Metraipolis › archive › dc_3b09ef2a4359

Understanding Decision-Making Mechanisms in Neural Routing Solvers — arXiv:2609.36063

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36063
License (as archived)
CC0-1.0
Archived
2026-10-07T16:25:13.396Z
SHA-256 of the archived text
6cd3dcaa50e9ac01b8773cd7752cadab91350adc65879e9f2657c6133cbfe27d
Stable URL of this page
https://metraipolis.com/documento/dc_3b09ef2a4359

How to cite

Understanding Decision-Making Mechanisms in Neural Routing Solvers — arXiv:2609.36063 — arXiv (en), https://arxiv.org/abs/2609.36063 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3b09ef2a4359 (Metraipolis archive dc_3b09ef2a4359, sha256 6cd3dcaa50e9ac01b8773cd7752cadab91350adc65879e9f2657c6133cbfe27d)
BibTeX
@misc{dc3b09ef2a4359,
  title = {Understanding Decision-Making Mechanisms in Neural Routing Solvers — arXiv:2609.36063},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36063},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3b09ef2a4359; sha256 6cd3dcaa50e9ac01b8773cd7752cadab91350adc65879e9f2657c6133cbfe27d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36063. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural Combinatorial Optimization (NCO) has achieved strong empirical success, yet the internal mechanisms driving model decisions remain largely unexplored. In this paper, we investigate three representative autoregressive NCO models spanning two encoder-decoder configurations: AM and POMO (heavy-encoder, light-decoder), and LEHD (light-encoder, heavy-decoder). Through behavioral analyses, representation probing, and causal interventions, we examine how these models construct solutions and use internal representations during decoding. Our results suggest that AM and POMO predominantly follow a persistent geometric pattern throughout solution construction, whereas LEHD contains linearly accessible information about multiple future actions. Causal experiments further provide evidence for the role of future-node representations in LEHD's decision-making. We also observe that LEHD relies strongly on the current-node representation for immediate local decisions, while the start-node representation plays a broader navigational role over the subsequent route. Cross-instance alignment analyses additionally indicate that LEHD maps current-node representations into a relatively shared latent region, which may provide a stable reference for evaluating subsequent decisions. Across the Traveling Salesman Problem and the Capacitated Vehicle Routing Problem, these results reveal distinct decision-making patterns across these architecturally distinct solvers and provide a foundation for more interpretable analyses of NCO solvers. Code and additional visualizations are provided in the this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.36063 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T15:54:53.763Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).