From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Models

TL;DR

This survey reviews how large language models can be used for hypothesis discovery and rule learning, highlighting progress, challenges, and future directions towards enabling models to generate new knowledge and foster innovation.

Contribution

It provides a structured overview of LLM-based hypothesis discovery, synthesizing existing methods, achievements, and gaps to guide future research in this area.

Findings

LLMs have shown potential in hypothesis generation and validation.

Significant gaps remain in automating the scientific discovery process.

Future work should focus on integrating reasoning and learning for genuine innovation.

Abstract

Since the advent of Large Language Models (LLMs), efforts have largely focused on improving their instruction-following and deductive reasoning abilities, leaving open the question of whether these models can truly discover new knowledge. In pursuit of artificial general intelligence (AGI), there is a growing need for models that not only execute commands or retrieve information but also learn, reason, and generate new knowledge by formulating novel hypotheses and theories that deepen our understanding of the world. Guided by Peirce's framework of abduction, deduction, and induction, this survey offers a structured lens to examine LLM-based hypothesis discovery. We synthesize existing work in hypothesis generation, application, and validation, identifying both key achievements and critical gaps. By unifying these threads, we illuminate how LLMs might evolve from mere ``information executors'' into engines of genuine innovation, potentially transforming research, science, and real-world problem solving.