Generative Reasoning Recommendation via LLMs

• URL: http://arxiv.org/abs/2510.20815v1
• Date: Thu, 23 Oct 2025 17:59:31 GMT
• Title: Generative Reasoning Recommendation via LLMs
• Authors: Minjie Hong, Zetong Zhou, Zirun Guo, Ziang Zhang, Ruofan Hu, Weinan Gan, Jieming Zhu, Zhou Zhao,
• Abstract summary: Large language models (LLMs) face fundamental challenges in functioning as generative reasoning recommendation models (GRRMs)<n>This work explores how to build GRRMs by adapting pre-trained LLMs, which achieves a unified understanding-reasoning-prediction manner for recommendation tasks.<n>We propose GREAM, an end-to-end framework that integrates three components: Collaborative-Semantic Alignment, Reasoning Curriculum Activation, and Sparse-Regularized Group Policy Optimization.
• Score: 48.45009951684554
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite their remarkable reasoning capabilities across diverse domains, large language models (LLMs) face fundamental challenges in natively functioning as generative reasoning recommendation models (GRRMs), where the intrinsic modeling gap between textual semantics and collaborative filtering signals, combined with the sparsity and stochasticity of user feedback, presents significant obstacles. This work explores how to build GRRMs by adapting pre-trained LLMs, which achieves a unified understanding-reasoning-prediction manner for recommendation tasks. We propose GREAM, an end-to-end framework that integrates three components: (i) Collaborative-Semantic Alignment, which fuses heterogeneous textual evidence to construct semantically consistent, discrete item indices and auxiliary alignment tasks that ground linguistic representations in interaction semantics; (ii) Reasoning Curriculum Activation, which builds a synthetic dataset with explicit Chain-of-Thought supervision and a curriculum that progresses through behavioral evidence extraction, latent preference modeling, intent inference, recommendation formulation, and denoised sequence rewriting; and (iii) Sparse-Regularized Group Policy Optimization (SRPO), which stabilizes post-training via Residual-Sensitive Verifiable Reward and Bonus-Calibrated Group Advantage Estimation, enabling end-to-end optimization under verifiable signals despite sparse successes. GREAM natively supports two complementary inference modes: Direct Sequence Recommendation for high-throughput, low-latency deployment, and Sequential Reasoning Recommendation that first emits an interpretable reasoning chain for causal transparency. Experiments on three datasets demonstrate consistent gains over strong baselines, providing a practical path toward verifiable-RL-driven LLM recommenders.

Related papers

• Give Users the Wheel: Towards Promptable Recommendation Paradigm [21.39017335979666]
  Decoupled Promptable Sequential Recommendation (DPR) is a model-agnostic framework that empowers conventional sequential backbones to support Promptable Recommendation.<n>DPR modulates the latent user representation directly within the retrieval space.<n>It significantly outperforms state-of-the-art baselines in prompt-guided tasks.
  arXiv  Detail & Related papers  (2026-02-21T18:41:28Z)
• Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction [4.01163688152329]
  Open mining of triplets is the foundation for structured knowledge without predefined schemas.<n>Existing methods exhibit vulnerability in ambiguity making often erroneous extraction patterns permanent.<n>We propose a Knowledge Reconstruction-driven Prompt Optimization (KRPO) framework to assist Large Language Models (LLMs) in continuously improving their extraction capabilities.
  arXiv  Detail & Related papers  (2026-01-21T14:42:13Z)
• Latent Chain-of-Thought for Visual Reasoning [53.541579327424046]
  Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs)<n>We reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference.<n>We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-10-27T23:10:06Z)
• CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning [93.05917922306196]
  Composed Image Retrieval (CIR) aims to find a target image from a reference image and a modification text.<n>CIR-CoT is the first end-to-end retrieval-oriented MLLM designed to integrate explicit Chain-of-Thought (CoT) reasoning.
  arXiv  Detail & Related papers  (2025-10-09T09:41:45Z)
• 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)
• LARES: Latent Reasoning for Sequential Recommendation [96.26996622771593]
  We present LARES, a novel and scalable LAtent REasoning framework for Sequential recommendation.<n>Our proposed approach employs a recurrent architecture that allows flexible expansion of reasoning depth without increasing parameter complexity.<n>Our framework exhibits seamless compatibility with existing advanced models, further improving their recommendation performance.
  arXiv  Detail & Related papers  (2025-05-22T16:22:54Z)
• SRA-CL: Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation [23.050104678143935]
  We propose a novel approach named Semantic Retrieval Augmented Contrastive Learning (SRA-CL)<n>SRA-CL leverages the semantic understanding and reasoning capabilities of LLMs to generate expressive embeddings that capture user preferences and item characteristics.<n>SRA-CL adopts a plug-and-play design, enabling seamless integration with existing sequential recommendation architectures.
  arXiv  Detail & Related papers  (2025-03-06T07:25:19Z)
• EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration [60.47645731801866]
  Large language models (LLMs) are increasingly leveraged as foundational backbones in advanced recommender systems.<n>LLMs are pre-trained linguistic semantics but learn collaborative semantics from scratch via the llm-Backbone.<n>We propose EAGER-LLM, a decoder-only generative recommendation framework that integrates endogenous and endogenous behavioral and semantic information in a non-intrusive manner.
  arXiv  Detail & Related papers  (2025-02-20T17:01:57Z)
• Semantic Convergence: Harmonizing Recommender Systems via Two-Stage Alignment and Behavioral Semantic Tokenization [10.47505806629852]
  Large language models (LLMs) are adept at discerning profound user interests from historical behaviors.<n>We propose a novel framework that harmoniously merges traditional recommendation models with the prowess of LLMs.<n>We design a series of specialized supervised learning tasks aimed at aligning collaborative signals with the subtleties of natural language semantics.
  arXiv  Detail & Related papers  (2024-12-18T12:07:58Z)
• Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs [63.36637269634553]
  We introduce a novel approach where LLMs are fine-tuned to generate a sequence of Diverse Chains of Thought (DCoT) within a single inference step.<n>We show that fine-tuning on DCoT improves performance over the CoT baseline across model families and scales.<n>Our work is also significant because both quantitative analyses and manual evaluations reveal the observed gains stem from the models' ability to refine an initial reasoning chain.
  arXiv  Detail & Related papers  (2024-07-03T15:01:18Z)
• DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation [53.62727171363384]
  We introduce a novel reasoning principle: Dynamic Reflection with Divergent Thinking. Our methodology is dynamic reflection, a process that emulates human learning through probing, critiquing, and reflecting. We evaluate our approach on three datasets using six pre-trained LLMs.
  arXiv  Detail & Related papers  (2023-12-18T16:41:22Z)

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.