Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search

• URL: http://arxiv.org/abs/2609.00618v2
• Date: Wed, 02 Sep 2026 03:17:33 GMT
• Title: Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search
• Abstract summary: We propose DREAMS, a novel tree-structured context modeling framework that captures user preference evolution throughout multi-turn interactions.<n> DREAMS supports the two fundamental objectives of Conversational Recommendation Systems (CRSs): preference elicitation and preference exploitation.
• Score: 78.39993606731646
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate the role of conversational context modeling in user preference tracking for Conversational Recommendation Systems (CRSs). In this regard, we propose DREAMS, a novel tree-structured context modeling framework that explicitly captures user preference evolution throughout multi-turn interactions. DREAMS introduces two specialized node types to support the two fundamental objectives of CRSs: preference elicitation and preference exploitation. Specifically, elicitation nodes leverage Monte Carlo Tree Search (MCTS) to strategically explore conversational actions and infer latent user preferences, while exploitation nodes employ LLM-based refinement to transform the tracked preference state into structured retrieval queries for recommendation. Extensive experiments on benchmark datasets demonstrate the effectiveness of DREAMS and its design.

Related papers

• Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation [16.06642257317271]
  Situated conversational recommendation (SCR) uses visual scenes grounded in specific environments and natural language dialogue to deliver contextually appropriate recommendations.<n>We propose situated preference reasoning (SiPeR), a novel framework that integrates two core mechanisms.<n> experiments on two representative benchmarks demonstrate SiPeR's superiority in both recommendation accuracy and response generation quality.
  arXiv  Detail & Related papers  (2026-04-22T16:39:52Z)
• REGEN: A Dataset and Benchmarks with Natural Language Critiques and Narratives [4.558818396613368]
  We extend the Amazon Product Reviews dataset by inpainting two key natural language features.<n>The narratives include product endorsements, purchase explanations, and summaries of user preferences.
  arXiv  Detail & Related papers  (2025-03-14T23:47:46Z)
• Graph Retrieval-Augmented LLM for Conversational Recommendation Systems [52.35491420330534]
  G-CRS (Graph Retrieval-Augmented Large Language Model for Conversational Recommender Systems) is a training-free framework that combines graph retrieval-augmented generation and in-context learning.<n>G-CRS achieves superior recommendation performance compared to existing methods without requiring task-specific training.
  arXiv  Detail & Related papers  (2025-03-09T03:56:22Z)
• Enhancing User Intent for Recommendation Systems via Large Language Models [0.0]
  DUIP is a novel framework that combines LSTM networks with Large Language Models (LLMs) to dynamically capture user intent and generate personalized item recommendations.<n>Our findings suggest that DUIP is a promising approach for next-generation recommendation systems, with potential for further improvements in cross-modal recommendations and scalability.
  arXiv  Detail & Related papers  (2025-01-18T20:35:03Z)
• 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)
• Beyond Inter-Item Relations: Dynamic Adaption for Enhancing LLM-Based Sequential Recommendation [83.87767101732351]
  Sequential recommender systems (SRS) predict the next items that users may prefer based on user historical interaction sequences. Inspired by the rise of large language models (LLMs) in various AI applications, there is a surge of work on LLM-based SRS. We propose DARec, a sequential recommendation model built on top of coarse-grained adaption for capturing inter-item relations.
  arXiv  Detail & Related papers  (2024-08-14T10:03:40Z)
• Enhancing Sequential Recommender with Large Language Models for Joint Video and Comment Recommendation [77.42486522565295]
  We propose a novel recommendation approach called LSVCR to jointly perform personalized video and comment recommendation.<n>Our approach comprises two key components: sequential recommendation (SR) model and supplemental large language model (LLM) recommender.<n>In particular, we attain a cumulative gain of 4.13% in comment watch time.
  arXiv  Detail & Related papers  (2024-03-20T13:14:29Z)
• Large Language Model Augmented Narrative Driven Recommendations [51.77271767160573]
  Narrative-driven recommendation (NDR) presents an information access problem where users solicit recommendations with verbose descriptions of their preferences and context. NDR lacks abundant training data for models, and current platforms commonly do not support these requests. We use large language models (LLMs) for data augmentation to train NDR models.
  arXiv  Detail & Related papers  (2023-06-04T03:46:45Z)
• Context-aware Tree-based Deep Model for Recommender Systems [22.537595224145356]
  In tree-based methods, a tree structure T is adopted as index and each item in corpus is attached to a leaf node on T. In this paper, we argue that the tree index used to support efficient retrieval in tree-based methods also has rich hierarchical information about the corpus. We propose a novel context-aware tree-based deep model (ConTDM) for recommender systems.
  arXiv  Detail & Related papers  (2021-09-22T09:06:36Z)

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.