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

A Survey of Personalization: From RAG to Agent (arXiv 2504.10147)

Forum topic · 小凯 · 2026-07-05

Summary

This arXiv survey (2504.10147, April 2025) systematically examines personalization in modern AI systems across three core stages of Retrieval-Augmented Generation (RAG): pre-retrieval, retrieval, and generation. The authors, led by Xiaopeng Li and Pengyue Jia, then extend the analysis to Personalized LLM-based Agents, which augment traditional RAG with agentic capabilities including user understanding, personalized planning and execution, and dynamic generation. The survey provides formal definitions, reviews recent literature, and summarizes key datasets and evaluation metrics such as nDCG, MRR, LLM-as-judge, and A/B testing. It also traces the evolution of neural retrieval from dense retrieval and late interaction (ColBERT) to generative IR and agentic search, where retrieval becomes a learnable sequential decision process. Open challenges include benchmark scarcity, evaluation credibility, latency and cost constraints, hallucination and safety risks, and cross-lingual/multimodal generalization. Relevant papers are continuously updated at the linked GitHub repository.

A Survey of Personalization: From RAG to Agent

Overview

  • Paper: A Survey of Personalization: From RAG to Agent
  • Authors: Xiaopeng Li, Pengyue Jia, Derong Xu, Yi Wen, Yingyi Zhang, Wenlin Zhang, et al. (14 authors total)
  • Published: 2025-04-14
  • Source: https://arxiv.org/abs/2504.10147
  • Type: Survey
  • Resources: https://github.com/Applied-Machine-Learning-Lab/Awesome-Personalized-RAG-Agent
  • Abstract (original)

    > Personalization has become an essential capability in modern AI systems, enabling customized interactions that align with individual user preferences, contexts, and goals. Recent research has increasingly concentrated on Retrieval-Augmented Generation (RAG) frameworks and their evolution into more advanced agent-based architectures within personalized settings to enhance user satisfaction. Building on this foundation, this survey systematically examines personalization across the three core stages of RAG: pre-retrieval, retrieval, and generation. Beyond RAG, we further extend its capabilities into the realm of Personalized LLM-based Agents, which enhance traditional RAG systems with agentic functionalities, including user understanding, personalized planning and execution, and dynamic generation. For both personalization in RAG and agent-based personalization, we provide formal definitions, conduct a comprehensive review of recent literature, and summarize key datasets and evaluation metrics. Additionally, we discuss fundamental challenges, limitations, and promising research directions in this evolving field.

    Key Points

  • Unified perspective: Consolidates fragmented personalization research across RAG and agent-based architectures into a comparable framework.
  • Component decomposition: Clearly breaks down method components — representation learning, retrievers, rerankers, planners, generators, and feedback mechanisms — to ease engineering adoption.
  • Taxonomy: Organizes work by modeling paradigm (discriminative vs. generative retrieval), LLM integration (RAG / Agent / tool-use), optimization objectives (relevance, diversity, freshness), and evaluation (offline, online, human).
  • Datasets and metrics: Summarizes benchmarks such as MS MARCO, BEIR, and Natural Questions, plus metrics like nDCG@10, MRR, Recall@k, LLM-as-judge, and A/B testing.
  • Research Evolution Timeline

  • 2019–2021: BERT reranking and DPR establish neural retrieval foundations.
  • 2022–2023: RAG and FreshLLM drive retrieval-generation fusion.
  • 2024: Conversational/agentic search and generative recommender systems (Gen-RecSys) explode.
  • 2025–2026: RL-trained search agents, Deep Research, and GraphRAG become new growth fronts.
  • Main Retrieval Paradigms Compared

  • Dense retrieval: High recall, low latency; suitable for first-stage retrieval; sensitive to domain shift and long-tail queries.
  • Late interaction (e.g., ColBERT): Higher precision but larger index footprint.
  • Generative IR: Directly "generates" documents or docids, simplifying cascades but complicating index updates.
  • Agentic search: Models search as sequential decision-making, enabling multi-hop reasoning and self-reflection.
  • Insights for Search, Recommendation, and Personalization

    1. Architecture: Cascaded retrieval + reranking + generation remains mainstream, but the agentic paradigm makes retrieval count and strategy themselves learnable. 2. Data: High-quality instruction data and click/session logs are both critical; synthetic data requires protection against 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 evaluation. 4. Production: Latency, cost, explainability, and safety are hard constraints for industrial deployment — academic benchmarks alone are insufficient.

    Open Problems and Future Directions

  • Lack of unified benchmarks; private data is hard to reproduce.
  • Evaluation biases in LLM judges; safety and cost constraints of agentic systems on the open web.
  • Promising directions: finer-grained process supervision, joint retrieval-reasoning training, enterprise metadata governance, and multimodal/cross-lingual consistency.
  • Engineering Checklist

    | Item | Question | Suggestion | |------|----------|------------| | Data | Does training/indexing data contain PII? How are versions managed? | Partitioned indexes, anonymization, rollback-capable embedding versions | | Latency | What is the p99 budget? How many retrieval steps? | Cascade + early stopping, query caching, async reranking | | Quality | Do offline gains translate to online CTR/satisfaction? | Interleaving experiments, human audits, citation verification | | Safety | Does open retrieval introduce poisoning/bias? | Source whitelists, adversarial detection, output filtering | | Cost | Per-query token and GPU usage? | Small-model routing, distillation, hybrid sparse+dense retrieval |

    Glossary

  • IR: Information Retrieval
  • RAG: Retrieval-Augmented Generation
  • LTR: Learning to Rank
  • nDCG: Normalized Discounted Cumulative Gain, a ranking quality metric
  • Agentic Search: Paradigm modeling search as sequential decisions and tool calls
  • Gen-IR: Generative Information Retrieval
  • References

  • Original paper: A Survey of Personalization: From RAG to Agent — https://arxiv.org/abs/2504.10147
  • Awesome list: https://github.com/Applied-Machine-Learning-Lab/Awesome-Personalized-RAG-Agent

Tags

#rag#personalization#llm-agents#survey#information-retrieval#recommendation-systems#agentic-search#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/178208793