COOPA: A Modular LLM Agent Architecture for Operations Research Problems
Chuanhao Li, Xiaoan Xu, Dirk Bergemann, Ethan X. Fang, Yehua Wei, Zhuoran Yang
Why It Matters
What makes this one worth your time
This work is relevant for AI researchers and engineers interested in improving decision-making processes in Operations Research through enhanced interpretability and solver flexibility.
COOPA enhances Operations Research decision-making with a modular LLM-agent architecture for better accuracy and interpretability.
Summary
The paper introduces COOPA, a modular LLM-agent architecture designed to enhance decision support in Operations Research by improving interpretability and scalability. It features iterative confidence-based modeling, element-level provenance explanations, and multi-solver routing, achieving superior accuracy on several benchmarks compared to existing baselines.
Key contributions
- Development of a modular LLM-agent architecture for Operations Research.
- Introduction of iterative confidence-based modeling for improved decision accuracy.
- Implementation of multi-solver routing to optimize different OR problem classes.
Notable insights
- Iterative confidence-based modeling allows for the generation and evaluation of multiple candidate formulations, enhancing decision accuracy.
- Element-level provenance explanations provide an audit trail, improving the transparency and verifiability of the decision-making process.
Possible limitations
- Not stated in the abstract
Abstract
arXiv:2606.27611v1 Announce Type: new Abstract: 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.