decision-support

This paper presents FST.ai 2.5, an explainable and uncertainty-aware AI framework for Olympic and Para-Taekwondo that integrates athlete digital twins, competition analytics, and federation-scale decision support.

This paper presents a conflict-free path-planning algorithm for en-route air traffic control, designed to be interpretable and computationally efficient for human operators. The algorithm integrates three conflict detection methods and achieves fast computation times, demonstrated on a real-world sector.

This paper introduces COOPA, a modular LLM agent architecture for operations research problems that combines iterative confidence-based modeling, element-level provenance, and multi-solver routing. Evaluated across eight LLM backbones and four baselines, COOPA achieves the best macro-average accuracy on six backbones and improves over the strongest baseline by up to 6.7 percentage points.

This paper proposes a framework for strategic decision support for AI agents, formulating an optimization problem to minimize support usage while controlling missed-support error. The authors develop an online algorithm and calibration method, demonstrating effectiveness across information gathering, human-AI collaboration, and tool use scenarios.

This paper presents a decision support framework for optimizing validator selection in proof-of-stake blockchains, balancing portfolio quality and diversification through multi-objective optimization and interactive preference learning.

This paper proposes a rolling-window framework for customer churn prediction in non-contractual service environments, using 30-day behavioral windows to enable continuous risk assessment. Evaluated on real-world data, the feature-based model achieves 87.6% accuracy and 0.94 ROC-AUC, while the sequence-based model reaches 96.1% recall.

This paper presents VDSS, a human-in-the-loop multi-agent framework for ventilator decision support that uses contextual bandit preference learning to adapt to clinician-specific tuning styles, with retrospective ICU trajectory replays showing improved recommendation acceptability and reduced interaction rounds.

RealICU is a hindsight-annotated benchmark for evaluating LLMs in ICU settings, covering four physician-motivated tasks. Experiments reveal that existing LLMs struggle with recall-safety tradeoffs and anchoring bias, while a new structured-memory agent improves reasoning but not fully eliminate safety failures.

Cryzo is an AI CEO Agent designed to manage business operations through a single chat interface, connecting to CRMs, ad platforms, and office tools to provide actionable insights and automate tasks.

This paper introduces DiagnosticIQ, a benchmark for evaluating LLMs in translating industrial symbolic maintenance rules into actionable steps. It highlights that while frontier models perform well on standard tasks, they exhibit brittleness and pattern-matching behaviors under structural perturbations.

Introduces how ChatGPT Work integrates internal and external financial signals into a CFO command center, automatically generates decision memos and Excel models, and helps CFOs proactively shape business outcomes.

Council of High Intelligence is an open-source tool that orchestrates 18 AI personas from multiple LLM providers to deliberate on hard decisions, providing structured disagreement and multi-perspective analysis via a single command.