Preprint
Aug 2026
Enhancing Group Recommendation with Memory-Augmented Reasoning in LLM Agent
This work proposes AGR, a LLM-based agent, which consists of a Memory Module and a Reasoning Module, which adopts the Reinforcement Fine-Tuning (RFT) paradigm, where it significantly outperforms existing state-of-the-art methods in both recommendation accuracy and explainability.
Qi-Meng Niu, Bowen Hao, Zi-Xuan Zhang et al.
· 0 citations