Towards Context-aware Reasoning-enhanced Generative Searching in E-commerce

2025-10-19

AI Summary

E-commerce search and recommendation face challenges in accurately understanding user intent and effectively integrating heterogeneous contextual signals. Method: This paper proposes a context-aware, reasoning-enhanced generative search framework comprising: (1) a multi-source heterogeneous context alignment mechanism that jointly models spatiotemporal, historical interaction, and current query information; (2) a self-evolving post-training paradigm to improve generalization; and (3) a debiased GRPO-based reinforcement learning strategy to optimize ranking objectives. The implementation integrates textual semantic representation, supervised fine-tuning, and reinforcement learning. Contribution/Results: Extensive experiments on real-world e-commerce search logs demonstrate that the proposed method significantly outperforms state-of-the-art baselines, achieving average improvements of 4.2%–6.8% in key metrics including NDCG@10 and MRR. These results validate its effectiveness and robustness in modeling complex user intent and enhancing ranking performance.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Learning Preferences or Rankings
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

Search-based recommendation is one of the most critical application scenarios in e-commerce platforms. Users' complex search contexts--such as spatiotemporal factors, historical interactions, and current query's information--constitute an essential part of their decision-making, reflecting implicit preferences that complement explicit query terms. Modeling such rich contextual signals and their intricate associations with candidate items remains a key challenge. Although numerous efforts have been devoted to building more effective search methods, existing approaches still show limitations in integrating contextual information, which hinders their ability to fully capture user intent. To address these challenges, we propose a context-aware reasoning-enhanced generative search framework for better extbf{understanding the complicated context}. Specifically, the framework first unifies heterogeneous user and item contexts into textual representations or text-based semantic identifiers and aligns them. To overcome the lack of explicit reasoning trajectories, we introduce a self-evolving post-training paradigm that iteratively combines supervised fine-tuning and reinforcement learning to progressively enhance the model's reasoning capability. In addition, we identify potential biases in existing RL algorithms when applied to search scenarios and present a debiased variant of GRPO to improve ranking performance. Extensive experiments on search log data collected from a real-world e-commerce platform demonstrate that our approach achieves superior performance compared with strong baselines, validating its effectiveness for search-based recommendation.

Problem

• Modeling complex search contexts and item associations
• Integrating heterogeneous contextual information for user intent
• Addressing reasoning limitations and biases in search algorithms

Innovation

• Unifies user and item contexts into textual representations
• Introduces self-evolving post-training for reasoning enhancement
• Presents debiased GRPO algorithm to improve ranking performance