourhood search is steered by high-level control decisions, yet its standard adaptation reacts to a narrow reward signal that conveys little about the state of the search. Recent work has strengthened this control with machine-learning and reinforcement-learning policies, but these generally require task-specific training. This paper proposes a framework in which a large language model acts as a bounded, training-free runtime supervisor of the search. The central contribution is a structured telemetry interface that compresses the evolving search into a compact, reproducible state representation over which the model can reason. The supervisor adjusts only search-control parameters and never modifies the solution, so construction, feasibility, and objective evaluation remain inside the metaheuristic. The framework is evaluated on a multi-depot capacitated vehicle routing problem with time windows on real city street networks, against conventional variants and two dedicated solvers. Under an equal iteration budget, the supervised algorithm reduces the mean gap to the best per-instance result from 2.93% to 0.18%, and its difference from the strongest dedicated solver is not statistically significant, although it runs at a higher computational cost. These results indicate that a language model can control metaheuristic search effectively when supported by a structured interface between the algorithm and the model.

Cite

APA

Raoofi, M., Maheut, J., & Tonelli, F. (2026). Representing Search State to a Large Language Model: A Structured Telemetry Interface for Runtime Control of Adaptive Large Neighbourhood Search. Systems, 14(10), 1200. https://doi.org/10.3390/systems14101200

Vancouver

Raoofi M, Maheut J, Tonelli F. Representing Search State to a Large Language Model: A Structured Telemetry Interface for Runtime Control of Adaptive Large Neighbourhood Search. Systems. 2026;14(10):1200. doi:10.3390/systems14101200

BibTeX
@article{Raoofi2026,
  author = {Raoofi, Mehdi and Maheut, Julien and Tonelli, Flavio},
  title = {Representing Search State to a Large Language Model: A Structured Telemetry Interface for Runtime Control of Adaptive Large Neighbourhood Search},
  journal = {Systems},
  year = {2026},
  volume = {14},
  number = {10},
  pages = {1200},
  doi = {10.3390/systems14101200}
}
Start for free →