We survey recent work on neurosymbolic programming, an emerging area that bridges the
areas of deep learning and program synthesis. Like in classic machine learning, the goal …

This survey reviews works in which language models (LMs) are augmented with reasoning
skills and the ability to use tools. The former is defined as decomposing a potentially …

Reasoning is a fundamental aspect of human intelligence that plays a crucial role in
activities such as problem solving, decision making, and critical thinking. In recent years …

The power of human language and thought arises from systematic compositionality—the
algebraic ability to understand and produce novel combinations from known components …

Chain-of-thought prompting has demonstrated remarkable performance on various natural
language reasoning tasks. However, it tends to perform poorly on tasks which requires …

Large pretrained (eg," foundation") models exhibit distinct capabilities depending on the
domain of data they are trained on. While these domains are generic, they may only barely …

Recent large-scale generative models learned on big data are capable of synthesizing
incredible images yet suffer from limited controllability. This work offers a new generation …

We investigate the ability of language models to perform compositional reasoning tasks
where the overall solution depends on correctly composing the answers to sub-problems …

Large language models (LLMs) show impressive abilities via few-shot prompting.
Commercialized APIs such as OpenAI GPT-3 further increase their use in real-world …

The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to
produce RL algorithms whose policies generalise well to novel unseen situations at …