DiffuReason: 联合潜在推理与生成细化以提升序列推荐
DiffuReason: Bridging Latent Reasoning and Generative Refinement for Sequential Recommendation
AI总结：
DiffuReason通过联合潜在推理与生成细化，提升序列推荐的准确性和实用性。
摘要：
潜在推理已成为序列推荐中一种有前景的范式，使模型能够通过多步推演捕捉复杂的用户意图。然而现有方法往往依赖于确定性的潜在链，累积噪声并忽略了用户意图中固有的不确定性，且通常在分阶段的流水线中训练，阻碍了联合优化和探索。为解决这些挑战，我们提出了DiffuReason，一种统一的
英文摘要：
Latent reasoning has emerged as a promising paradigm for sequential recommendation, enabling models to capture complex user intent through multi-step deliberation. Yet existing approaches often rely on deterministic latent chains that accumulate noise and overlook the uncertainty inherent in user intent, and they are typically trained in staged pipelines that hinder joint optimization and exploration. To address these challenges, we propose DiffuReason, a unified "Think-then-Diffuse" framework for sequential recommendation. It integrates multi-step Thinking Tokens for latent reasoning, diffusion-based refinement for denoising intermediate representations, and end-to-end Group Relative Policy Optimization (GRPO) alignment to optimize for ranking performance. In the Think stage, the model generates Thinking Tokens that reason over user history to form an initial intent hypothesis. In the Diffuse stage, rather than treating this hypothesis as the final output, we refine it through a diffusion process that models user intent as a probabilistic distribution, providing iterative denoising against reasoning noise. Finally, GRPO-based reinforcement learning enables the reasoning and refinement modules to co-evolve throughout training, without the constraints of staged optimization. Extensive experiments on four benchmarks demonstrate that DiffuReason consistently improves diverse backbone architectures. Online A/B tests on a large-scale industrial platform further validate its practical effectiveness.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
