Metraipolis › archive › dc_22bddadf8754
LangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial Optimization — arXiv:2610.23190
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.23190
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:43:10.167Z
- SHA-256 of the archived text
86727d8d6087b435fad19098a2c9280ea90999070bf001345e596a500fa5f0c0- Stable URL of this page
https://metraipolis.com/documento/dc_22bddadf8754
How to cite
LangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial Optimization — arXiv:2610.23190 — arXiv (en), https://arxiv.org/abs/2610.23190 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_22bddadf8754 (Metraipolis archive dc_22bddadf8754, sha256 86727d8d6087b435fad19098a2c9280ea90999070bf001345e596a500fa5f0c0)
BibTeX
@misc{dc22bddadf8754,
title = {LangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial Optimization — arXiv:2610.23190},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.23190},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_22bddadf8754; sha256 86727d8d6087b435fad19098a2c9280ea90999070bf001345e596a500fa5f0c0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23190. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neural combinatorial optimization (NCO) rapidly produces high-quality solutions for problem structures encountered during training, but operational requirements may change after deployment and be communicated in natural language. We propose LangNCO, a framework that compiles instance-specific requirements into structured inference-time interventions for a frozen NCO solver, without changing the pretrained policy's architecture, learned input representation, or parameters. A pretrained LLM serves as a replaceable semantic front end, translating each requirement into a schema-validated domain-specific language (DSL) rule set. A deterministic Rule Executor applies the rules as nonexpansive hard action masks. Because local masking prevents immediate violations but does not ensure that a complete feasible continuation remains reachable, Critical-Offset Decoding extracts rule-referenced critical nodes and reallocates part of a fixed rollout budget to multi-strength biased rollouts. Using controlled task-specific language to isolate solver adaptation from open-ended language robustness, we evaluate a CVRP policy on road closures, time windows, vehicle assignments, visit-order requirements, all pairwise combinations, and twelve additional constraint types. LangNCO achieves 100% feasibility on the four primary datasets with mean reference gaps of 1.63--3.26%, 97.33--100% feasibility when separately generated rules are composed for pairwise constraints, and 98.67% feasibility across the additional constraints. These results demonstrate modular post-training adaptation of a frozen NCO solver through inspectable language-derived rules, without retraining. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.23190 — 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 2026-10-19T08:39:10.145Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).