Nov 2026· Proceedings of the 35th ACM International Conference on Information and Knowledge Management· pp. 4258-4269· 1 citation· 43 references
TL;DR
Experiments on two real-world public benchmarks show that CaLR consistently improves multiple sequential recommendation backbones and outperforms strong latent reasoning baselines and outperforms strong latent reasoning baselines in real-world industrial deployment.
Abstract
Sequential recommendation aims to model users' evolving preferences from their historical interactions. Recent latent reasoning methods improve sequential recommenders by extending inferencetime computation in continuous representation space, refining user representations without generating explicit reasoning text. However, existing methods mainly reason over the encoded history itself and make limited use of contextual feedback from users' recent interactions. Such feedback, especially positive and negative signals in the latest session, can not only complement the long-term user representation but also provide directional guidance for latent reasoning by indicating which preference patterns should be strengthened or suppressed. In this paper, we propose Context-Aware Latent Reasoning (CaLR), a model-agnostic framework that grounds latent reasoning in session-level context. From the input perspective, CaLR selects informative positive and negative items from users' recent sessions as reasoning anchors. From the architecture perspective, it injects these anchors into each reasoning step through a Cross-Attention-based module. From the optimization perspective, it introduces Process Supervision Loss (PSL) to supervise intermediate reasoning states according to anchor feedback polarity. Experiments on two real-world public benchmarks show that CaLR consistently improves multiple sequential recommendation backbones and outperforms strong latent reasoning baselines. Ablation and further analyses verify the effectiveness of each component in CaLR. Moreover, a seven-day online A/B test on Kuaishou Lite demonstrates its effectiveness in real-world industrial deployment. Our code is available at https://github.com/Ak4ne-windsky/CaLR.
Sequential recommenders are widely applied in real-world scenarios to model user preferences and behavior patterns based on user interactions. Recent advances in sequential recommendation enhance transformer-based models with latent reasoning to refine user representations by autoregressively generating intermediate re...
Hao-Bo Zhang, Qian-Nan Zhu, Yutao Zhu et al.· 0 citations
LLM-based recommender systems increasingly generate chain-of-thought (CoT) text before each item prediction to activate the LLM's reasoning capacity, costing tens to hundreds of extra tokens per recommendation at inference. We ask whether inference-time reasoning artifacts (textual or latent) can be replaced by trainin...
Hong-Yang Su, Bei-Bei Kong, Lei Cheng et al.· Proceedings of the 35th ACM...· 1 citation
Generative recommendation (GR) models for ranking typically adopt a fast-thinking direct prediction paradigm with strong practical efficiency. However, ranking requires fine-grained scoring across multiple candidate items, while existing GR models still mainly rely on one-shot prediction. This raises the question wheth...
Hai-Han Shi, Rui-Dong Han, Wen-Jie Wang et al.· Proceedings of the 35th ACM...· 0 citations
Evo-Rec is proposed, a three-stage framework for learning better reasoning and further enhancing it through reinforcement learning that consistently outperforms discriminative, generative, and reasoning-enhanced recommenders across all evaluation metrics.
Meng-Dan Zhu, Yu-Fan Zhao, Sophie Di et al.· arXiv.org· 0 citations
Large language model (LLM)-enhanced recommender systems leverage rich item semantics to support personalized recommendation. However, semantic representations alone do not determine which historical behaviors reflect persistent preferences and which mainly indicate recent interests, leaving an important aspect of user...
Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their use as the backbone of foundation recommendation models (FRMs). Existing methods enhance recommendations through explicit Chain-of-Thought (CoT) reasoning under a Think-then-Answer paradigm. However, explicit CoT incurs subst...
Hao Jiang, Pei Du, Peng-Fei Yao et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.