# EvoRec: Self Evolving Agentic Recommender Systems

arXiv: https://arxiv.org/abs/2606.28368 · HTML: https://mlsanity.com/paper/2606.28368/

## Key facts

- Cited by 1 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 18 of its 31 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Placed in

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

## Builds on (most cited first, 18 of 18)

- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization](https://mlsanity.com/paper/2008.07873/) (2020)
- [Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills](https://mlsanity.com/paper/2603.25158/) (2026)
- [CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification](https://mlsanity.com/paper/2604.01687/) (2026)
- [Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited](https://mlsanity.com/paper/2303.13835/) (2023)
- [A Survey on Session-based Recommender Systems](https://mlsanity.com/paper/1902.04864/) (2019)
- [SkillClaw: Let Skills Evolve Collectively with Agentic Evolver](https://mlsanity.com/paper/2604.08377/) (2026)
- [Empowering News Recommendation with Pre-trained Language Models](https://mlsanity.com/paper/2104.07413/) (2021)
- [Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations](https://mlsanity.com/paper/2503.02453/) (2025)
- [Rethinking Large Language Model Architectures for Sequential Recommendations](https://mlsanity.com/paper/2402.09543/) (2024)
- [RecoWorld: Building Simulated Environments for Agentic Recommender Systems](https://mlsanity.com/paper/2509.10397/) (2025)
- [Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents](https://mlsanity.com/paper/2602.10226/) (2026)
- [REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems](https://mlsanity.com/paper/2508.15308/) (2025)
- [Interactive Recommendation Agent with Active User Commands](https://mlsanity.com/paper/2509.21317/) (2025)
- [OxygenREC: An Instruction-Following Generative Framework for E-commerce Recommendation](https://mlsanity.com/paper/2512.22386/) (2025)
- [Let the Agent Steer: Closed-Loop Ranking Optimization via Influence Exchange](https://mlsanity.com/paper/2603.27765/) (2026)

## Built on by (most cited first, 1 of 1)

- [RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems](https://mlsanity.com/paper/2607.29241/) (2026)

## Abstract (arXiv)

Optimizing modern recommender systems still relies heavily on engineers iterating by hand, which is slow and bounded by individual expertise. LLM-based agents open a path toward automating this loop, yet two issues remain. First, the agent is used only as a code translator and accumulates no methodology across iterations. Second, the optimization space is confined to a predefined range and rarely introduces structurally new ideas. To address these problems, we propose EvoRec, a multi-agent framework that co-evolves the recommendation model and the optimization methodology driving it. Four collaborating agents carry out a dual-track loop: the Research Agent and Code Agent iterate the model each round, while the Skill Evolver periodically distills reusable methodology from a persistent Memory of past experiments. Experiments on two public benchmarks and one large-scale industrial dataset show that EvoRec improves offline metrics by up to 5.54% over the strongest baseline, and an online A/B test delivers a 1.85% revenue lift and a 1.02% CTR gain.