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

arXiv: https://arxiv.org/abs/2601.19121 · HTML: https://mlsanity.com/paper/2601.19121/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 21 of 21)

- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems](https://mlsanity.com/paper/2310.09233/) (2023)
- [MACRec: a Multi-Agent Collaboration Framework for Recommendation](https://mlsanity.com/paper/2402.15235/) (2024)
- [Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning](https://mlsanity.com/paper/2405.15114/) (2024)
- [A Survey on LLM-powered Agents for Recommender Systems](https://mlsanity.com/paper/2502.10050/) (2025)
- [A Survey on Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2308.01118/) (2023)
- [Fairness in Recommender Systems: Research Landscape and Future Directions](https://mlsanity.com/paper/2205.11127/) (2022)
- [Multi-FR: A Multi-objective Optimization Framework for Multi-stakeholder Fairness-aware Recommendation](https://mlsanity.com/paper/2105.02951/) (2021)
- [Fairness and Diversity in Recommender Systems: A Survey](https://mlsanity.com/paper/2307.04644/) (2023)
- [ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation](https://mlsanity.com/paper/2506.21931/) (2025)
- [Pareto-based Multi-Objective Recommender System with Forgetting Curve](https://mlsanity.com/paper/2312.16868/) (2023)
- [CAL-RAG: Retrieval-Augmented Multi-Agent Generation for Content-Aware Layout Design](https://mlsanity.com/paper/2506.21934/) (2025)
- [Push and Pull Search for Solving Constrained Multi-objective Optimization Problems](https://mlsanity.com/paper/1709.05915/) (2017)
- [CARTS: Collaborative Agents for Recommendation Textual Summarization](https://mlsanity.com/paper/2506.17765/) (2025)
- [Deep Pareto Reinforcement Learning for Multi-Objective Recommender Systems](https://mlsanity.com/paper/2407.03580/) (2024)
- [User-item fairness tradeoffs in recommendations](https://mlsanity.com/paper/2412.04466/) (2024)
- [Enhancing New-item Fairness in Dynamic Recommender Systems](https://mlsanity.com/paper/2504.21362/) (2025)
- [GRACE: Generative Recommendation via Journey-Aware Sparse Attention on Chain-of-Thought Tokenization](https://mlsanity.com/paper/2507.14758/) (2025)
- [Adaptive GPU Resource Allocation for Multi-Agent Collaborative Reasoning in Serverless Environments](https://mlsanity.com/paper/2512.22149/) (2025)
- [A Review on Constraint Handling Techniques for Population-based Algorithms: from single-objective to multi-objective optimization](https://mlsanity.com/paper/2206.13802/) (2022)

## Built on by (most cited first, 5 of 5)

- [AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System Optimization](https://mlsanity.com/paper/2604.26969/) (2026)
- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [Winning by Peeking: Unenforced Budgets and Test-Set Selection Inflate Short-Budget AutoML Comparisons](https://mlsanity.com/paper/2608.07303/) (2026)
- [An LLM-powered Agentic Recommendation System for Connected TV Content Discovery](https://mlsanity.com/paper/2607.09988/) (2026)
- [VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents](https://mlsanity.com/paper/2609.38270/) (2026)

## Abstract (arXiv)

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.