Book Open access

Beyond the Single Path: Divergent Reasoning for LLM-based Recommendation

Guo-Jia An Jie Zou Yu-Han Yang Shuai Qin Wei-Kang Guo Jin-Yu Guo Yang Yang

Jul 2026 · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval · pp. 41-52 · 1 citation · 59 references

Computer Science

TL;DR

Divergent Reasoning for LLM-based Recommendation is proposed, which effectively mitigates the issue of reasoning path collapse, while improving both the accuracy and diversity of LLM-based recommendations.

Abstract

Large Language Models (LLMs) have demonstrated strong potential in recommendations due to their powerful reasoning capabilities. However, existing methods typically rely on a single reasoning path to drive the entire Top-K recommendations. This paradigm is prone to reasoning path collapse, where limiting exploration of potentially superior and diverse reasoning paths within the LLMs space. As a result, both the accuracy and diversity of the recommendation outcomes are constrained. To address this issue, we propose a novel model, Divergent Reasoning for LLM-based Recommendation, named DivReason. Inspired by the structure of intellect theory, which emphasizes a two-stage cognitive process of divergent thinking followed by convergent thinking, DivReason is designed with two core components: the Divergent Reasoning Path Generation Module and the Reasoning Path Aggregation Module. In the first module, DivReason introduces a training-free form of controlled uncertainty to promote diverse reasoning, leveraging Monte Carlo Dropout and Directional Perturbation to expand exploration in the latent reasoning space. In the Reasoning Path Aggregation Module, we adaptively select a subset of high-quality reasoning paths from the entire path pool and aggregate them into a unified reasoning representation. Meanwhile, we further adopt an alternating reinforcement learning strategy to optimize the model, explicitly balancing accuracy and diversity during training. Extensive experimental results show that DivReason effectively mitigates the issue of reasoning path collapse, while improving both the accuracy and diversity of LLM-based recommendations.

DOI Semantic Scholar

Read PDF

Similar papers

Jul 2026

LaRec: Unleashing LLM-based Latent Reasoning for Generative Recommendation

This work proposes LaRec, an efficient generative recommendation framework designed to unleash the potential of latent reasoning in LLMs by designing Latent Pre-training that empowers LLMs with latent reasoning capabilities by providing rich supervisory signals to the latent space reasoning via step-level alignment and process direction alignment.

Yu Xia, Zihan Lin, Wei Yang et al. · arXiv.org · 0 citations

Jul 2026

Hierarchical Latent Reasoning for LLM-based Recommendation

To further optimize the reasoning trajectory, HiLaR combines final recommendation feedback with layer-aware process rewards derived from the marginal target-likelihood gain of each state, and generally outperforms strong sequential, generative, and LLM-based recommendation baselines.

Pei-Yu Hu, Si-Ying Gu, Wei-Hai Lu et al. · arXiv.org · 1 citation

Preprint Aug 2026

Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging

This work proposes the first model merging framework for reasoning compression in recommender systems, and proposes selective injection of the concise behaviour of the fast-thinking model into the slow-thinking model and reducing reasoning verbosity without compromising recommendation quality.

Linh Le, Tong Chen, S. Sadiq et al. · 0 citations

Jul 2026

WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models

WhisperRec compresses teacher-generated CoT into learnable latent reasoning tokens, enabling a Latent-Reason-then-Answer paradigm that performs reasoning in latent space without producing verbose rationales, and achieves over 10x higher online inference throughput.

Hao Jiang, Pei Du, Pengfei Yao et al. · arXiv.org · 0 citations

Preprint Sep 2026

SelfDR: Self-Distillation from Reasoning for LLM-Based Recommendation

Large Language Models (LLMs) have recently emerged as powerful backbones for recommendation. To better elicit their capabilities, reasoning has been widely incorporated to help LLMs interpret rich textual signals and improve recommendation accuracy. However, explicitly generating intermediate reasoning traces often incurs substantial computational costs, which limits practical deployment in real-world recommender systems. To address this challenge, we propose SelfDR, a Self-Distillation from Reasoning framework for LLM-based Recommendation. SelfDR distills an LLM's own reasoning-enhanced predictions to produce recommendations directly, improving recommendation effectiveness while maintaining inference efficiency. All components in the framework are built on the same base LLM, without relying on any external models. Specifically, the teacher recommender is constructed by training a reasoner with downstream performance as the reward, enabling it to generate targeted rationales that are later incorporated into the teacher's input. A student recommender for direct recommendation, with the same underlying model, then learns from the teacher through self-distillation with a dynamic weighting strategy. Extensive experiments on three public datasets validate the effectiveness, rationality, and efficiency of SelfDR. Codes are available at https://github.com/JiangDeccc/SelfDistillation.

Chumeng Jiang, Jiayin Wang, Xin-Jie Lin et al. · 0 citations

Preprint Aug 2026

ChainPrune: Evaluating and Reducing Redundancy in Long Chain-of-Thought Reasoning

This work proposes ChainPrune, a novel reasoning path semantic structural optimization method to efficiently and controllably synthesize self-generated high-quality training data and incorporates a DPO-based preference learning method combined with supervised loss, effectively mitigating false reward suppression.

Weihang Pan, Zhengxu Yu, Yuxiang Zhang et al. · 1 citation