# AgenticTagger: Structured Item Representation for Recommendation with LLM Agents

arXiv: https://arxiv.org/abs/2602.05945 · HTML: https://mlsanity.com/paper/2602.05945/

## Key facts

- Cited by 2 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 15 of its 84 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Placed in

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

## Builds on (most cited first, 15 of 15)

- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [User Behavior Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2306.02552/) (2023)
- [Leveraging Large Language Models in Conversational Recommender Systems](https://mlsanity.com/paper/2305.07961/) (2023)
- [RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents](https://mlsanity.com/paper/2308.09904/) (2023)
- [PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations](https://mlsanity.com/paper/2510.07784/) (2025)
- [Prospect Personalized Recommendation on Large Language Model-based Agent Platform](https://mlsanity.com/paper/2402.18240/) (2024)
- [Multi-Agent Collaborative Filtering: Orchestrating Users and Items for Agentic Recommendations](https://mlsanity.com/paper/2511.18413/) (2025)
- [RecGPT: Generative Personalized Prompts for Sequential Recommendation via ChatGPT Training Paradigm](https://mlsanity.com/paper/2404.08675/) (2024)
- [Inference Computation Scaling for Feature Augmentation in Recommendation Systems](https://mlsanity.com/paper/2502.16040/) (2025)
- [News Recommendation with Category Description by a Large Language Model](https://mlsanity.com/paper/2405.13007/) (2024)
- [Unleashing the Native Recommendation Potential: LLM-Based Generative Recommendation via Structured Term Identifiers](https://mlsanity.com/paper/2601.06798/) (2026)
- [Personalized Recommendation Systems using Multimodal, Autonomous, Multi Agent Systems](https://mlsanity.com/paper/2410.19855/) (2024)
- [Language Models as Semantic Augmenters for Sequential Recommenders](https://mlsanity.com/paper/2510.18046/) (2025)
- [What Matters in LLM-Based Feature Extractor for Recommender? A Systematic Analysis of Prompts, Models, and Adaptation](https://mlsanity.com/paper/2509.14979/) (2025)

## Built on by (most cited first, 2 of 2)

- [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)

## Abstract (arXiv)

High-quality representations are a core requirement for effective recommendation. In this work, we study the problem of LLM-based descriptor generation, i.e., keyphrase-like natural language item representation generation frameworks with minimal constraints on downstream applications. We propose AgenticTagger, a framework that queries LLMs for representing items with sequences of text descriptors. However, open-ended generation provides little control over the generation space, leading to high cardinality, low-performance descriptors that render downstream modeling challenging. To this end, AgenticTagger features two core stages: (1) a vocabulary-building stage in which a set of hierarchical, low-cardinality, and high-quality descriptors is identified, and (2) a vocabulary-assignment stage in which LLMs assign in-vocabulary descriptors to items. To effectively and efficiently ground vocabulary in the item corpus of interest, we design a multi-agent reflection mechanism in which an architect LLM iteratively refines the vocabulary guided by parallelized feedback from annotator LLMs that validate the vocabulary against item data. Experiments on public and private data show AgenticTagger brings consistent improvements across diverse recommendation scenarios, including generative and term-based retrieval, ranking, and controllability-oriented, critique-based recommendation.