arXiv AI
Jul 24
SPORD: A Simulation-Propose-then-OR-Dispose Approach for Supply Chain Planning
arXiv:2607. 21354v1 Announce Type: new Abstract: For years, supply chain planning at e-commerce firms has operated as a collection of isolated projects.
SPORD: A Simulation-Propose-then-OR-Dispose Approach for Supply Chain Planning
For years, supply chain planning at e-commerce firms has operated as a collection of isolated projects. Each planning task from static network planning to dynamic warehouse assortment planning requires analysts to spend weeks building models from scratch, calibrating and persuading executives to act on outputs they cannot verify.
Related stories
arXiv AI
Jun 26
Context-Aware Synthesis of Optimization Pipelines for Warehouse Optimization
arXiv:2606. 26852v1 Announce Type: new Abstract: Order fulfillment in manual picker-to-goods warehouses involves interconnected decisions such as item assignment, order batching, and picker routing.
arXiv AI
Jun 17
Blueprint First, Model Second: A Framework for Deterministic LLM Workflow
arXiv:2508. 02721v2 Announce Type: replace-cross Abstract: While powerful, the inherent non-determinism of large language model (LLM) agents limits their application in structured operational environments where procedural fidelity and predictable execution are strict requirements.
arXiv Machine Learning
Jul 31
SCOPE: Supply-Chain Operations through Coupled Policies for End-to-End Coordination
arXiv:2607. 28488v1 Announce Type: cross Abstract: Can supply-chain AI move beyond isolated decision modules toward unified operational planning?
arXiv AI
Aug 28
LLMs Can Design Near-Optimal OR Algorithms
The paper investigates whether large language models (LLMs) can design effective algorithms for well-specified operations research (OR) problems, focusing on inventory control, queueing network control, and assortment optimization. Two usage levels are examined: (1) the model receives a single problem instance and outputs a solution, and (2) the model receives only a problem class description and returns a general algorithm mapping instance parameters to solutions. Using a single untuned prompt and a Python sandbox, the strongest tested model, gpt-5.6-sol, matches or surpasses existing methods on nearly all evaluated instances, even when the algorithm is fixed before seeing evaluation cases, and performance improves markedly across models released within eight months.
arXiv AI
2d ago
OR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Framework
The paper introduces OSCAR, an LLM‑based framework that translates business descriptions into accurate optimization models while verifying and improving them through a simulator, coder, and reviewer. OSCAR uses a cost‑ordered escalation strategy to select among LLMs of varying price and capability, achieving 95–100% accuracy on benchmark problems with local, open‑weight models. The framework also provides competitive guarantees and token‑cost advantages over existing LLMs like Codex and Claude Code.
arXiv Machine Learning
Jul 7
A Policy Decomposition Framework for Dynamic Order Fulfillment Operations
arXiv:2607. 04056v1 Announce Type: cross Abstract: Modern supply chains span diverse operational environments, ranging from e-commerce distribution networks to customized production-to-order manufacturing lines.
arXiv AI
Sep 15
A Hybrid Agentic AI Framework for Intelligent Supply Chain Analytics
arXiv:2609.13561v1 Announce Type: new Abstract: Efficient utilization of supply chain analytics for decision making remains a significant challenge for planners, as critical tasks such as database qu...
arXiv AI
Sep 12
Planning and Scheduling Business Processes under Control-Flow Uncertainty: Extended Version
The paper addresses the challenge of scheduling business process activities when the exact sequence of required tasks is uncertain due to data‑driven decisions made during execution. It proposes framing the problem as a chance‑constrained optimization and introduces two formulations: a decomposed two‑stage approach (planning to minimize superfluous activities under a feasibility constraint, followed by scheduling to minimize makespan) and an integrated single‑stage approach. Experiments on two real‑world and one synthetic dataset show that the integrated method achieves better makespans but struggles with scalability, whereas the decomposed method scales to larger settings.
arXiv AI
Jun 30
Solver-Verified Formulation Generation and Selection for Multi-Warehouse Inventory Allocation Using Large Language Models
arXiv:2606. 29366v1 Announce Type: cross Abstract: Balance-oriented multi-warehouse inventory allocation is a recurring decision problem in large-scale e-commerce supply chains, in which a fixed replenishment quantity is distributed across warehouses to balance post-allocation inventory coverage while accounting for demand forecasts and heterogeneous allocation constraints.
arXiv AI
Jul 14
A Formal Hierarchical Architecture for Agentic Orchestration with Stack-Based Execution and Lazy Discovery
arXiv:2607. 11138v1 Announce Type: new Abstract: The rapid expansion of capabilities in Large Language Model (LLM) agents has exposed a critical architectural bottleneck: when agents are given access to a flat, monolithic registry of tools, the model must evaluate hundreds or thousands of options simultaneously.
arXiv Machine Learning
Sep 1
E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation
E-Commerce Bench is an open‑source benchmark that simulates a year‑long e‑commerce operation, requiring LLM agents to manage multiple online stores, negotiate with suppliers, optimize sales, fulfill orders, handle returns, and manage cash flow. The environment uses real product and supplier data, a calendar of promotions and shocks, and deterministic customer and negotiation models to enable reproducible evaluation. The study evaluates 18 state‑of‑the‑art models across seven metrics, finding no single model dominates, with GPT‑5.6 Sol achieving the highest year‑end assets but lagging in fraud avoidance and operational efficiency.