RECAP: Feedback-Driven Streaming Semantic User Profiles for Short-Video Recommendation

• URL: http://arxiv.org/abs/2607.15730v1
• Date: Fri, 17 Jul 2026 08:10:37 GMT
• Title: RECAP: Feedback-Driven Streaming Semantic User Profiles for Short-Video Recommendation
• Abstract summary: Language-based user profiles convert long behavioral histories into explicit semantic representations for recommendation.<n>We study this problem in real-world short-video recommendation, where user behaviors continuously arrive as streams and profiles must be incrementally updated under limited capacity.<n>We propose RECAP, an offline closed-loop framework for optimizing streaming structured semantic profiles with historical recommendation feedback.
• Score: 74.86562505934961
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language-based user profiles convert long behavioral histories into explicit semantic representations for recommendation. However, most profile generators are optimized in an open loop: they may summarize past behavior fluently, but are not directly trained to improve future recommendation. We study this problem in real-world short-video recommendation, where user behaviors continuously arrive as streams and profiles must be incrementally updated under limited capacity. This requires maintaining a consistent bounded profile state and constructing profile-targeted semantic feedback from industrial implicit behavior logs. We propose RECAP, an offline closed-loop framework for optimizing streaming structured semantic profiles with historical recommendation feedback. RECAP maintains each profile as a bounded structured memory by combining LLM-based semantic updates with deterministic lifecycle and capacity control. RECAP constructs profile-targeted semantic feedback by filtering label-consistent behavior pairs with an LLM judge and training a dual-tower evaluator whose matching score serves as a GRPO reward. Experiments on Kuaishou short-video data show that RECAP improves uAUC by 0.0084 and Recall@2000 by about 4.9% over the base generator. Further analyses confirm the benefits of feedback construction and policy optimization, and show more grounded refinement and user-level abstraction in profile updates. A seven-day online A/B test further shows a statistically significant 0.139% improvement in average application usage time per user.

Related papers

• Less Is Personal: Learning Minimal Sufficient User Profiles for Personalized Language Models [77.02066500576528]
  Enough is a method that iteratively appends behavioral records or emits STOP to construct profiles with adaptive lengths.<n>Enough consistently outperforms strong and retrieval-augmented baselines in both effectiveness and efficiency.
  arXiv  Detail & Related papers  (2026-09-08T03:09:19Z)
• RecoReward: Recommender-Guided Multimodal Description Generation for Recommendation [41.239756064223776]
  We introduce RecoReward, which uses behavior-derived rewards during training and preserves content-only inference.<n>We show that RecoReward trains the MLLM to produce item features that benefit downstream recommendation while retaining content-only serving.
  arXiv  Detail & Related papers  (2026-07-28T15:59:00Z)
• Prediction Is Not Memory: Dual-Timescale Gated Profile Writing for Persistent User Modeling [0.0]
  Persistent user profiles increasingly serve as reusable memory in recommender systems.<n>We formulate this boundary as selective profile-write control.<n>We instantiate the controller as SPW-Gate, a lightweight write-risk gate using long-term, short-term, and candidate-profile drift features.
  arXiv  Detail & Related papers  (2026-07-03T14:49:15Z)
• Long-Term Optimization for Large-Scale Generative Retrieval with Off-Policy REINFORCE [0.0]
  We formulate recommendation as a session-level sequential decision-making problem.<n>We introduce an autoregressive approach for training generative retrievers with off-policy REINFORCE on pre-collected data.
  arXiv  Detail & Related papers  (2026-07-02T23:13:36Z)
• LATTE: Forecasting Peer Anchored Preference Trajectories for Personalized LLM Generation [26.684846150915153]
  We propose LAtent Trajectory Tracking and Extrapolation (LATTE), a framework that represents personalization as forecasting a peer anchored relative preference state.<n>LATTE consistently outperforms retrieval, summary memory, static latent profiles, difference aware latent profiles, and soft prompt compression baselines.
  arXiv  Detail & Related papers  (2026-05-26T06:50:45Z)
• StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Streaming Scenarios [38.37032285408029]
  We introduce StreamProfileBench, a benchmark for fine-grained streaming user profiling.<n>We curate a highly authentic dataset of over 120,000 posts from 7,000+ real users across five diverse platforms.<n>By leveraging the temporal correlation of user interests, we propose a novel, annotation-free evaluation framework.
  arXiv  Detail & Related papers  (2026-05-25T12:10:15Z)
• Prompt Tuning as User Inherent Profile Inference Machine [68.16976932088708]
  We propose UserIP-Tuning, which uses prompt-tuning to infer user profiles.<n>UserIP-Tuning outperforms state-of-the-art recommendation algorithms.<n>The presented solution has been deployed in Huawei AppGallery's Explore page since May 2025.
  arXiv  Detail & Related papers  (2024-08-13T02:25:46Z)
• 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)
• Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems [0.0]
  Reinforcement learning (RL) recommender systems often rely on static datasets that fail to capture the fluid, ever changing nature of user preferences in real-world scenarios.<n>We introduce Lusifer, an LLM-based simulation environment designed to generate dynamic, realistic user feedback for RL-based recommender training.
  arXiv  Detail & Related papers  (2024-05-22T05:43:15Z)
• RLVF: Learning from Verbal Feedback without Overgeneralization [94.19501420241188]
  We study the problem of incorporating verbal feedback without such overgeneralization. We develop a new method Contextualized Critiques with Constrained Preference Optimization (C3PO) Our approach effectively applies verbal feedback to relevant scenarios while preserving existing behaviors for other contexts.
  arXiv  Detail & Related papers  (2024-02-16T18:50:24Z)
• Recommender Transformers with Behavior Pathways [50.842316273120744]
  We build the Recommender Transformer (RETR) with a novel Pathway Attention mechanism. We empirically verify the effectiveness of RETR on seven real-world datasets.
  arXiv  Detail & Related papers  (2022-06-13T08:58:37Z)

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.