Cheol Woo Kim

Dimitris Bertsimas, Cheol Woo Kim

We propose an approach based on machine learning to solve two-stage linear adaptive robust optimization (ARO) problems with binary here-and-now variables and polyhedral uncertainty sets. We encode the optimal here-and-now decisions, the worst-case scenarios associated with the optimal here-and-now decisions, and the optimal wait-and-see decisions into what we denote as the strategy. We solve multiple similar ARO instances in advance using the column and constraint generation algorithm and extract the optimal strategies to generate a training set. We train a machine learning model that predicts high-quality strategies for the here-and-now decisions, the worst-case scenarios associated with the optimal here-and-now decisions, and the wait-and-see decisions. We also introduce an algorithm to reduce the number of different target classes the machine learning algorithm needs to be trained on. We apply the proposed approach to the facility location, the multi-item inventory control and the unit commitment problems. Our approach solves ARO problems drastically faster than the state-of-the-art algorithms with high accuracy.

Dimitris Bertsimas, Cheol Woo Kim

We propose a machine learning approach to the optimal control of multiclass fluid queueing networks (MFQNETs) that provides explicit and insightful control policies. We prove that a threshold type optimal policy exists for MFQNET control problems, where the threshold curves are hyperplanes passing through the origin. We use Optimal Classification Trees with hyperplane splits (OCT-H) to learn an optimal control policy for MFQNETs. We use numerical solutions of MFQNET control problems as a training set and apply OCT-H to learn explicit control policies. We report experimental results with up to 33 servers and 99 classes that demonstrate that the learned policies achieve 100\% accuracy on the test set. While the offline training of OCT-H can take days in large networks, the online application takes milliseconds.

Eleni Straitouri, Cheol Woo Kim, Milind Tambe

Mathematical optimization is a powerful tool for structured decision-making across domains such as resource allocation and planning. Formulating optimization models faithful to reality, though, remains a significant bottleneck as it typically demands both domain expertise and optimization knowledge that are often scarce. Recent advances in large language models (LLMs) promise to bridge this gap, enabling the generation of candidate optimization models from natural language descriptions. However, there is no guarantee that any single LLM-generated model is reliable, and existing approaches that output only one model are therefore risky. In this work, we propose a novel algorithm that generates a portfolio of optimization models, designed to be robust to the limitations of LLMs. Our method exploits the observation that a single LLM can play two distinct roles $\unicode{x2014}$ as a stochastic generator and as a reasoning evaluator $\unicode{x2014}$ and proposes a unified framework that leverages both capabilities in a complementary manner. We provide theoretical guarantees showing that, as long as either the generator or the evaluator is well-aligned with human preferences, the portfolio is guaranteed to contain high-quality candidates, enabling a principled human-in-the-loop process in which a decision-maker can review multiple candidates before committing to one. We further validate our approach empirically, demonstrating strong performance across a range of optimization modeling tasks.

Shresth Verma, Mauricio Tec, Cheol Woo Kim et al.

While LLMs excel at single-turn generation, they struggle with long-horizon, multi-turn interactions. Offline reinforcement learning (RL) offers a scalable approach, yet its performance hinges on the availability and quality of multi-turn trajectory data. A common remedy is to augment training with synthetic trajectories generated by LLMs or simulators, but synthetic data is highly heterogeneous in quality, and naively treating all trajectories as equally informative can degrade performance. We propose BOOST, a bilevel optimization framework where the inner level trains the LLM on reweighted data and the outer level trains a lightweight reweighting head on held-out real validation tasks, assigning continuous trajectory-level weights without requiring an external judge. To ground this approach, we derive a PAC-Bayesian bound revealing a three-way trade-off: synthetic data increases diversity but risks task-shift, while concentrating weight on high-quality trajectories improves empirical performance at the cost of effective sample size. Empirically, our method consistently outperforms multiple baselines. Analysis reveals it upweights synthetic trajectories that align with the real data distribution and exhibit higher qualitative merit.

Cheol Woo Kim, Davin Choo, Tzeh Yuan Neoh et al.

As AI systems grow more capable and autonomous, ensuring their safety and reliability requires not only model-level alignment but also strategic oversight of the humans and institutions involved in their development and deployment. Existing safety frameworks largely treat alignment as a static optimization problem (e.g., tuning models to desired behavior) while overlooking the dynamic, adversarial incentives that shape how data are collected, how models are evaluated, and how they are ultimately deployed. We propose a new perspective on AI safety grounded in Stackelberg Security Games (SSGs): a class of game-theoretic models designed for adversarial resource allocation under uncertainty. By viewing AI oversight as a strategic interaction between defenders (auditors, evaluators, and deployers) and attackers (malicious actors, misaligned contributors, or worst-case failure modes), SSGs provide a unifying framework for reasoning about incentive design, limited oversight capacity, and adversarial uncertainty across the AI lifecycle. We illustrate how this framework can inform (1) training-time auditing against data/feedback poisoning, (2) pre-deployment evaluation under constrained reviewer resources, and (3) robust multi-model deployment in adversarial environments. This synthesis bridges algorithmic alignment and institutional oversight design, highlighting how game-theoretic deterrence can make AI oversight proactive, risk-aware, and resilient to manipulation.

Sarah Martinson, Lingkai Kong, Cheol Woo Kim et al.

Agent-based simulation is crucial for modeling complex human behavior, yet traditional approaches require extensive domain knowledge and large datasets. In data-scarce healthcare settings where historic and counterfactual data are limited, large language models (LLMs) offer a promising alternative by leveraging broad world knowledge. This study examines an LLM-driven simulation of a maternal mobile health program, predicting beneficiaries' listening behavior when they receive health information via automated messages (control) or live representatives (intervention). Since uncertainty quantification is critical for decision-making in health interventions, we propose an LLM epistemic uncertainty estimation method based on binary entropy across multiple samples. We enhance model robustness through ensemble approaches, improving F1 score and model calibration compared to individual models. Beyond direct evaluation, we take a decision-focused approach, demonstrating how LLM predictions inform intervention feasibility and trial implementation in data-limited settings. The proposed method extends to public health, disaster response, and other domains requiring rapid intervention assessment under severe data constraints. All code and prompts used for this work can be found at https://github.com/sarahmart/LLM-ABS-ARMMAN-prediction.

Lingkai Kong, Haichuan Wang, Yuqi Pan et al.

In green security, defenders must forecast adversarial behavior, such as poaching, illegal logging, and illegal fishing, to plan effective patrols. These behavior are often highly uncertain and complex. Prior work has leveraged game theory to design robust patrol strategies to handle uncertainty, but existing adversarial behavior models primarily rely on Gaussian processes or linear models, which lack the expressiveness needed to capture intricate behavioral patterns. To address this limitation, we propose a conditional diffusion model for adversary behavior modeling, leveraging its strong distribution-fitting capabilities. To the best of our knowledge, this is the first application of diffusion models in the green security domain. Integrating diffusion models into game-theoretic optimization, however, presents new challenges, including a constrained mixed strategy space and the need to sample from an unnormalized distribution to estimate utilities. To tackle these challenges, we introduce a mixed strategy of mixed strategies and employ a twisted Sequential Monte Carlo (SMC) sampler for accurate sampling. Theoretically, our algorithm is guaranteed to converge to an epsilon equilibrium with high probability using a finite number of iterations and samples. Empirically, we evaluate our approach on both synthetic and real-world poaching datasets, demonstrating its effectiveness.

Cheol Woo Kim, Jai Moondra, Shresth Verma et al.

In many real-world applications of reinforcement learning (RL), deployed policies have varied impacts on different stakeholders, creating challenges in reaching consensus on how to effectively aggregate their preferences. Generalized $p$-means form a widely used class of social welfare functions for this purpose, with broad applications in fair resource allocation, AI alignment, and decision-making. This class includes well-known welfare functions such as Egalitarian, Nash, and Utilitarian welfare. However, selecting the appropriate social welfare function is challenging for decision-makers, as the structure and outcomes of optimal policies can be highly sensitive to the choice of $p$. To address this challenge, we study the concept of an $α$-approximate portfolio in RL, a set of policies that are approximately optimal across the family of generalized $p$-means for all $p \in [-\infty, 1]$. We propose algorithms to compute such portfolios and provide theoretical guarantees on the trade-offs among approximation factor, portfolio size, and computational efficiency. Experimental results on synthetic and real-world datasets demonstrate the effectiveness of our approach in summarizing the policy space induced by varying $p$ values, empowering decision-makers to navigate this landscape more effectively.

Cheol Woo Kim, Shresth Verma, Mauricio Tec et al.

Direct Preference Optimization (DPO) has become a popular method for fine-tuning large language models (LLMs) due to its stability and simplicity. However, it is also known to be sensitive to noise in the data and prone to overfitting. Recent works have proposed using distributionally robust optimization (DRO) to address potential noise and distributional shift in the data. However, these methods often suffer from excessive conservatism and high computational cost. We propose DPO-PRO (DPO with Preference Robustness), a robust fine-tuning algorithm based on DPO which accounts for uncertainty in the preference distribution through a lightweight DRO formulation. Unlike prior DRO-based variants, DPO-PRO focuses solely on uncertainty in preferences, avoiding unnecessary conservatism and incurring negligible computational overhead. We further show that DPO-PRO is equivalent to a regularized DPO objective that penalizes model overconfidence under weak preference signals. We evaluate DPO-PRO on standard alignment benchmarks and a real-world public health task. Experimental results show that our method consistently improves robustness to noisy preference signals compared to existing DPO variants.

Cheol Woo Kim, Shresth Verma, Mauricio Tec et al.

We study an LLM fine-tuning task for designing reward functions for sequential resource allocation problems in public health, guided by human preferences expressed in natural language. This setting presents a challenging testbed for alignment due to complex and ambiguous objectives and limited data availability. We propose DPO-PRO, a robust fine-tuning algorithm based on Direct Preference Optimization (DPO), which accounts for uncertainty in the preference distribution using a lightweight Distributionally Robust Optimization (DRO) formulation. Unlike prior DRO-based DPO methods, DPO-PRO is significantly less conservative. We evaluate DPO-PRO on a real-world maternal mobile health program operated by the non-profit organization ARMMAN, as well as on standard alignment benchmarks. Experimental results demonstrate that our method consistently improves robustness to noisy preference signals compared to existing DPO variants. Moreover, DPO-PRO achieves comparable performance to prior self-reflection-based baseline for reward function design, while requiring significantly lower inference-time cost.

Dimitris Bertsimas, Cheol Woo Kim, José Niño-Mora

We propose a machine learning approach to the optimal control of fluid restless multi-armed bandits (FRMABs) with state equations that are either affine or quadratic in the state variables. By deriving fundamental properties of FRMAB problems, we design an efficient machine learning based algorithm. Using this algorithm, we solve multiple instances with varying initial states to generate a comprehensive training set. We then learn a state feedback policy using Optimal Classification Trees with hyperplane splits (OCT-H). We test our approach on machine maintenance, epidemic control and fisheries control problems. Our method yields high-quality state feedback policies and achieves a speed-up of up to 26 million times compared to a direct numerical algorithm for fluid problems.