REVIEW 5 cited by
A Survey of Personalization: From RAG to Agent
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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. Relevant papers and resources are continuously updated at https://github.com/Applied-Machine-Learning-Lab/Awesome-Personalized-RAG-Agent.
Forward citations
Cited by 5 Pith papers
-
ComBodied Agents: a New Paradigm of Human-Centric Agentic AI
A new human-centric agentic AI paradigm, Combodied Agents, organizes perception, memory, prediction, and intervention around the evolving human state and agency over time.
-
Beyond Retrieval: Analytic Memory for Multimodal Agents
ADAMM induces queryable analytic tables from multimodal interaction histories and combines them with semantic retrieval, improving benchmark accuracy by up to 11.3 points over memory baselines.
-
DeepTutor: Towards Agentic Personalized Tutoring
DeepTutor proposes an agent-native framework that uses a hybrid personalization engine and closed tutoring loop to deliver adaptive, citation-grounded tutoring while introducing TutorBench for evaluation.
-
UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization
The paper introduces UrbanMind, a tool-enhanced RAG framework with a multilevel optimization formulation for continual adaptation in urban AI, but offers only qualitative prototype results.
-
SELF: Surrogate-light Feature Selection with Large Language Models in Deep Recommender Systems
SELF combines LLM-generated feature rankings with a lightweight learnable refinement to select features in deep recommender systems, and reports the best AUC/Logloss among the compared baselines on three public datasets.
Discussion (0). Continue with ORCID to comment.