Open Capacity Pooling in Agentic Supply Chains: Coordination-Directed LLM Discovery and Distributed Re-optimization
Abstract
Disruptions can leave logistics networks short of capacity, yet outside capacity is hard to use: incumbent models are private, provider records are incomplete, and offers stay hidden until a costly request for quotation (RFQ). We introduce open capacity pooling as a budgeted provider-discovery problem that links which capacity need to pursue, whom to contact, and which verified offer to admit. The alternating direction method of multipliers (ADMM) coordinates incumbents without sharing models, and the resulting capacity gaps direct discovery. A machine-learning layer fitted before search ranks providers by predicted capability and a fleet-size proxy from directory records and large language model (LLM) readings of self-descriptions. Verification reveals offers, reduced-cost screening admits them, and re-optimization updates the gaps and prices. Under fixed offers and exact coordination, a full-revelation reference reaches the finite-universe optimum, while budgeted discovery remains heuristic. We evaluate the mechanism on 4,509 real firms in three US regions excluded from predictor training, using scenarios calibrated to seven historical disruptions and simulated availability, offered quantities, and prices. With 80 RFQs, about 1% of exhaustive search, the mechanism recovers 19-43% of the full-information value of outside transport, against 2-6% for random search, and saves USD 73,000-104,000 per event before search and contracting costs. At tight RFQ budgets, gap-guided need selection and learned ranking are complements in these testbeds. LLM reading helps rank capabilities that records omit, such as refrigerated service, but its operating value varies by region. The results support combining record-based learning with coordination-derived gaps under limited search budgets.
Related
- Noise-Robust Distributed Optimization Over Directed Graphs With Row Stochastic Matrices
- Networked Admissibility-Preserving Control for Directed Safe Coordination
- Action-Directed Information for Distributed Control and Agentic Interaction
- Causal Discovery beyond Conditional Independence: Identifiability, Algorithms, and Statistical Inference for Directed Acyclic and Cyclic Graphs
- Capacity Meets the Four Subspace Problem: Distributed Linear Computation and the Cross-Ratio
BibTeX
@misc{xu2026open,
title = {{Open Capacity Pooling in Agentic Supply Chains: Coordination-Directed LLM Discovery and Distributed Re-optimization}},
author = {Yujia Xu and Walid Klibi and Benoit Montreuil},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.40296},
eprint = {2609.40296},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.40296},
}
RIS
TY - UNPB
TI - Open Capacity Pooling in Agentic Supply Chains: Coordination-Directed LLM Discovery and Distributed Re-optimization
AU - Yujia Xu
AU - Walid Klibi
AU - Benoit Montreuil
PY - 2026
DA - 2026/09/30
PB - arXiv
DO - 10.48550/arxiv.2609.40296
UR - https://arxiv.org/abs/2609.40296
AB - Disruptions can leave logistics networks short of capacity, yet outside capacity is hard to use: incumbent models are private, provider records are incomplete, and offers stay hidden until a costly request for quotation (RFQ). We introduce open capacity pooling as a budgeted provider-discovery problem that links which capacity need to pursue, whom to contact, and which verified offer to admit. The alternating direction method of multipliers (ADMM) coordinates incumbents without sharing models, and the resulting capacity gaps direct discovery. A machine-learning layer fitted before search ranks providers by predicted capability and a fleet-size proxy from directory records and large language model (LLM) readings of self-descriptions. Verification reveals offers, reduced-cost screening admits them, and re-optimization updates the gaps and prices. Under fixed offers and exact coordination, a full-revelation reference reaches the finite-universe optimum, while budgeted discovery remains heuristic. We evaluate the mechanism on 4,509 real firms in three US regions excluded from predictor training, using scenarios calibrated to seven historical disruptions and simulated availability, offered quantities, and prices. With 80 RFQs, about 1% of exhaustive search, the mechanism recovers 19-43% of the full-information value of outside transport, against 2-6% for random search, and saves USD 73,000-104,000 per event before search and contracting costs. At tight RFQ budgets, gap-guided need selection and learned ranking are complements in these testbeds. LLM reading helps rank capabilities that records omit, such as refrigerated service, but its operating value varies by region. The results support combining record-based learning with coordination-derived gaps under limited search budgets.
ER -