COOPA: A Modular LLM Agent Architecture for Operations Research Problems
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 12 of its 18 references that are in the map. First posted on arXiv 25 Jun 2026.
Builds on
12 of 18 references.
Closest ancestors · 1
Same direction, newest first
Other references · 11
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
- 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
- 2022Language Models (Mostly) Know What They Knowcited by 1,856
- 2023Teaching Large Language Models to Self-Debugcited by 988
- 2024ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modelingcited by 124
- 2024LLMOPT: Learning to Define and Solve General Optimization Problems from Scratchcited by 102
- 2025Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modelingcited by 45
- 2024OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scalecited by 38
- 2025OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization Modelingcited by 23
- 2025OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement Learningcited by 17
- 2025Auto-Formulating Dynamic Programming Problems with Large Language Modelscited by 16
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM
- 2026ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?
- 2026OptiSkill: A Hierarchical and Evolving SkillBank for LLM-Based Optimization Modeling
- 2026EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutions
- 2025LLM Driven Processes to Foster Explainable AI
- 2025Multi-Agent LLM Orchestration Achieves Deterministic, High-Quality Decision Support for Incident Response
- 2026MIRROR: A Multi-Agent Framework with Iterative Adaptive Revision and Hierarchical Retrieval for Optimization Modeling in Operations Research
- 2024Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs