RecMind

# RecMind

One of the first LLM-based agentic system for recommendation that combines tool use, memory, and self-inspiring planning for zero-shot and few-shot recommendation tasks.

## Paper

**Title:** RecMind: Large Language Model Powered Agent For Recommendation

**Conference:** Findings of the Association for Computational Linguistics: NAACL 2024

**Paper:** https://aclanthology.org/2024.findings-naacl.271/

## Repository Note

This repository is maintained for the RecMind project webpage.

Due to company policy, the source code associated with this paper cannot be open-sourced at this time.

## Citation

If you find this work useful, please cite:

```bibtex
@inproceedings{wang2024recmind,
  title={Recmind: Large language model powered agent for recommendation},
  author={Wang, Yancheng and Jiang, Ziyan and Chen, Zheng and Yang, Fan and Zhou, Yingxue and Cho, Eunah and Fan, Xing and Lu, Yanbin and Huang, Xiaojiang and Yang, Yingzhen},
  booktitle={Findings of the Association for Computational Linguistics: NAACL 2024},
  pages={4351--4364},
  year={2024}
}
```