# HoloRec: Holistic Encoding and Interleaved Reasoning for Generative Recommendation

arXiv: https://arxiv.org/abs/2606.15331 · HTML: https://mlsanity.com/paper/2606.15331/

## 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 26 of its 36 references that are in the map.
- First posted on arXiv 13 Jun 2026.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)

## Builds on (most cited first, 26 of 26)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach](https://mlsanity.com/paper/2305.07001/) (2023)
- [Learnable Item Tokenization for Generative Recommendation](https://mlsanity.com/paper/2405.07314/) (2024)
- [IDGenRec: LLM-RecSys Alignment with Textual ID Learning](https://mlsanity.com/paper/2403.19021/) (2024)
- [Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation](https://mlsanity.com/paper/2503.22675/) (2025)
- [OneRec-Think: In-Text Reasoning for Generative Recommendation](https://mlsanity.com/paper/2510.11639/) (2025)
- [Non-autoregressive Generative Models for Reranking Recommendation](https://mlsanity.com/paper/2402.06871/) (2024)
- [Generative Recommendation with Semantic IDs: A Practitioner's Handbook](https://mlsanity.com/paper/2507.22224/) (2025)
- [REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems](https://mlsanity.com/paper/2508.15308/) (2025)
- [OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System](https://mlsanity.com/paper/2509.18091/) (2025)
- [RecExplainer: Aligning Large Language Models for Explaining Recommendation Models](https://mlsanity.com/paper/2311.10947/) (2023)
- [R2ec: Towards Large Recommender Models with Reasoning](https://mlsanity.com/paper/2505.16994/) (2025)
- [CoFiRec: Coarse-to-Fine Tokenization for Generative Recommendation](https://mlsanity.com/paper/2511.22707/) (2025)
- [Towards Efficient and Generalizable Retrieval: Adaptive Semantic Quantization and Residual Knowledge Transfer](https://mlsanity.com/paper/2602.23978/) (2026)
- [Variable-Length Semantic IDs for Recommender Systems](https://mlsanity.com/paper/2602.16375/) (2026)
- [KERAG_R: Knowledge-Enhanced Retrieval-Augmented Generation for Recommendation](https://mlsanity.com/paper/2507.05863/) (2025)
- [CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation](https://mlsanity.com/paper/2605.05096/) (2026)
- [Reasoning Pattern Matters: Learning to Reason without Human Rationales](https://mlsanity.com/paper/2510.12643/) (2025)
- [SCoTER: Structured Chain-of-Thought Transfer for Enhanced Recommendation](https://mlsanity.com/paper/2511.19514/) (2025)
- [Verifiable Reasoning for LLM-based Generative Recommendation](https://mlsanity.com/paper/2603.07725/) (2026)
- [Quantized Inference for OneRec-V2](https://mlsanity.com/paper/2603.11486/) (2026)

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

- [OneLA: Scaling Linear-Attention Decoding to Large Beams in Generative Recommendation](https://mlsanity.com/paper/2609.12399/) (2026)
- [The Disconnect Between Better Descriptive Reasoning Trace Quality and Recommendation Effectiveness](https://mlsanity.com/paper/2608.23154/) (2026)

## Abstract (arXiv)

Generative recommendation models that formulate the task as sequence generation overcome the objective fragmentation problem of traditional cascade architectures, yet existing approaches still suffer from flat semantic representations lacking hierarchical structure for multi-step reasoning and an externally constructed chain-of-thought (CoT) that requires expensive annotations and remains disconnected from the generation objective. We propose HoloRec, an endogenous chain-of-thought recommendation mechanism that unifies representation, reasoning, and generation by constructing a hierarchical semantic encoding matrix via multi-granularity nested residual quantization optimized by a holistic reconstruction loss. HoloRec supports two inference modes: a non-thinking mode that uses lightweight multi-granularity supervised alignment for fast prediction, and a thinking mode that employs an interleaved reasoning scheme to generate CoT steps on the fly, directly embedding reasoning into the generation process without external data. Experiments on multiple public recommendation datasets demonstrate that HoloRec consistently outperforms baselines, with especially significant gains in sparse scenarios, and the thinking mode achieves better accuracy than the non-thinking mode with only modest inference overhead.