Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations
Abstract
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%.
Related
- The cost of ensembling: Is it always worth combining global retail forecasting models?
- AI-Mediation in Retail Markets: Revenue Effects and Assortment Optimization
- Adapting offline models to a streaming context for music source separation
- Adapting Linear-Time Architectures for Tabular In-Context Learning
- Adapting Pairs Trading to Gambling Markets A Case Study of the U.S. Presidential Election
BibTeX
@misc{zheng2026adapting,
title = {{Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations}},
author = {Lei Zheng and Liping Yang and Zihao Li and Guodong Lyu and Chaik Ming Koh and Chung-Piaw Teo},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.03860},
eprint = {2609.03860},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.03860},
}
RIS
TY - UNPB
TI - Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations
AU - Lei Zheng
AU - Liping Yang
AU - Zihao Li
AU - Guodong Lyu
AU - Chaik Ming Koh
AU - Chung-Piaw Teo
PY - 2026
DA - 2026/09/03
PB - arXiv
DO - 10.48550/arxiv.2609.03860
UR - https://arxiv.org/abs/2609.03860
AB - 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%.
ER -