ReaSeq: Unleashing World Knowledge via Reasoning for Sequential Modeling

Chuan Wang, Jiakai Tang, Gaoming Yang, Jian Wu, Xiangheng Kong, Junjun Zheng, Yeqiu Yang, Yuning Jiang, Jiahao Yu, Longbin Li, Shuwen Xiao, Han Wu

Abstract:

Industrial recommender systems face two fundamental limitations under the log-driven
paradigm: (1) knowledge poverty in ID-based item representations that causes brittle
interest modeling under data sparsity, and (2) systemic blindness to beyond-log user
interests that constrains model performance within platform boundaries. These limitations
stem from an over-reliance on shallow interaction statistics and close-looped feedback while
neglecting the rich world knowledge about product semantics and cross-domain behavioral
patterns that Large Language Models have learned from vast corpora.
To address these challenges, we introduce ReaSeq, a reasoning-enhanced framework that
leverages world knowledge in Large Language Models to address both limitations through
explicit and implicit reasoning. Specifically, ReaSeq employs explicit Chain-of-Thought
reasoning via multi-agent collaboration to distill structured product knowledge into semantically enriched item representations, and latent reasoning via Diffusion Large Language
Models to infer plausible beyond-log behaviors. Deployed on Taobao’s ranking system
serving hundreds of millions of users, ReaSeq achieves substantial gains: >6.0% in IPV and
CTR, >2.9% in Orders, and >2.5% in GMV, validating the effectiveness of world-knowledgeenhanced reasoning over purely log-driven approaches.