# Rethinking Recommendation Paradigms: From Pipelines to Agentic Recommender Systems

arXiv: https://arxiv.org/abs/2603.26100 · HTML: https://mlsanity.com/paper/2603.26100/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 7 of its 20 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Placed in

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

## Builds on (most cited first, 7 of 7)

- [Generative Recommendation: Towards Next-generation Recommender Paradigm](https://mlsanity.com/paper/2304.03516/) (2023)
- [Generating Long Semantic IDs in Parallel for Recommendation](https://mlsanity.com/paper/2506.05781/) (2025)
- [Rethinking Large Language Model Architectures for Sequential Recommendations](https://mlsanity.com/paper/2402.09543/) (2024)
- [OneRec Technical Report](https://mlsanity.com/paper/2506.13695/) (2025)
- [REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems](https://mlsanity.com/paper/2508.15308/) (2025)
- [Synergistic Integration and Discrepancy Resolution of Contextualized Knowledge for Personalized Recommendation](https://mlsanity.com/paper/2510.14257/) (2025)
- [Masked Diffusion Generative Recommendation](https://mlsanity.com/paper/2601.19501/) (2026)

## Built on by (most cited first, 3 of 3)

- [SAGER: Self-Evolving User Policy Skills for Recommendation Agent](https://mlsanity.com/paper/2604.14972/) (2026)
- [CORAL: An LLM-Native Harness for Production Recommender Systems](https://mlsanity.com/paper/2609.02730/) (2026)
- [The User Asks, Platforms Compete: How Agentic Recommendation Markets Take Shape](https://mlsanity.com/paper/2607.25253/) (2026)

## Abstract (arXiv)

Large-scale industrial recommenders typically use a fixed multi-stage pipeline (recall, ranking, re-ranking) and have progressed from collaborative filtering to deep and large pre-trained models. However, both multi-stage and so-called One Model designs remain essentially static: models are black boxes, and system improvement relies on manual hypotheses and engineering, which is hard to scale under heterogeneous data and multi-objective business constraints. We propose an Agentic Recommender System (AgenticRS) that reorganizes key modules as agents. Modules are promoted to agents only when they form a functionally closed loop, can be independently evaluated, and possess an evolvable decision space. For model agents, we outline two self-evolution mechanisms: reinforcement learning style optimization in well-defined action spaces, and large language model based generation and selection of new architectures and training schemes in open-ended design spaces. We further distinguish individual evolution of single agents from compositional evolution over how multiple agents are selected and connected, and use a layered inner and outer reward design to couple local optimization with global objectives. This provides a concise blueprint for turning static pipelines into self-evolving agentic recommender systems.