# Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents

arXiv: https://arxiv.org/abs/2602.10226 · HTML: https://mlsanity.com/paper/2602.10226/

## Key facts

- Cited by 19 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 38 references that are in the map.
- First posted on arXiv 10 Feb 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)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [Reinforcement learning based recommender systems: A survey](https://mlsanity.com/paper/2101.06286/) (2021)
- [Top-K Off-Policy Correction for a REINFORCE Recommender System](https://mlsanity.com/paper/1812.02353/) (2018)
- [Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges](https://mlsanity.com/paper/2107.05847/) (2021)
- [Deep reinforcement learning for search, recommendation, and online advertising: a survey](https://mlsanity.com/paper/1812.07127/) (2018)
- [Beyond Item Dissimilarities: Diversifying by Intent in Recommender Systems](https://mlsanity.com/paper/2405.12327/) (2024)
- [Learned Ranking Function: From Short-term Behavior Predictions to Long-term User Satisfaction](https://mlsanity.com/paper/2408.06512/) (2024)

## Built on by (most cited first, 19 of 19)

- [AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems](https://mlsanity.com/paper/2606.26859/) (2026)
- [AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System Optimization](https://mlsanity.com/paper/2604.26969/) (2026)
- [NeuroClaw Technical Report](https://mlsanity.com/paper/2604.24696/) (2026)
- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [SAGER: Self-Evolving User Policy Skills for Recommendation Agent](https://mlsanity.com/paper/2604.14972/) (2026)
- [What Do Evolutionary Coding Agents Evolve?](https://mlsanity.com/paper/2605.20086/) (2026)
- [RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems](https://mlsanity.com/paper/2607.29241/) (2026)
- [SEA-TS: Self-Evolving Agent for Autonomous Code Generation of Time Series Forecasting Algorithms](https://mlsanity.com/paper/2603.04873/) (2026)
- [EvoRec: Self Evolving Agentic Recommender Systems](https://mlsanity.com/paper/2606.28368/) (2026)
- [From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents](https://mlsanity.com/paper/2608.05235/) (2026)
- [RecEvolve: A Knowledge-Driven Autonomous Agent System for Recommender Systems](https://mlsanity.com/paper/2609.01622/) (2026)
- [AutoLR: Automating the Path from Research to Launch Review in Industrial Recommender Systems](https://mlsanity.com/paper/2609.04871/) (2026)
- [An LLM-powered Agentic Recommendation System for Connected TV Content Discovery](https://mlsanity.com/paper/2607.09988/) (2026)
- [SR-Agent: An Experience-Driven Agentic Framework for Post-Ranking Strategy Refinement in E-Commerce Recommendation](https://mlsanity.com/paper/2607.17719/) (2026)
- [AURA: Agentic Diagnosis and Refinement for Production Recommender Systems at Scale](https://mlsanity.com/paper/2609.16625/) (2026)
- [One Prompt Does Not Fit All: Self-Meta-Evolve for Personalized Information Extraction](https://mlsanity.com/paper/2609.21626/) (2026)
- [Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems](https://mlsanity.com/paper/2609.30001/) (2026)
- [PEAR: Progressive Evidence-Based AutoResearch for Industrial Search Systems](https://mlsanity.com/paper/2609.35031/) (2026)
- [RankEvolve: A Reliable Multi-Agent Auto-Research Harness for Evolving Ranking Models](https://mlsanity.com/paper/2609.39551/) (2026)

## Abstract (arXiv)

Optimizing large-scale machine learning systems, such as recommendation models for global video platforms, requires navigating a massive hyperparameter search space and, more critically, designing sophisticated optimizers, architectures, and reward functions to capture nuanced user behaviors. Achieving substantial improvements in these areas is a non-trivial task, traditionally relying on extensive manual iterations to test new hypotheses. We propose a self-evolving system that leverages Large Language Models (LLMs), specifically those from Google's Gemini family, to autonomously generate, train, and deploy high-performing, complex model changes within an end-to-end automated workflow. The self-evolving system consists of an Offline Agent (Fast Loop) that performs high-throughput hypothesis generation to optimize for proxy metrics, and an Online Agent (Slow Loop) that validates candidates against delayed north star business metrics in live production. Our agents act as specialized Machine Learning Engineers (MLEs): they exhibit deep reasoning capabilities, discovering novel improvements in optimization algorithms and model architecture, and formulating innovative reward functions that target long-term user engagement. The effectiveness of this approach is demonstrated through several successful production launches at YouTube, confirming that autonomous, LLM-driven evolution can surpass traditional engineering workflows in both development velocity and model performance.