# Abstract Concept Modelling in Conceptual Spaces: A Study on Chess Strategies

arXiv: https://arxiv.org/abs/2601.21771 · HTML: https://mlsanity.com/paper/2601.21771/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Builds on (most cited first, 9 of 9)

- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [Acquisition of Chess Knowledge in AlphaZero](https://mlsanity.com/paper/2111.09259/) (2021)
- [Aligning Superhuman AI with Human Behavior: Chess as a Model System](https://mlsanity.com/paper/2006.01855/) (2020)
- [Evidence of Learned Look-Ahead in a Chess-Playing Neural Network](https://mlsanity.com/paper/2406.00877/) (2024)
- [Maia-2: A Unified Model for Human-AI Alignment in Chess](https://mlsanity.com/paper/2409.20553/) (2024)
- [Chess AI: Competing Paradigms for Machine Intelligence](https://mlsanity.com/paper/2109.11602/) (2021)
- [Conceptual Spaces for Cognitive Architectures: A Lingua Franca for Different Levels of Representation](https://mlsanity.com/paper/1701.00464/) (2017)
- [Bridging the Gap between Expert and Language Models: Concept-guided Chess Commentary Generation and Evaluation](https://mlsanity.com/paper/2410.20811/) (2024)
- [Information based explanation methods for deep learning agents -- with applications on large open-source chess models](https://mlsanity.com/paper/2309.09702/) (2023)

## Abstract (arXiv)

We present a conceptual space framework for modelling abstract concepts that unfold over time, demonstrated through a chess-based proof-of-concept. Strategy concepts, such as attack or sacrifice, are represented as geometric regions across interpretable quality dimensions, with chess games instantiated and analysed as trajectories whose directional movement toward regions enables recognition of intended strategies. This approach also supports dual-perspective modelling, capturing how players interpret identical situations differently. Our implementation demonstrates the feasibility of trajectory-based concept recognition, with movement patterns aligning with expert commentary. This work explores extending the conceptual spaces theory to temporally realised, goal-directed concepts. The approach establishes a foundation for broader applications involving sequential decision-making and supports integration with knowledge evolution mechanisms for learning and refining abstract concepts over time.