Recommender System as Slow and Fast Thinkers

• URL: http://arxiv.org/abs/2609.02671v1
• Date: Wed, 02 Sep 2026 14:45:39 GMT
• Title: Recommender System as Slow and Fast Thinkers
• Abstract summary: textscDS-Frame is an adaptive fast--slow inference framework for sequential recommendation.<n>textscDS-Frame consistently improves representative sequential recommendation backbones.<n>This highlights the potential of adaptive inference for more efficient and robust recommendation.
• Score: 12.034704337954613
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sequential recommendation models are foundational to modern personalized services, yet their effectiveness varies substantially across heterogeneous user environments. In particular, static one-pass recommenders often perform well on common behavior patterns but degrade on operationally challenging user groups, such as users with longer histories or less mainstream item profiles. To address this limitation, we propose \textsc{DS-Frame}, an adaptive fast--slow inference framework for sequential recommendation. \textsc{DS-Frame} combines a Fast System for efficient routine prediction, a Slow System for iterative latent refinement, and a learned selector that routes each sample under a controllable computation budget. Experiments on five real-world datasets show that \textsc{DS-Frame} consistently improves representative sequential recommendation backbones, with larger gains on challenging groups and effective accuracy--efficiency trade-offs. This highlights the potential of adaptive inference for more efficient and robust recommendation. Code is available at \href{https://github.com/ZichenYuan233/Recommender-System-as-Slow-and-Fast-Thinkers}{this link}.

Related papers

• TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning [3.2829140652979647]
  Generative recommendation with Semantic IDs (SIDs) has emerged as a promising paradigm.<n>Existing methods apply a fixed inference strategy, either fast direct generation or slow chain-of-thought reasoning, uniformly across all user histories.<n>We propose Think Fast, Think Slow, Then Act, a framework that learns to adaptively allocate reasoning effort per user sequence.
  arXiv  Detail & Related papers  (2026-05-12T05:35:00Z)
• 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)
• Bi-Level Optimization for Generative Recommendation: Bridging Tokenization and Generation [42.09028908758132]
  Generative recommendation is emerging as a transformative paradigm by directly generating recommended items, rather than relying on matching.<n>Existing approaches treat the tokenizer to derive suitable item identifiers and the recommender based on those identifiers separately.<n>We propose BLOGER, a Bi-Level Optimization for GEnerative Recommendation framework, which explicitly models the interdependence between the tokenizer and the recommender.
  arXiv  Detail & Related papers  (2025-10-24T08:25:56Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• Embed Progressive Implicit Preference in Unified Space for Deep Collaborative Filtering [13.24227546548424]
  Generalized Neural Ordinal Logistic Regression (GNOLR) is proposed to capture the structured progression of user engagement.<n>GNOLR enhances predictive accuracy, captures the progression of user engagement, and simplifies the retrieval process.<n>Experiments on ten real-world datasets show that GNOLR significantly outperforms state-of-the-art methods in efficiency and adaptability.
  arXiv  Detail & Related papers  (2025-05-27T08:43:35Z)
• AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems [17.329692234349768]
  Agentic recommender systems are powered by Large Language Models (LLMs)<n>LLMs' advanced reasoning and role-playing capabilities enable autonomous, adaptive decision-making.<n>The field currently lacks standardized evaluation protocols to assess these methods.
  arXiv  Detail & Related papers  (2025-05-26T07:45:11Z)
• 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)
• Interactive Visualization Recommendation with Hier-SUCB [52.11209329270573]
  We propose an interactive personalized visualization recommendation (PVisRec) system that learns on user feedback from previous interactions.<n>For more interactive and accurate recommendations, we propose Hier-SUCB, a contextual semi-bandit in the PVisRec setting.
  arXiv  Detail & Related papers  (2025-02-05T17:14:45Z)
• Generative Recommender with End-to-End Learnable Item Tokenization [51.82768744368208]
  We introduce ETEGRec, a novel End-To-End Generative Recommender that unifies item tokenization and generative recommendation into a cohesive framework.<n>ETEGRec consists of an item tokenizer and a generative recommender built on a dual encoder-decoder architecture.<n>We develop an alternating optimization technique to ensure stable and efficient end-to-end training of the entire framework.
  arXiv  Detail & Related papers  (2024-09-09T12:11:53Z)
• Semantic Codebook Learning for Dynamic Recommendation Models [55.98259490159084]
  Dynamic sequential recommendation (DSR) can generate model parameters based on user behavior to improve personalization of sequential recommendation. It faces the challenges of large parameter search space and sparse and noisy user-item interactions, which reduces the applicability of the generated model parameters. The Semantic Codebook Learning for Dynamic Recommendation Models (SOLID) framework presents a significant advancement in DSR by effectively tackling these challenges.
  arXiv  Detail & Related papers  (2024-07-31T19:25:25Z)
• A Simple Yet Effective Approach for Diversified Session-Based Recommendation [28.980166530417645]
  We propose an end-to-end framework applied for every existing representative (accuracy-oriented) SBRS, called diversified category-aware attentive SBRS (DCA-SBRS) It consists of two novel designs: a model-agnostic diversity-oriented loss function, and a non-invasive category-aware attention mechanism. Our framework helps existing SBRSs achieve extraordinary performance in terms of recommendation diversity and comprehensive performance, without significantly deteriorating recommendation accuracy.
  arXiv  Detail & Related papers  (2024-03-30T06:21:56Z)
• AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender Systems [25.18963930580529]
  Reinforcement Learning (RL) has garnered increasing attention for its ability to optimize user retention in recommender systems.<n>This paper introduces a novel approach called textbfAdaptive textbfUser textbfRetention textbfOptimization (AURO) to address this challenge.
  arXiv  Detail & Related papers  (2023-10-06T02:45:21Z)
• HyperBandit: Contextual Bandit with Hypernewtork for Time-Varying User Preferences in Streaming Recommendation [11.908362247624131]
  Existing streaming recommender models only consider time as a timestamp. We propose a contextual bandit approach using hypernetwork, called HyperBandit. We show that the proposed HyperBandit consistently outperforms the state-of-the-art baselines in terms of accumulated rewards.
  arXiv  Detail & Related papers  (2023-08-14T14:04:57Z)

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.