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

• URL: http://arxiv.org/abs/2608.06632v1
• Date: Thu, 06 Aug 2026 22:54:16 GMT
• Title: Shape Your Feed: An LLM-based Agentic System for Conversational Recommendation
• Abstract summary: Shape Your Feed (SYF) is an agentic recommendation framework that enables real-time, multimodal co-curation of content.<n>SYF employs a three-tier architecture: (i) a Perception Flow that captures 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; and (iii) a Self-Evolution Flow that aligns system behavior with human judgments.
• Score: 18.690831845179797
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback [46.88440233575785]
  We advocate for prioritizing explicit context feedback in the next generation of Large Language Models (LLMs)-based RecSys.<n>We aim to foster more personalized, transparent, and explainable RecSys online platforms.
  arXiv  Detail & Related papers  (2026-05-27T22:10:33Z)
• RecNet: Self-Evolving Preference Propagation for Agentic Recommender Systems [109.9061591263748]
  RecNet is a self-evolving preference propagation framework for recommender systems.<n>It proactively propagates real-time preference updates across related users and items.<n>In the backward phase, the feedback-driven propagation optimization mechanism simulates a multi-agent reinforcement learning framework.
  arXiv  Detail & Related papers  (2026-01-29T12:14:31Z)
• Effectiveness of LLMs in Temporal User Profiling for Recommendation [2.7543979996398513]
  This paper examines the capability of leveraging Large Language Models (LLMs) to capture temporal dynamics.<n>Our observations suggest that while LLMs tend to improve recommendation quality in domains with more active user engagement, their benefits appear less pronounced in sparser environments.
  arXiv  Detail & Related papers  (2025-10-31T18:28:40Z)
• Interactive Recommendation Agent with Active User Commands [35.77744269746443]
  We introduce the Interactive Recommendation Feed (IRF), a pioneering paradigm that enables natural language commands within mainstream recommendation feeds.<n>Unlike traditional systems that confine users to passive implicit behavioral influence, IRF empowers active explicit control over recommendation policies through real-time linguistic commands.<n> RecBot shows significant improvements in both user satisfaction and business outcomes.
  arXiv  Detail & Related papers  (2025-09-25T15:38:27Z)
• What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context [56.590259941275434]
  RecPO is a preference optimization framework for sequential recommendation.<n>It exploits adaptive reward margins based on inferred preference hierarchies and temporal signals.<n>It mirrors key characteristics of human decision-making: favoring timely satisfaction, maintaining coherent preferences, and exercising discernment under shifting contexts.
  arXiv  Detail & Related papers  (2025-06-02T21:09:29Z)
• Multi-agents based User Values Mining for Recommendation [52.26100802380767]
  We propose a zero-shot multi-LLM collaborative framework for effective and accurate user value extraction.<n>We apply text summarization techniques to condense item content while preserving essential meaning.<n>To mitigate hallucinations, we introduce two specialized agent roles: evaluators and supervisors.
  arXiv  Detail & Related papers  (2025-05-02T04:01:31Z)
• Towards Explainable Temporal User Profiling with LLMs [3.719862246745416]
  We leverage large language models (LLMs) to generate natural language summaries of users' interaction histories.<n>Our framework not only models temporal user preferences but also produces natural language profiles that can be used to explain recommendations in an interpretable manner.
  arXiv  Detail & Related papers  (2025-05-01T22:02:46Z)
• Reasoning over User Preferences: Knowledge Graph-Augmented LLMs for Explainable Conversational Recommendations [58.61021630938566]
  Conversational Recommender Systems (CRSs) aim to provide personalized recommendations by capturing user preferences through interactive dialogues.<n>Current CRSs often leverage knowledge graphs (KGs) or language models to extract and represent user preferences as latent vectors, which limits their explainability.<n>We propose a plug-and-play framework that synergizes LLMs and KGs to reason over user preferences, enhancing the performance and explainability of existing CRSs.
  arXiv  Detail & Related papers  (2024-11-16T11:47:21Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)
• Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts [95.09994361995389]
  Relative Preference Optimization (RPO) is designed to discern between more and less preferred responses derived from both identical and related prompts. RPO has demonstrated a superior ability to align large language models with user preferences and to improve their adaptability during the training process.
  arXiv  Detail & Related papers  (2024-02-12T22:47:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.