mlsanityData to 7 Oct 2026

QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling

arXiv 2602.08559 ↗First posted 9 Feb 2026cs.IRcited by 2

On the map: LLM reasoning → LLM reasoning for recommendation

Abstract (arXiv)

With the evolution of large language models (LLMs), there is growing interest in leveraging their rich semantic understanding to enhance industrial recommendation systems (RecSys). Traditional RecSys relies on ID-based embeddings for user sequence modeling in the General Search Unit (GSU) and Exact Search Unit (ESU) paradigm, which suffers from low information density, knowledge isolation, and weak generalization ability. While LLMs offer complementary strengths with dense semantic representations and strong generalization, directly applying LLM embeddings to RecSys faces critical challenges: representation unmatch with business objectives and representation unlearning end-to-end with downstream tasks. In this paper, we present QARM V2, a unified framework that bridges LLM semantic understanding with RecSys business requirements for user sequence modeling.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning. Builds on 14 of its 28 references that are in the map. First posted on arXiv 9 Feb 2026.

Builds on

14 of 28 references.

References · 14

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2025Qwen2.5-VL Technical Reportcited by 5,418
  3. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  4. 2023Qwen Technical Reportcited by 3,273
  5. 2024DeepSeek-V3 Technical Reportcited by 724
  6. 2023Finite Scalar Quantization: VQ-VAE Made Simplecited by 425
  7. 2025OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignmentcited by 167
  8. 2025Kwai Keye-VL 1.5 Technical Reportcited by 68
  9. 2025Kwai Keye-VL Technical Reportcited by 47
  10. 2020Large Scale Product Graph Construction for Recommendation in E-commercecited by 28
  11. 2025OneRec Technical Reportcited by 24
  12. 2025MUSE: A Simple Yet Effective Multimodal Search-Based Framework for Lifelong User Interest Modelingcited by 6
2 more
  1. 2025LLM-Alignment Live-Streaming Recommendationcited by 5
  2. 2025ChorusCVR: Chorus Supervision for Entire Space Post-Click Conversion Rate Modelingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequencecited by 0
  2. 2026PRQ-KMeans: Projection Residual Quantization for Semantic ID Tokenizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains
  2. 2026Harmonizing Semantic and Collaborative in LLMs: Reasoning-based Embedding Generator for Sequential Recommendation
  3. 2024RA-Rec: An Efficient ID Representation Alignment Framework for LLM-based Recommendation
  4. 2024Semantic Convergence: Harmonizing Recommender Systems via Two-Stage Alignment and Behavioral Semantic Tokenization
  5. 2025GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models
  6. 2023RecExplainer: Aligning Large Language Models for Explaining Recommendation Models
  7. 2026Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations
  8. 2026RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems