# A Survey of Reasoning with Foundation Models

**Authors:** Jiankai Sun, Chuanyang Zheng, Enze Xie, Zhengying Liu, Ruihang Chu, Jianing Qiu, Jiaqi Xu, Mingyu Ding, Hongyang Li, Mengzhe Geng, Yue Wu, Wenhai Wang, Junsong Chen, Zhangyue Yin, Xiaozhe Ren, Jie Fu, Junxian He, Wu Yuan, Qi Liu, Xihui Liu  
**arXiv:** [2312.11562](https://arxiv.org/abs/2312.11562)  
**Date:** 2023-12-17  
**Summary page:** https://www.summarizepaper.com/en/paper/2312.11562v4/

## Key points

- Reasoning is a critical skill for solving complex problems
- Reasoning is used in real-world scenarios such as negotiation, medical diagnosis, and criminal investigation
- Reasoning plays a fundamental role in the development of Artificial General Intelligence (AGI)
- There is increasing interest in exploring the capabilities of foundation models in reasoning tasks
- The paper titled "A Survey of Reasoning with Foundation Models" introduces seminal foundation models for reasoning
- The authors discuss advancements in reasoning tasks, methods, and benchmarks
- Potential future directions include exploring multimodal learning, autonomous agents, and super alignment in reasoning
- The goal is to inspire researchers to explore this field and contribute to AGI development

## Summary

Reasoning is a critical skill for solving complex problems and is widely used in various real-world scenarios such as negotiation, medical diagnosis, and criminal investigation. It also plays a fundamental role in the development of Artificial General Intelligence (AGI). With the continuous advancement of foundation models, there has been an increasing interest in exploring their capabilities in reasoning tasks. In this paper titled "A Survey of Reasoning with Foundation Models," the authors introduce seminal foundation models that have been proposed or can be adapted for reasoning. They discuss the latest advancements in various reasoning tasks, methods, and benchmarks. The paper further delves into potential future directions for the emergence of reasoning abilities within foundation models. This includes exploring multimodal learning, autonomous agents, and super alignment in the context of reasoning. By examining these research directions, they aim to inspire researchers to further explore this field and stimulate advancements in reasoning with foundation models. Ultimately, their goal is to contribute to the development of AGI. The paper is authored by Jiankai Sun et al.