RRCM trains an LLM to dynamically retrieve from collaborative and meta memories using group relative policy optimization driven by final top-k recommendation quality.
Recgpt technical report
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.IR 8years
2026 8roles
background 1polarities
background 1representative citing papers
UniSID jointly optimizes embeddings and Semantic IDs end-to-end with multi-granularity contrastive learning and summary-based reconstruction, outperforming RQ-based methods by up to 4.62% in Hit Rate for ad recommendation.
ShopX is a single foundation model combining intent understanding, planning, and SID-native item fulfillment for agentic shopping, with claimed improvements over tool-mediated systems on Taobao logs.
UniVA unifies value alignment in generative recommendation via a Commercial SID tokenizer, eCPM-aware RL decoder, and personalized beam search, reporting 37% offline Hit Rate gains and 1.5% online GMV lift on Tencent WeChat Channels.
TriAlignGR introduces cross-modal alignment, deep interest mining via CoT, and triangular multitask training to fix semantic degradation and opacity in SID-based generative recommendation.
Fine-tuned LLM acts as ancillary advertiser predictor in production ads RecSys, augmenting retrieval and ranking with measurable offline and online gains.
RecGPT-Mobile runs a compact LLM on phones to understand evolving user intent from behaviors and improve mobile e-commerce recommendations.
citing papers explorer
-
RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
RRCM trains an LLM to dynamically retrieve from collaborative and meta memories using group relative policy optimization driven by final top-k recommendation quality.