Researchers have developed MARS, a novel multi-agent re-ranking framework designed for repeat-order food delivery recommendations. This framework integrates large language models (LLMs) with collaborative filtering and contextual reasoning to improve recommendation accuracy. MARS operates in two stages, first predicting cuisine and then ranking vendors, utilizing signals from user preferences, peer evidence, and geospatial data. The system was evaluated on real-world benchmarks from Delivery Hero, demonstrating competitive performance when LLMs are combined with lightweight collaborative retrieval methods. AI
IMPACT This framework demonstrates how LLMs can be effectively integrated into structured recommendation pipelines, potentially improving personalized user experiences in e-commerce and delivery services.
RANK_REASON The cluster contains a research paper detailing a new framework for recommender systems.
Read on arXiv cs.IR (Information Retrieval) →
- alphaXiv
- arXiv
- CatalyzeX
- CORE Recommender
- DagsHub
- Delivery Hero
- DHRD-SE
- DHRD-SG
- Gotit.pub
- Hugging Face
- Large language models
- LightGCN
- MARS
- ScienceCast
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
