Metraipolis › archive › dc_273de9854997
Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations — arXiv:2609.03860
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03860
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T01:11:24.051Z
- SHA-256 of the archived text
b6c480683910013971c6af208a74ed98f7664664fb24b3886d18ee86c4209d83- Stable URL of this page
https://metraipolis.com/documento/dc_273de9854997
How to cite
Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations — arXiv:2609.03860 — arXiv (en), https://arxiv.org/abs/2609.03860 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_273de9854997 (Metraipolis archive dc_273de9854997, sha256 b6c480683910013971c6af208a74ed98f7664664fb24b3886d18ee86c4209d83)
BibTeX
@misc{dc273de9854997,
title = {Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations — arXiv:2609.03860},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03860},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_273de9854997; sha256 b6c480683910013971c6af208a74ed98f7664664fb24b3886d18ee86c4209d83},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03860. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retail supply chain operations rely on coupled decision modules that must adapt as requirements evolve. LLMs offer a natural-language interface for this task, but existing methods primarily focus on individual optimization models. Extending them to heterogeneous decision pipelines is challenging because a requirement may admit multiple intervention paths with different downstream effects. We formulate requirement-driven adaptation as the joint selection of an intervention route and an admissible module-level change, and propose a graph-constrained agentic framework in which domain agents expose admissible reformulation interfaces and a central processor searches over bounded intervention paths. Candidates are validated and compared using downstream KPIs. In collaboration with a large retail partner, we evaluate 100 warehouse requirements elicited from practitioner interviews, with GPT, Qwen, and DeepSeek as base LLMs. Relative to direct LLM reformulation, our framework improves correctness and end-to-end success across all three models, raising end-to-end success from 72--76% to 79--83%. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2609.03860 — 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 2026-10-17T00:28:02.882Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).