COOPA: A Modular LLM Agent Architecture for Operations Research Problems

Operations Research (OR) provides a rigorous framework for high-stakes decision-making, but effective OR modeling requires substantial domain knowledge, mathematical abstraction, and solver expertise. Recent LLM-based systems automate parts of this pipeline, yet remain limited by low accuracy on complex problems, opaque outputs, and narrow solver support. We propose COOPA (COoperative OPerations Agent), a modular LLM-agent architecture for interpretable and scalable OR decision support. It combines three components: iterative confidence-based modeling, which generates multiple candidate formulations, self-evaluates them across modeling dimensions, and selects one using a max-min confidence criterion; element-level provenance and confidence explanations, which link variables, parameters, constraints, and objectives to quoted source text and provide an audit trail for human verification; and multi-solver routing to specialized optimizer agents for different OR problem classes. Across three OR benchmarks, eight LLM backbones, and four baselines under identical conditions, COOPA achieves the best macro-average accuracy on six of eight backbones and improves over the strongest baseline by up to 6.7 percentage points. A within-system ablation isolates the contribution of iterative confidence-based modeling, while additional analyses and case studies illustrate the value of source traceability and multi-solver dispatch.

Online Pandora's Box for Contextual LLM Cascading

Motivated by Large Language Model (LLM) cascading, we propose an online contextual Pandora's Box model for adaptively querying and selecting LLM APIs. In each period, a decision-maker observes a request context and faces a two-phase decision problem. In the query phase, the decision-maker sequentially queries APIs, where each query reveals a generated output and the decision-maker incurs an (output-dependent) cost. In the selection phase, the decision-maker selects one of the generated outputs to deploy and observes only the downstream reward of the deployed output. This output-mediated feedback structure differs from classical online contextual Pandora's Box models, in which opening a box directly reveals its reward. Rather than estimating the full conditional output and cost distributions of each API, we directly model the reservation index and develop a learning approach for the query phase. Specifically, we impose a parametric structure on the contextual reservation index functions induced by the classical Weitzman's policy. Our policy combines generalized method of moments (GMM) type estimation of these reservation indices with UCB-style confidence bounds for both these indices and the shared output-level reward evaluator. Under regularity conditions, we prove that the resulting policy achieves dimension-dependent $\widetilde O(\sqrt T)$ cumulative regret over a horizon of $T$ periods.

Latency Guarantee for Ubiquitous Intelligence in 6G: A Network Calculus Approach

With the gradual deployment of 5G and the continuous popularization of edge intelligence (EI), the explosive growth of data on the edge of the network has promoted the rapid development of 6G and ubiquitous intelligence (UbiI). This article aims to explore a new method for modeling latency guarantees for UbiI in 6G given 6G's extremely stochastic nature in terahertz (THz) environments, THz channel tail behavior, and delay distribution tail characteristics generated by the UBiI random component, and to find the optimal solution that minimizes the end-to-end (E2E) delay of UbiI. In this article, the arrival curve and service curve of network calculus can well characterize the stochastic nature of wireless channels, the tail behavior of wireless systems and the E2E service curve of network calculus can model the tail characteristic of the delay distribution in UbiI. Specifically, we first propose demands and challenges facing 6G, edge computing (EC), edge deep learning (DL), and UbiI. Then, we propose the hierarchical architecture, the network model, and the service delay model of the UbiI system based on network calculus. In addition, two case studies demonstrate the usefulness and effectiveness of the network calculus approach in analyzing and modeling the latency guarantee for UbiI in 6G. Finally, future open research issues regarding the latency guarantee for UbiI in 6G are outlined.

Reinforcement Learning for Flexibility Design Problems

Flexibility design problems are a class of problems that appear in strategic decision-making across industries, where the objective is to design a ($e.g.$, manufacturing) network that affords flexibility and adaptivity. The underlying combinatorial nature and stochastic objectives make flexibility design problems challenging for standard optimization methods. In this paper, we develop a reinforcement learning (RL) framework for flexibility design problems. Specifically, we carefully design mechanisms with noisy exploration and variance reduction to ensure empirical success and show the unique advantage of RL in terms of fast-adaptation. Empirical results show that the RL-based method consistently finds better solutions compared to classical heuristics.

Belief Propagation for Min-cost Network Flow: Convergence and Correctness

Message passing type algorithms such as the so-called Belief Propagation algorithm have recently gained a lot of attention in the statistics, signal processing and machine learning communities as attractive algorithms for solving a variety of optimization and inference problems. As a decentralized, easy to implement and empirically successful algorithm, BP deserves attention from the theoretical standpoint, and here not much is known at the present stage. In order to fill this gap we consider the performance of the BP algorithm in the context of the capacitated minimum-cost network flow problem - the classical problem in the operations research field. We prove that BP converges to the optimal solution in the pseudo-polynomial time, provided that the optimal solution of the underlying problem is unique and the problem input is integral. Moreover, we present a simple modification of the BP algorithm which gives a fully polynomial-time randomized approximation scheme (FPRAS) for the same problem, which no longer requires the uniqueness of the optimal solution. This is the first instance where BP is proved to have fully-polynomial running time. Our results thus provide a theoretical justification for the viability of BP as an attractive method to solve an important class of optimization problems.