LLMs as Orchestrators: Constraint-Compliant Multi-Agent Optimization for Recommendation Systems

TL;DR

This paper introduces DualAgent-Rec, an LLM-coordinated framework for multi-objective recommendation systems that guarantees constraint satisfaction and improves optimization performance.

Contribution

It presents a novel dual-agent framework utilizing LLMs to effectively coordinate constrained multi-objective optimization in recommendation systems.

Findings

Achieves 100% constraint satisfaction in experiments.

Improves Pareto hypervolume by 4-6% over baselines.

Maintains competitive accuracy-diversity trade-offs.

Abstract

Recommendation systems must optimize multiple objectives while satisfying hard business constraints such as fairness and coverage. For example, an e-commerce platform may require every recommendation list to include items from multiple sellers and at least one newly listed product; violating such constraints--even once--is unacceptable in production. Prior work on multi-objective recommendation and recent LLM-based recommender agents largely treat constraints as soft penalties or focus on item scoring and interaction, leading to frequent violations in real-world deployments. How to leverage LLMs for coordinating constrained optimization in recommendation systems remains underexplored. We propose DualAgent-Rec, an LLM-coordinated dual-agent framework for constrained multi-objective e-commerce recommendation. The framework separates optimization into an Exploitation Agent that prioritizes accuracy under hard constraints and an Exploration Agent that promotes diversity through unconstrained Pareto search. An LLM-based coordinator adaptively allocates resources between agents based on optimization progress and constraint satisfaction, while an adaptive epsilon-relaxation mechanism guarantees feasibility of final solutions. Experiments on the Amazon Reviews 2023 dataset demonstrate that DualAgent-Rec achieves 100% constraint satisfaction and improves Pareto hypervolume by 4-6% over strong baselines, while maintaining competitive accuracy-diversity trade-offs. These results indicate that LLMs can act as effective orchestration agents for deployable and constraint-compliant recommendation systems.