Trajectory-Based Recommender Systems as Control Systems

• URL: http://arxiv.org/abs/2606.22957v1
• Date: Mon, 22 Jun 2026 07:36:21 GMT
• Title: Trajectory-Based Recommender Systems as Control Systems
• Abstract summary: Tray-Based Recommender Systems (TBRS) are a subfield for which many related studies exist, yet still lacking a common framework.<n>We argue that Control Theory provides an appropriate foundation for formalizing and solving S problems.<n>We show how Educational Recommender Systems (ERS), intrinsically long-term and goal-driven, can be modeled within the proposed Control Theory framework.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recommender Systems (RS) are a key research domain and play an increasing role in our content-overwhelmed lives. In this paper, we explore Trajectory-Based Recommender Systems (TBRS), a subfield for which many related studies exist, yet still lacking a common framework. We argue that Control Theory provides an appropriate foundation for formalizing and solving TBRS problems. TBRS, sometimes named Long Term goal Recommender Systems, share core principles with classical RS, but at their core lies the concept of a trajectory, a defining element that makes these systems a singular category. To date, most RSs that include a notion of goal or long-term objective, when this goal is explicit, have not been recognized as having specific characteristics that make them worth regrouping under a dedicated field of research. We review related work, observe how they differ from already conceptualized RSs, and sketch the foundations of a possible theoretical framework based on control theory. Finally, we show how Educational Recommender Systems (ERS), intrinsically long-term and goal-driven, can be modeled within the proposed TBRS framework.

Related papers

• RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards [76.17893114021757]
  Deep research systems that plan, search, evaluate evidence, and synthesize long-form reports lack ground-truth answers and span many tool-augmented decisions.<n>In this work, we argue that rubrics should serve not merely as final-answer evaluators, but as the shared interface that structures policy execution, judge feedback, and agent memory.<n>We introduceEM, a rubric-guided reinforcement learning framework that combines stagewise policy decomposition with reflection-based meta-policy evolution.
  arXiv  Detail & Related papers  (2026-05-11T17:40:38Z)
• Curr-RLCER:Curriculum Reinforcement Learning For Coherence Explainable Recommendation [5.971765441013208]
  Curr-RLCER is a reinforcement learning framework for explanation coherent recommendation with dynamic rating alignment.<n>It employs curriculum learning, transitioning from basic predictions to open-ended recommendation explanation generation.<n>The experimental results on three explainable recommendation datasets indicate that the proposed framework is effective.
  arXiv  Detail & Related papers  (2026-04-07T02:25:36Z)
• Knowledge-Graph Based RAG System Evaluation Framework [27.082302648704708]
  Large language models (LLMs) has become a significant research focus.<n>Retrieval Augmented Generation (RAG) greatly enhances generated content's reliability and relevance.<n> evaluating RAG systems remains a challenging task.
  arXiv  Detail & Related papers  (2025-10-02T20:36:21Z)
• Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs [69.10441885629787]
  Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge.<n>It falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts.<n>This survey synthesizes both strands under a unified reasoning-retrieval perspective.
  arXiv  Detail & Related papers  (2025-07-13T03:29:41Z)
• A Methodology for Evaluating RAG Systems: A Case Study On Configuration Dependency Validation [6.544757635738911]
  Retrieval-augmented generation (RAG) is an umbrella of different components, design decisions, and domain-specific adaptations. There is currently no generally accepted methodology for RAG evaluation despite a growing interest in this technology. We propose a first blueprint of a methodology for a sound and reliable evaluation of RAG systems.
  arXiv  Detail & Related papers  (2024-10-11T13:36:13Z)
• A Comprehensive Review of Recommender Systems: Transitioning from Theory to Practice [12.047370735494601]
  Recommender Systems (RS) play an integral role in enhancing user experiences by providing personalized item suggestions.<n>This survey reviews the progress in RS inclusively from 2017 to 2024.<n>The primary goal of this survey is to bridge theory with practice.
  arXiv  Detail & Related papers  (2024-07-18T17:00:53Z)
• Concept -- An Evaluation Protocol on Conversational Recommender Systems with System-centric and User-centric Factors [68.68418801681965]
  We propose a new and inclusive evaluation protocol, Concept, which integrates both system- and user-centric factors. Our protocol, Concept, serves a dual purpose. First, it provides an overview of the pros and cons in current CRS models. Second, it pinpoints the problem of low usability in the "omnipotent" ChatGPT and offers a comprehensive reference guide for evaluating CRS.
  arXiv  Detail & Related papers  (2024-04-04T08:56:48Z)
• Set-to-Sequence Ranking-based Concept-aware Learning Path Recommendation [49.85548436111153]
  We propose a novel framework named Set-to-Sequence Ranking-based Concept-aware Learning Path Recommendation (SRC) SRC formulates the recommendation task under a set-to-sequence paradigm. We conduct extensive experiments on two real-world public datasets and one industrial dataset.
  arXiv  Detail & Related papers  (2023-06-07T08:24:44Z)
• Learning Rational Subgoals from Demonstrations and Instructions [71.86713748450363]
  We present a framework for learning useful subgoals that support efficient long-term planning to achieve novel goals. At the core of our framework is a collection of rational subgoals (RSGs), which are essentially binary classifiers over the environmental states. Given a goal description, the learned subgoals and the derived dependencies facilitate off-the-shelf planning algorithms, such as A* and RRT.
  arXiv  Detail & Related papers  (2023-03-09T18:39:22Z)
• Deep Conversational Recommender Systems: A New Frontier for Goal-Oriented Dialogue Systems [54.06971074217952]
  Conversational Recommender System (CRS) learns and models user's preferences through interactive dialogue conversations. Deep learning approaches are applied to CRS and have produced fruitful results.
  arXiv  Detail & Related papers  (2020-04-28T02:20:42Z)

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.