# Towards a Neurosymbolic Reasoning System Grounded in Schematic Representations

arXiv: https://arxiv.org/abs/2509.03644 · HTML: https://mlsanity.com/paper/2509.03644/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 3 Sep 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 15 of 15)

- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve](https://mlsanity.com/paper/2309.13638/) (2023)
- [ASP-Core-2 Input Language Format](https://mlsanity.com/paper/1911.04326/) (2019)
- [Leveraging Large Language Models to Generate Answer Set Programs](https://mlsanity.com/paper/2307.07699/) (2023)
- [How to build your own ASP-based system?!](https://mlsanity.com/paper/2008.06692/) (2020)
- [Language (Re)modelling: Towards Embodied Language Understanding](https://mlsanity.com/paper/2005.00311/) (2020)
- [LOGIC-LM++: Multi-Step Refinement for Symbolic Formulations](https://mlsanity.com/paper/2407.02514/) (2024)
- [VERUS-LM: a Versatile Framework for Combining LLMs with Symbolic Reasoning](https://mlsanity.com/paper/2501.14540/) (2025)
- [A Uniform Treatment of Aggregates and Constraints in Hybrid ASP](https://mlsanity.com/paper/2003.04176/) (2020)
- [Non-Monotonic Spatial Reasoning with Answer Set Programming Modulo Theories](https://mlsanity.com/paper/1606.07860/) (2016)
- [Exploring Spatial Schema Intuitions in Large Language and Vision Models](https://mlsanity.com/paper/2402.00956/) (2024)
- [Talking about the Moving Image: A Declarative Model for Image Schema Based Embodied Perception Grounding and Language Generation](https://mlsanity.com/paper/1508.03276/) (2015)
- [Answer Set Programming Modulo `Space-Time'](https://mlsanity.com/paper/1805.06861/) (2018)
- [Grounding Agent Reasoning in Image Schemas: A Neurosymbolic Approach to Embodied Cognition](https://mlsanity.com/paper/2503.24110/) (2025)

## Abstract (arXiv)

Despite significant progress in natural language understanding, Large Language Models (LLMs) remain error-prone when performing logical reasoning, often lacking the robust mental representations that enable human-like comprehension. We introduce a prototype neurosymbolic system, Embodied-LM, that grounds understanding and logical reasoning in schematic representations based on image schemas-recurring patterns derived from sensorimotor experience that structure human cognition. Our system operationalizes the spatial foundations of these cognitive structures using declarative spatial reasoning within Answer Set Programming. Through evaluation on logical deduction problems, we demonstrate that LLMs can be guided to interpret scenarios through embodied cognitive structures, that these structures can be formalized as executable programs, and that the resulting representations support effective logical reasoning with enhanced interpretability. While our current implementation focuses on spatial primitives, it establishes the computational foundation for incorporating more complex and dynamic representations.