# AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System Optimization

arXiv: https://arxiv.org/abs/2604.26969 · HTML: https://mlsanity.com/paper/2604.26969/

## 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 17 of its 23 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 17 of 17)

- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations](https://mlsanity.com/paper/2308.16505/) (2023)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [Large Language Model Agent for Hyper-Parameter Optimization](https://mlsanity.com/paper/2402.01881/) (2024)
- [ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering](https://mlsanity.com/paper/2505.23723/) (2025)
- [PACEvolve: Enabling Progress-Aware Consistent Evolution](https://mlsanity.com/paper/2601.10657/) (2026)
- [Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents](https://mlsanity.com/paper/2602.10226/) (2026)
- [Optimal Algorithms for Stochastic Multi-Level Compositional Optimization](https://mlsanity.com/paper/2202.07530/) (2022)
- [MemRec: Collaborative Memory-Augmented Agentic Recommender System](https://mlsanity.com/paper/2601.08816/) (2026)
- [Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch](https://mlsanity.com/paper/2603.24647/) (2026)
- [Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback](https://mlsanity.com/paper/2602.12612/) (2026)
- [RecPrompt: A Self-tuning Prompting Framework for News Recommendation Using Large Language Models](https://mlsanity.com/paper/2312.10463/) (2023)
- [STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning](https://mlsanity.com/paper/2508.18812/) (2025)
- [LLMs as Orchestrators: Constraint-Compliant Multi-Agent Optimization for Recommendation Systems](https://mlsanity.com/paper/2601.19121/) (2026)
- [Decentralized Multi-Level Compositional Optimization Algorithms with Level-Independent Convergence Rate](https://mlsanity.com/paper/2306.03322/) (2023)
- [AgenticTagger: Structured Item Representation for Recommendation with LLM Agents](https://mlsanity.com/paper/2602.05945/) (2026)

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

- [Dream-RSI: Recursive Self-Improvement through Evolving Worlds](https://mlsanity.com/paper/2609.14858/) (2026)
- [AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems](https://mlsanity.com/paper/2606.26859/) (2026)
- [From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents](https://mlsanity.com/paper/2608.05235/) (2026)
- [AutoLR: Automating the Path from Research to Launch Review in Industrial Recommender Systems](https://mlsanity.com/paper/2609.04871/) (2026)
- [DMRL: Document-Mediated Reinforcement Learning for Skill Optimization in Advertising Recommendation](https://mlsanity.com/paper/2609.02170/) (2026)

## Abstract (arXiv)

Modern large-scale recommendation systems are typically constructed as multi-stage pipelines, encompassing pre-ranking, ranking, and re-ranking phases. While traditional recommendation research typically focuses on optimizing a specific model, such as improving the pre-ranking model structure or ranking models training algorithm, system-level configurations optimization play a crucial role, which integrates the output from each model head to get the final score in each stage. Due to the complexity of the system, the configuration optimization is highly important and challenging. Any model modification requires new optimal system-level configurations. But each experimental iteration requires significant tuning effort. Furthermore, models in different stage operates within a distinct context and optimizes for different targets, requiring specialized domain expertise. In addition, optimization success depends on balancing competing multiple online metrics and alignment with shifting production development objectives. To address these challenges, we propose AgenticRecTune, an agentic framework comprising five specialized agents, Actor, Critic, Insight, Skill, and Online, designed to manage the end-to-end configuration optimization workflow. By leveraging the advanced reasoning of Large Language Models (LLMs), specifically Gemini, AgenticRecTune explore the optimal configuration spaces. The Actor Agent proposes multiple candidates and Critic Agent filters out suboptimal proposals.Then Online Agent autonomously prepares A/B tests based on the proposed configurations set from the Critic Agent and captures the subsequencet experimental results. We also introduce a self-evolving Skillhub, which utilizes a collaboration between the Insight Agent and Skill Agent to summarize the history results, extract underlying mechanics of each task in recommendation system and update skills.