ManCAR：面向序列推荐的流形约束隐式推理与自适应测试时计算

ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation

February 23, 2026

作者: Kun Yang, Yuxuan Zhu, Yazhe Chen, Siyao Zheng, Bangyang Hong, Kangle Wu, Yabo Ni, Anxiang Zeng, Cong Fu, Hui Li

cs.AI

摘要

顺序推荐系统日益采用潜在多步推理来增强测试时的计算效率。尽管取得了实证性进展，现有方法大多通过目标主导目标驱动中间推理状态，而未施加明确的可行性约束。这导致潜在漂移现象，即推理轨迹偏离至不合理区域。我们认为，有效的推荐推理应被视为在协作流形上的导航过程，而非自由形式的潜在优化。为此，我们提出ManCAR（流形约束自适应推理）这一原则性框架，将推理过程锚定在全局交互图的拓扑结构内。ManCAR从用户近期行为的协作邻域构建局部意图先验，将其表示为项目单纯形上的概率分布。在训练过程中，模型逐步将其潜在预测分布与该先验对齐，迫使推理轨迹始终保持在有效流形内。测试时，推理过程会自适应进行直至预测分布稳定，避免过度优化。我们通过变分推断理论对ManCAR进行阐释，从理论上验证其漂移预防机制和自适应测试终止机制。在七个基准数据集上的实验表明，ManCAR持续优于现有最先进基线，在NDCG@10指标上实现最高46.88%的相对提升。代码已开源：https://github.com/FuCongResearchSquad/ManCAR。

English

Sequential recommendation increasingly employs latent multi-step reasoning to enhance test-time computation. Despite empirical gains, existing approaches largely drive intermediate reasoning states via target-dominant objectives without imposing explicit feasibility constraints. This results in latent drift, where reasoning trajectories deviate into implausible regions. We argue that effective recommendation reasoning should instead be viewed as navigation on a collaborative manifold rather than free-form latent refinement. To this end, we propose ManCAR (Manifold-Constrained Adaptive Reasoning), a principled framework that grounds reasoning within the topology of a global interaction graph. ManCAR constructs a local intent prior from the collaborative neighborhood of a user's recent actions, represented as a distribution over the item simplex. During training, the model progressively aligns its latent predictive distribution with this prior, forcing the reasoning trajectory to remain within the valid manifold. At test time, reasoning proceeds adaptively until the predictive distribution stabilizes, avoiding over-refinement. We provide a variational interpretation of ManCAR to theoretically validate its drift-prevention and adaptive test-time stopping mechanisms. Experiments on seven benchmarks demonstrate that ManCAR consistently outperforms state-of-the-art baselines, achieving up to a 46.88% relative improvement w.r.t. NDCG@10. Our code is available at https://github.com/FuCongResearchSquad/ManCAR.