HARPO: Hierarchical Agentic Reasoning for User-Aligned Conversational Recommendation

• URL: http://arxiv.org/abs/2604.10048v1
• Date: Sat, 11 Apr 2026 06:07:15 GMT
• Title: HARPO: Hierarchical Agentic Reasoning for User-Aligned Conversational Recommendation
• Abstract summary: We propose HARPO, an agentic framework that reframes conversational recommendation as a structured decision-making process.<n>HarPO integrates hierarchical preference learning that decomposes recommendation quality into interpretable dimensions.<n>We demonstrate consistent improvements over strong baselines on recommendation-centric metrics.
• Score: 10.766058469348382
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conversational recommender systems (CRSs) operate under incremental preference revelation, requiring systems to make recommendation decisions under uncertainty. While recent approaches particularly those built on large language models achieve strong performance on standard proxy metrics such as Recall@K and BLEU, they often fail to deliver high-quality, user-aligned recommendations in practice. This gap arises because existing methods primarily optimize for intermediate objectives like retrieval accuracy, fluent generation, or tool invocation, rather than recommendation quality itself. We propose HARPO (Hierarchical Agentic Reasoning with Preference Optimization), an agentic framework that reframes conversational recommendation as a structured decision-making process explicitly optimized for multi-dimensional recommendation quality. HARPO integrates hierarchical preference learning that decomposes recommendation quality into interpretable dimensions (relevance, diversity, predicted user satisfaction, and engagement) and learns context-dependent weights over these dimensions; (ii) deliberative tree-search reasoning guided by a learned value network that evaluates candidate reasoning paths based on predicted recommendation quality rather than task completion; and (iii) domain-agnostic reasoning abstractions through Virtual Tool Operations and multi-agent refinement, enabling transferable recommendation reasoning across domains. We evaluate HARPO on ReDial, INSPIRED, and MUSE, demonstrating consistent improvements over strong baselines on recommendation-centric metrics while maintaining competitive response quality. These results highlight the importance of explicit, user-aligned quality optimization for conversational recommendation.

Related papers

• Reinforced Preference Optimization for Reasoning-Augmented Recommendations [34.99578717556569]
  We introduce RPORec, a reinforced preference optimization framework for Recommender systems.<n>RPORec unifies an LLM backbone's reasoning ability with a dedicated recommendation head (Rechead) for precise item retrieval.<n>Extensive experiments on public benchmarks and large-scale online deployments show that RPORec consistently outperforms state-of-the-art LLM-based recommendation methods.
  arXiv  Detail & Related papers  (2026-05-21T03:56:42Z)
• RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation [63.74915464611075]
  RecThinker is an agentic framework for tool-augmented reasoning in recommendation.<n>We develop a suite of specialized tools for RecThinker, enabling the model to acquire user item-side and collaborative information.
  arXiv  Detail & Related papers  (2026-03-10T16:07:17Z)
• CARE: Contextual Adaptation of Recommenders for LLM-based Conversational Recommendation [66.51329063956538]
  We introduce the CARE (Contextual Adaptation of Recommenders) framework.<n> CARE customizes large language models for CRS tasks, and synergizes them with external recommendation systems.<n>Our results demonstrate that incorporating external recommender systems with entity-level information significantly enhances recommendation accuracy of CRS.
  arXiv  Detail & Related papers  (2025-08-19T14:53:30Z)
• Towards Comprehensible Recommendation with Large Language Model Fine-tuning [41.218487308635126]
  We propose a novel Content Understanding from a Collaborative Perspective framework (CURec) for recommendation systems.<n>Curec generates collaborative-aligned content features for more comprehensive recommendations.<n>Experiments on public benchmarks demonstrate the superiority of CURec over existing methods.
  arXiv  Detail & Related papers  (2025-08-11T03:55:31Z)
• 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)
• In-context Ranking Preference Optimization [65.5489745857577]
  We propose an In-context Ranking Preference Optimization (IRPO) framework to optimize large language models (LLMs) based on ranking lists constructed during inference.<n>We show IRPO outperforms standard DPO approaches in ranking performance, highlighting its effectiveness in aligning LLMs with direct in-context ranking preferences.
  arXiv  Detail & Related papers  (2025-04-21T23:06:12Z)
• Reason4Rec: Large Language Models for Recommendation with Deliberative User Preference Alignment [69.11529841118671]
  We propose a new Deliberative Recommendation task, which incorporates explicit reasoning about user preferences as an additional alignment goal.<n>We then introduce the Reasoning-powered Recommender framework for deliberative user preference alignment.
  arXiv  Detail & Related papers  (2025-02-04T07:17:54Z)
• The Best Decisions Are Not the Best Advice: Making Adherence-Aware Recommendations [4.6789662847602065]
  We propose an adherence-aware optimization framework to capture the dichotomy between the recommended and the implemented policy. We show that overlooking the partial adherence phenomenon, as is currently being done by most recommendation engines, can lead to arbitrarily severe performance deterioration. Our framework also provides useful tools to analyze the structure and to compute optimal recommendation policies that are naturally immune against such human deviations.
  arXiv  Detail & Related papers  (2022-09-05T10:11:09Z)
• Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning [68.45370492516531]
  We introduce Scalarized Multi-Objective Reinforcement Learning (SMORL) for the Recommender Systems (RS) setting. SMORL agent augments standard recommendation models with additional RL layers that enforce it to simultaneously satisfy three principal objectives: accuracy, diversity, and novelty of recommendations. Our experimental results on two real-world datasets reveal a substantial increase in aggregate diversity, a moderate increase in accuracy, reduced repetitiveness of recommendations, and demonstrate the importance of reinforcing diversity and novelty as complementary objectives.
  arXiv  Detail & Related papers  (2021-10-28T13:22:45Z)

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.