mlsanityData to 14 Oct 2026

Shape Your Feed: An LLM-based Agentic System for Conversational Recommendation

arXiv 2608.06632 ↗First posted 6 Aug 2026cs.AIcited by 0

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

Abstract (arXiv)

Industrial recommendation systems predominantly adopt a passive ranking paradigm that infers user preferences from implicit behavioral signals (e.g., clicks, dwell time) rather than explicit, natural language inputs. As a result, users experience a persistent discrepancy between their explicit interests and what passive behavioral algorithms deliver, limiting their ability to express nuanced preferences or steer their feed in real time. To address this growing gap between how recommendations are optimized and how users wish to articulate their interests, we present Shape Your Feed (SYF), an LLM-based agentic recommendation framework that enables real-time, multimodal co-curation of content. SYF employs a three-tier architecture: (i) a Perception Flow that captures fine-grained user intent from text prompts, voice commands, and UI interactions; (ii) a Serving Flow that performs real-time agentic re-ranking and pruning of candidate items, grounded in a persistent Semantic Profile encoding evolving user preferences; and (iii) a Self-Evolution Flow that aligns system behavior with human judgments via Direct Preference Optimization (DPO) and an LLM-as-a-Judge ensemble. Offline evaluations show that SYF's alignment scoring module achieves 98.85% accuracy, substantially improving over strong few-shot baselines. Large-scale online A/B experiments on production traffic further demonstrate that SYF improves feed relevance and user sentiment, indicating a practical and scalable path toward interactive, user-steerable recommendation in industrial settings.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use. Builds on 22 of its 29 references that are in the map. First posted on arXiv 6 Aug 2026.

Builds on

22 of 29 references.

References · 22

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2018Self-Attentive Sequential Recommendationcited by 1,184
  4. 2017Neural Collaborative Filteringcited by 1,111
  5. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
  6. 2016Wide & Deep Learning for Recommender Systemscited by 747
  7. 2023A Survey on Large Language Models for Recommendationcited by 379
  8. 2019Deep Learning Recommendation Model for Personalization and Recommendation Systemscited by 327
  9. 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 189
  10. 2023LLMRec: Large Language Models with Graph Augmentation for Recommendationcited by 172
  11. 2020A Survey on Conversational Recommender Systemscited by 143
  12. 2020Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusioncited by 122
10 more
  1. 2021Advances and Challenges in Conversational Recommender Systems: A Surveycited by 118
  2. 2019Towards Knowledge-Based Recommender Dialog Systemcited by 113
  3. 2021Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Groundingcited by 106
  4. 2020Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Surveycited by 51
  5. 2025Bayesian Teaching Enables Probabilistic Reasoning in Large Language Modelscited by 37
  6. 2023A Large Language Model Enhanced Conversational Recommender Systemcited by 31
  7. 2024Retrieval-Augmented Conversational Recommendation with Prompt-based Semi-Structured Natural Language State Trackingcited by 18
  8. 2025Collaborative Retrieval for Large Language Model-based Conversational Recommender Systemscited by 16
  9. 2021Generating Usage-related Questions for Preference Elicitation in Conversational Recommender Systemscited by 10
  10. 2023Explicit Knowledge Graph Reasoning for Conversational Recommendationcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models
  2. 2023AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems
  3. 2026Rethinking Recommendation Paradigms: From Pipelines to Agentic Recommender Systems
  4. 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
  5. 2025A Survey on LLM-powered Agents for Recommender Systems
  6. 2026AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders
  7. 2026Do Recommendation Algorithms Work When Users Are LLM Agents? A Case Study on Moltbook
  8. 2023Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations