mlsanityData to 7 Oct 2026

Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems

arXiv 2607.04433 ↗First posted 5 Jul 2026cs.IR cs.CLcited by 3

On the map: LLM agents and tool use → Agentic recommender systems

Abstract (arXiv)

The rapid integration of large language model-based agents into recommender systems has driven a shift from static, ranking-based pipelines toward autonomous and interactive systems that can reason, plan, and act. This survey provides a comprehensive overview of this emerging landscape by introducing a unified taxonomy grounded in the level of autonomy and three core paradigms of agentic recommender systems: agent-assisted recommendation, agent-as-recommender, and agent-as-user-simulator. The autonomy framework organizes existing methods along increasing capabilities in proactivity, context awareness, interaction flexibility, and adaptivity. Building on this framework, the survey analyzes how each paradigm adopts different agentic architectures and how agents enhance key components such as profiles, memory, tool use, workflows, and optimization mechanisms. We further examine evaluation methodologies for agentic recommendation, covering automated metrics, LLM-based judging, and simulation-based assessment, and discuss their limitations in capturing reasoning quality, user experience, and system behavior. Beyond existing evaluation protocols, we further discuss unresolved issues in evaluating agentic recommender systems, including trajectory-level assessment, agent contribution analysis, and calibration of user simulation. Lastly, the survey outlines open challenges in lifelong user modeling, contextual abstraction, multimodal alignment, controllability, trustworthiness, privacy, scalability, and efficiency. Together, these analyses establish a unified foundation for understanding the current progress of agentic recommender systems and highlight promising opportunities for developing more autonomous, reliable, and human-aligned recommendation agents.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use. Builds on 120 of its 153 references that are in the map. First posted on arXiv 5 Jul 2026.

Builds on

120 of 153 references.

Closest ancestors · 48

Same direction, newest first

  1. 2026Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents10 Feb
  2. 2026Internalizing Multi-Agent Reasoning for Accurate and Efficient LLM-based Recommendation10 Feb
  3. 2026AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders9 Feb
  4. 2026AgenticTagger: Structured Item Representation for Recommendation with LLM Agents5 Feb
  5. 2026RecNet: Self-Evolving Preference Propagation for Agentic Recommender Systems29 Jan
  6. 2026LLMs as Orchestrators: Constraint-Compliant Multi-Agent Optimization for Recommendation Systems27 Jan
  7. 2026PCN-Rec: Agentic Proof-Carrying Negotiation for Reliable Governance-Constrained Recommendation14 Jan
  8. 2026MemRec: Collaborative Memory-Augmented Agentic Recommender System13 Jan
  9. 2026Exploring Recommender System Evaluation: A Multi-Modal User Agent Framework for A/B Testing8 Jan
  10. 2026ScienceDB AI: An LLM-Driven Agentic Recommender System for Large-Scale Scientific Data Sharing Services3 Jan
  11. 2026AlignUSER: Human-Aligned LLM Agents via World Models for Recommender System Evaluation2 Jan
  12. 2025CogRec: A Cognitive Recommender Agent Fusing Large Language Models and Soar for Explainable Recommendation30 Dec
36 more
  1. 2025Multi-Agent Collaborative Filtering: Orchestrating Users and Items for Agentic Recommendations23 Nov
  2. 2025SRLF: An Agent-Driven Set-Wise Reflective Learning Framework for Sequential Recommendation14 Nov
  3. 2025MARC: Multimodal and Multi-Task Agentic Retrieval-Augmented Generation for Cold-Start Recommender System11 Nov
  4. 2025MADREC: A Multi-Aspect Driven LLM Agent for Explainable and Adaptive Recommendation15 Oct
  5. 2025AgentDR: Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents7 Oct
  6. 2025AgentRec: Next-Generation LLM-Powered Multi-Agent Collaborative Recommendation with Adaptive Intelligence2 Oct
  7. 2025Temporal-Aware User Behaviour Simulation with Large Language Models for Recommender Systems21 Sep
  8. 2025RecoWorld: Building Simulated Environments for Agentic Recommender Systems12 Sep
  9. 2025Cloud-Device Collaborative Agents for Sequential Recommendation1 Sep
  10. 2025STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning26 Aug
  11. 2025Collab-REC: An LLM-based Agentic Framework for Balancing Recommendations in Tourism20 Aug
  12. 2025AdaptJobRec: Enhancing Conversational Career Recommendation through an LLM-Powered Agentic System19 Aug
  13. 2025Agent0: Leveraging LLM Agents to Discover Multi-value Features from Text for Enhanced Recommendations25 Jul
  14. 2025The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems2 Jul
  15. 2025Rethinking Group Recommender Systems in the Era of Generative AI: From One-Shot Recommendations to Agentic Group Decision Support1 Jul
  16. 2025Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent30 Jun
  17. 2025ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation27 Jun
  18. 2025CARTS: Collaborative Agents for Recommendation Textual Summarization21 Jun
  19. 2025Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent17 Jun
  20. 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems26 May
  21. 2025Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems22 May
  22. 2025A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms23 Apr
  23. 2025Simulating Filter Bubble on Short-video Recommender System with Large Language Model Agents23 Mar
  24. 2025Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models20 Mar
  25. 2025A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval7 Mar
  26. 2025iAgent: LLM Agent as a Shield between User and Recommender Systems20 Feb
  27. 2025AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations19 Feb
  28. 2025A Survey on LLM-powered Agents for Recommender Systems14 Feb
  29. 2024Agentic Feedback Loop Modeling Improves Recommendation and User Simulation26 Oct
  30. 2024MAS4POI: a Multi-Agents Collaboration System for Next POI Recommendation5 Sep
  31. 2024MACRec: a Multi-Agent Collaboration Framework for Recommendation23 Feb
  32. 2024A Multi-Agent Conversational Recommender System2 Feb
  33. 2023AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems13 Oct
  34. 2023Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations31 Aug
  35. 2023RecMind: Large Language Model Powered Agent For Recommendation28 Aug
  36. 2023RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents19 Aug

Other references · 72

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  7. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  8. 2023A Survey on Large Language Models for Recommendationcited by 378
  9. 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 188
  10. 2023User Behavior Simulation with Large Language Model based Agentscited by 136
  11. 2023Large Language Models for Generative Recommendation: A Survey and Visionary Discussionscited by 72
  12. 2024Large Language Models Empowered Personalized Web Agentscited by 64
38 more
  1. 2024A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)cited by 58
  2. 2025Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendationcited by 56
  3. 2024Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learningcited by 51
  4. 2024Evaluating Large Language Models as Generative User Simulators for Conversational Recommendationcited by 45
  5. 2024CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendationcited by 44
  6. 2024LLM-Powered User Simulator for Recommender Systemcited by 38
  7. 2023DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendationcited by 27
  8. 2025G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendationcited by 26
  9. 2024How Reliable is Your Simulator? Analysis on the Limitations of Current LLM-based User Simulators for Conversational Recommendationcited by 25
  10. 2024Large Language Models as Recommender Systems: A Study of Popularity Biascited by 25
  11. 2024Large Language Models are Learnable Planners for Long-Term Recommendationcited by 24
  12. 2025CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agentcited by 22
  13. 2024RecAI: Leveraging Large Language Models for Next-Generation Recommender Systemscited by 20
  14. 2024Retrieval-Augmented Conversational Recommendation with Prompt-based Semi-Structured Natural Language State Trackingcited by 18
  15. 2024Federated Recommendation via Hybrid Retrieval Augmented Generationcited by 16
  16. 2025R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systemscited by 16
  17. 2024Recommendation with Generative Modelscited by 13
  18. 2023Automated Interactive Domain-Specific Conversational Agents that Understand Human Dialogscited by 12
  19. 2024A LLM-based Controllable, Scalable, Human-Involved User Simulator Framework for Conversational Recommender Systemscited by 12
  20. 2024Knowledge Graph Enhanced Language Agents for Recommendationcited by 11
  21. 2025RecUserSim: A Realistic and Diverse User Simulator for Evaluating Conversational Recommender Systemscited by 11
  22. 2025The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exitcited by 10
  23. 2025Graph Retrieval-Augmented LLM for Conversational Recommendation Systemscited by 10
  24. 2025Interactive Recommendation Agent with Active User Commandscited by 10
  25. 2024Large Language Model Simulator for Cold-Start Recommendationcited by 9
  26. 2024Re2LLM: Reflective Reinforcement Large Language Model for Session-based Recommendationcited by 8
  27. 2024Beyond Retrieval: Generating Narratives in Conversational Recommender Systemscited by 8
  28. 2025Stealthy LLM-Driven Data Poisoning Attacks Against Embedding-Based Retrieval-Augmented Recommender Systemscited by 8
  29. 2025VRAgent-R1: Boosting Video Recommendation with MLLM-based Agents via Reinforcement Learningcited by 8
  30. 2026AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systemscited by 8
  31. 2025MAP: Multi-user Personalization with Collaborative LLM-powered Agentscited by 7
  32. 2025Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendationcited by 7
  33. 2025Diagnostic-Guided Dynamic Profile Optimization for LLM-based User Simulators in Sequential Recommendationcited by 7
  34. 2024RAMO: Retrieval-Augmented Generation for Enhancing MOOCs Recommendationscited by 6
  35. 2024Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systemscited by 5
  36. 2025RALLRec: Improving Retrieval Augmented Large Language Model Recommendation with Representation Learningcited by 5
  37. 2025RALLRec+: Retrieval Augmented Large Language Model Recommendation with Reasoningcited by 5
  38. 2024MoRE: A Mixture of Reflectors Framework for Large Language Model-Based Sequential Recommendationcited by 4

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026SR-Agent: An Experience-Driven Agentic Framework for Post-Ranking Strategy Refinement in E-Commerce Recommendationcited by 0
  2. 2026The User Asks, Platforms Compete: How Agentic Recommendation Markets Take Shapecited by 0
  3. 2026Self-Evolving Memory for Generative Recommendationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Who Are We Recommending To? Recommender Systems in the Agentic Web
  2. 2026Rethinking Recommendation Paradigms: From Pipelines to Agentic Recommender Systems
  3. 2026AgenticRec: A Recommendation-Oriented Agentic Framework with Progressive Tool-Integrated Reasoning Optimization
  4. 2026EvoRec: Self Evolving Agentic Recommender Systems
  5. 2026CARA: Cognitive Adaptive Recommendation Agent
  6. 2023On Generative Agents in Recommendation
  7. 2026AURA: Agentic Diagnosis and Refinement for Production Recommender Systems at Scale
  8. 2026RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation