# HARPO: Hierarchical Agentic Reasoning for User-Aligned Conversational Recommendation

arXiv: https://arxiv.org/abs/2604.10048 · HTML: https://mlsanity.com/paper/2604.10048/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 20 of its 27 references that are in the map.
- First posted on arXiv 11 Apr 2026.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)
- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 20 of 20)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [A Survey of Multi-Objective Sequential Decision-Making](https://mlsanity.com/paper/1402.0590/) (2014)
- [Towards Deep Conversational Recommendations](https://mlsanity.com/paper/1812.07617/) (2018)
- [A Survey on Conversational Recommender Systems](https://mlsanity.com/paper/2004.00646/) (2020)
- [Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations](https://mlsanity.com/paper/2308.16505/) (2023)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion](https://mlsanity.com/paper/2007.04032/) (2020)
- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [Conversational Recommender System](https://mlsanity.com/paper/1806.03277/) (2018)
- [Towards Knowledge-Based Recommender Dialog System](https://mlsanity.com/paper/1908.05391/) (2019)
- [INSPIRED: Toward Sociable Recommendation Dialog Systems](https://mlsanity.com/paper/2009.14306/) (2020)
- [Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning](https://mlsanity.com/paper/2206.09363/) (2022)
- [BARCOR: Towards A Unified Framework for Conversational Recommendation Systems](https://mlsanity.com/paper/2203.14257/) (2022)
- [Muse: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profiles](https://mlsanity.com/paper/2412.18416/) (2024)

## Built on by (most cited first, 2 of 2)

- [Position: Recommender Systems Should Move Beyond Platform-Centric Ranking toward Personal Agent-Mediated Recommendation](https://mlsanity.com/paper/2609.11942/) (2026)
- [AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side](https://mlsanity.com/paper/2609.31166/) (2026)

## Abstract (arXiv)

Conversational recommender systems (CRSs) operate under incremental preference revelation, requiring recommendation decisions under uncertainty. While recent LLM-based approaches achieve strong performance on proxy metrics such as Recall@K and BLEU, they often fail to deliver high-quality, user-aligned recommendations in practice, as they optimize intermediate objectives like retrieval accuracy or fluent generation 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 optimized for multi-dimensional recommendation quality. HARPO integrates (i) hierarchical preference learning that decomposes recommendation quality into interpretable dimensions (relevance, diversity, satisfaction, and engagement) with context-dependent weighting; (ii) deliberative tree-search reasoning guided by a learned value network evaluating candidate paths on predicted quality; and (iii) domain-agnostic reasoning abstractions through Virtual Tool Operations and multi-agent refinement. We evaluate HARPO on ReDial, INSPIRED, and MUSE, demonstrating consistent improvements over strong baselines on recommendation-centric metrics while maintaining competitive response quality.