Search papers, labs, and topics across Lattice.
This paper introduces LoopMemGR, a novel framework for generative recommendation that addresses the limitations of traditional history-as-context methods by incorporating a closed-loop memory system. By maintaining a recommendation experience log alongside user behavior logs, LoopMemGR captures valuable feedback and exploration data, enabling the model to leverage past recommendations and their outcomes. Experimental results on a large-scale Taobao dataset reveal significant improvements in recommendation accuracy and user engagement through the use of multi-view experience extraction and closed-loop memory accumulation.
LoopMemGR transforms generative recommendation by integrating past recommendations into the memory framework, leading to more informed and effective predictions.
Generative recommendation formulates next-item prediction as conditional autoregressive generation over discrete Semantic IDs, enabling end-to-end recommendation over large-scale item spaces. However, most existing methods follow a history-as-context paradigm that repeatedly reconstructs user preference from behavior history while discarding system-side recommendation decisions after each request. This creates an asymmetric memory: the system remembers what the user has done, but not what it has previously recommended or learned from the resulting feedback. Consequently, useful preference-validation signals, potential negative evidence, and historical exploration information cannot be directly reused across requests. To address these limitations, we propose LoopMemGR, a closed-loop recommendation experience memory framework for generative recommendation. In addition to the conventional behavior log, LoopMemGR maintains a recommendation experience log that records past recommendation--feedback trajectories. It extracts request-relevant evidence through three complementary views: the recency view captures short-term interaction dynamics, the frequency view summarizes recurring recommendation patterns, and the global view distills transferable regularities shared across users. These signals are compressed into a fixed number of experience tokens to condition the generative backbone under a bounded input budget. Extensive experiments on an industrial Taobao dataset demonstrate the effectiveness of closed-loop experience accumulation and multi-view experience extraction.
DAMO