# Neural Meta-Symbolic Reasoning and Learning

arXiv: https://arxiv.org/abs/2211.11650 · HTML: https://mlsanity.com/paper/2211.11650/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 21 of its 50 references that are in the map.
- First posted on arXiv 21 Nov 2022.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [Learning Explanatory Rules from Noisy Data](https://mlsanity.com/paper/1711.04574/) (2017)
- [End-to-End Differentiable Proving](https://mlsanity.com/paper/1705.11040/) (2017)
- [Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations](https://mlsanity.com/paper/2011.12854/) (2020)
- [Neural Logic Reinforcement Learning](https://mlsanity.com/paper/1904.10729/) (2019)
- [Differentiable Inductive Logic Programming for Structured Examples](https://mlsanity.com/paper/2103.01719/) (2021)
- [Learning with Algorithmic Supervision via Continuous Relaxations](https://mlsanity.com/paper/2110.05651/) (2021)
- [Kandinsky Patterns](https://mlsanity.com/paper/1906.00657/) (2019)
- [Neuro-Symbolic Forward Reasoning](https://mlsanity.com/paper/2110.09383/) (2021)
- [FF-NSL: Feed-Forward Neural-Symbolic Learner](https://mlsanity.com/paper/2106.13103/) (2021)

## Built on by (most cited first, 4 of 4)

- [BlendRL: A Framework for Merging Symbolic and Neural Policy Learning](https://mlsanity.com/paper/2410.11689/) (2024)
- [DeiSAM: Segment Anything with Deictic Prompting](https://mlsanity.com/paper/2402.14123/) (2024)
- [Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planning](https://mlsanity.com/paper/2505.11661/) (2025)
- [Boosting deep Reinforcement Learning using pretraining with Logical Options](https://mlsanity.com/paper/2603.06565/) (2026)

## Abstract (arXiv)

Deep neural learning uses an increasing amount of computation and data to solve very specific problems. By stark contrast, human minds solve a wide range of problems using a fixed amount of computation and limited experience. One ability that seems crucial to this kind of general intelligence is meta-reasoning, i.e., our ability to reason about reasoning. To make deep learning do more from less, we propose the first neural meta-symbolic system (NEMESYS) for reasoning and learning: meta programming using differentiable forward-chaining reasoning in first-order logic. Differentiable meta programming naturally allows NEMESYS to reason and learn several tasks efficiently. This is different from performing object-level deep reasoning and learning, which refers in some way to entities external to the system. In contrast, NEMESYS enables self-introspection, lifting from object- to meta-level reasoning and vice versa. In our extensive experiments, we demonstrate that NEMESYS can solve different kinds of tasks by adapting the meta-level programs without modifying the internal reasoning system. Moreover, we show that NEMESYS can learn meta-level programs given examples. This is difficult, if not impossible, for standard differentiable logic programming