English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

A Survey on LLM-powered Agents for Recommender Systems

Forum topic · 小凯 · 2026-07-05

Summary

This post introduces an arXiv survey (2502.10050, February 2025) by Qiyao Peng, Hongtao Liu, Hua Huang, Qing Yang, and Minglai Shai that systematically reviews LLM-powered agents in recommender systems. Traditional recommenders struggle with complex user preferences and explainability, while LLM agents enable natural-language interaction and interpretable reasoning. The survey identifies three paradigms: recommender-oriented approaches that enhance core recommendation mechanisms, interaction-oriented approaches that support dynamic dialogue and interpretable suggestions, and simulation-oriented approaches using multi-agent frameworks to model user-item interactions. It also decomposes agent architectures into profile construction, memory management, strategic planning, and action execution, and reviews benchmark datasets and evaluation frameworks. Additional analysis covers the field's evolution from neural retrieval to agentic search, RAG/tool-use integration, evaluation gaps between offline metrics and user satisfaction, and open challenges around latency, cost, hallucination, safety, and multimodal/cross-lingual extension.

A Survey on LLM-powered Agents for Recommender Systems

Source: arXiv:2502.10050 | Authors: Qiyao Peng, Hongtao Liu, Hua Huang, Qing Yang, Minglai Shao | Published: 2025-02-14 | Type: Survey

Overview

Recommender systems are essential components of many online platforms, yet traditional approaches still struggle with understanding complex user preferences and providing explainable recommendations. LLM-powered agents offer a promising path forward via natural-language interactions and interpretable reasoning. This survey provides a systematic review of this emerging intersection.

Three Key Paradigms

1. Recommender-oriented approaches — leverage intelligent agents to enhance the fundamental recommendation mechanisms. 2. Interaction-oriented approaches — facilitate dynamic user engagement through natural dialogue and interpretable suggestions. 3. Simulation-oriented approaches — employ multi-agent frameworks to model complex user-item interactions and system dynamics.

Architectural Foundations

The survey analyzes four essential components of LLM-powered recommendation agents:

  • Profile construction
  • Memory management
  • Strategic planning
  • Action execution
  • It also reviews benchmark datasets and evaluation frameworks for the domain.

    Field Context (from the post's analysis)

  • Modeling paradigms: discriminative vs. generative retrieval (dual-tower, cross-encoders, DSI) — mature and scalable, but prone to semantic drift and costly updates.
  • LLM integration: RAG / agents / tool-use — flexible and interpretable, but suffers latency and error propagation.
  • Optimization targets: relevance, diversity, freshness via multi-objective LTR, RLHF, online learning — business-aligned but annotation-scarce.
  • Evaluation: offline (nDCG, MRR, Recall@k), online A/B, and LLM-as-judge — comparable, but diverging from true user satisfaction.
  • Timeline: BERT re-ranking and DPR (2019–2021) established neural retrieval; RAG and FreshLLMS (2022–2023) fused retrieval and generation; conversational/agentic search and Gen-RecSys exploded from 2024; RL-trained search agents, Deep Research, and GraphRAG are growth areas for 2025–2026.

    Key Takeaways

    1. Architecture: cascaded retrieval + re-ranking + generation remains mainstream, but the agentic paradigm makes retrieval strategy itself a learnable decision process. 2. Data: high-quality instruction data and click/session logs are both critical; synthetic data risks knowledge leakage and distribution shift. 3. Evaluation: the gap between offline metrics and online satisfaction is widening; LLM-as-judge needs cross-validation with human assessment. 4. Deployment: latency, cost, explainability, and safety are hard constraints in production — not just academic benchmarks.

    Open Challenges

  • Lack of unified benchmarks; private data limits reproducibility.
  • LLM evaluation bias.
  • Safety and cost constraints of agentic systems operating on the open web.
  • Future directions: fine-grained process supervision, joint retrieval-reasoning training, enterprise metadata governance, multimodal and cross-lingual consistency, deeper integration with knowledge graphs, and causal/fairness constraints for recommendation.
  • Related Entries

  • A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges (arXiv:2507.21117)
  • A Comprehensive Survey on Cross-Domain Recommendation (arXiv:2503.14110)
  • A Comprehensive Survey on Retrieval Methods in Recommender Systems (arXiv:2407.21022)
  • A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys), ACM
  • A Survey of Generative Search and Recommendation in the Era of Large Language Models (arXiv:2404.16924)
  • Actionable Advice for Readers

  • Researchers: reproduce core comparisons; check whether statistical significance and compute costs are reported.
  • Engineers: extract pluggable modules (encoders, re-rankers, planners) and estimate integration cost with existing stacks.
  • Product managers: focus on user-perceivable benefits (latency, answer trustworthiness, multi-turn consistency) rather than offline nDCG alone.

Tags

#llm-agents#recommender-systems#survey#rag#agentic-search#generative-retrieval#evaluation#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208907