# Maia-2: A Unified Model for Human-AI Alignment in Chess

arXiv: https://arxiv.org/abs/2409.20553 · HTML: https://mlsanity.com/paper/2409.20553/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 30 Sep 2024.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [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)
- [ChessGPT: Bridging Policy Learning and Language Modeling](https://mlsanity.com/paper/2306.09200/) (2023)
- [Modeling Strong and Human-Like Gameplay with KL-Regularized Search](https://mlsanity.com/paper/2112.07544/) (2021)
- [Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero](https://mlsanity.com/paper/2310.16410/) (2023)
- [The Chess Transformer: Mastering Play using Generative Language Models](https://mlsanity.com/paper/2008.04057/) (2020)
- [Learning Models of Individual Behavior in Chess](https://mlsanity.com/paper/2008.10086/) (2020)
- [Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess](https://mlsanity.com/paper/2208.01366/) (2022)
- [Diversifying AI: Towards Creative Chess with AlphaZero](https://mlsanity.com/paper/2308.09175/) (2023)
- [Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning Engines](https://mlsanity.com/paper/2212.08195/) (2022)
- [Mimetic Models: Ethical Implications of AI that Acts Like You](https://mlsanity.com/paper/2207.09394/) (2022)

## Built on by (most cited first, 25 of 25)

- [ChessQA: Evaluating Large Language Models for Chess Understanding](https://mlsanity.com/paper/2510.23948/) (2025)
- [Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess](https://mlsanity.com/paper/2507.21488/) (2025)
- [Chessformer: A Unified Architecture for Chess Modeling](https://mlsanity.com/paper/2605.19091/) (2026)
- [Learning to Plan via Supervised Contrastive Learning and Strategic Interpolation: A Chess Case Study](https://mlsanity.com/paper/2506.04892/) (2025)
- [Mixture of Masters: Sparse Chess Language Models with Player Routing](https://mlsanity.com/paper/2602.04447/) (2026)
- [Ailed: A Psyche-Driven Chess Engine with Dynamic Emotional Modulation](https://mlsanity.com/paper/2603.05352/) (2026)
- [Toward Modeling Player-Specific Chess Behaviors](https://mlsanity.com/paper/2605.11893/) (2026)
- [Matilda: Engine-Agnostic Search with Human Policy Guidance](https://mlsanity.com/paper/2606.25176/) (2026)
- [StudentSim: Training LLM-based Student Simulators](https://mlsanity.com/paper/2609.01591/) (2026)
- [A Behavior-Based Knowledge Representation Improves Prediction of Players' Moves in Chess by 25%](https://mlsanity.com/paper/2504.05425/) (2025)
- [Policies of Multiple Skill Levels for Better Strength Estimation in Games](https://mlsanity.com/paper/2505.00279/) (2025)
- [Understanding Role Switching in Human-AI Collaboration through Multimodal Behavioral Signals](https://mlsanity.com/paper/2509.20666/) (2025)
- [Abstract Concept Modelling in Conceptual Spaces: A Study on Chess Strategies](https://mlsanity.com/paper/2601.21771/) (2026)
- [Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning](https://mlsanity.com/paper/2603.13761/) (2026)
- [Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers](https://mlsanity.com/paper/2603.29761/) (2026)
- [ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction in Online Blitz Chess](https://mlsanity.com/paper/2606.04473/) (2026)
- [RePAIR: Predictive Self-Supervised Representation Learning in Chess](https://mlsanity.com/paper/2606.11860/) (2026)
- [Tandem Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2606.28166/) (2026)
- [Communicating Chess Strategies in Natural Language](https://mlsanity.com/paper/2607.11486/) (2026)
- [Engine-Equal, Human-Unequal: A Reproducible Outcome Skew in Engine-Assessed Equal Chess Positions](https://mlsanity.com/paper/2607.25655/) (2026)
- [Hallucinations on the Board: Tool-Augmented Evaluation of LLM Chess Commentary](https://mlsanity.com/paper/2608.04240/) (2026)
- [Otter: A Time-Aware, History-Conditioned Human Chess AI](https://mlsanity.com/paper/2608.05206/) (2026)
- [What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models](https://mlsanity.com/paper/2609.18286/) (2026)
- [Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer](https://mlsanity.com/paper/2609.23917/) (2026)
- [Language Models that Play Chess and Explain Their Moves](https://mlsanity.com/paper/2610.03695/) (2026)

## Abstract (arXiv)

There are an increasing number of domains in which artificial intelligence (AI) systems both surpass human ability and accurately model human behavior. This introduces the possibility of algorithmically-informed teaching in these domains through more relatable AI partners and deeper insights into human decision-making. Critical to achieving this goal, however, is coherently modeling human behavior at various skill levels. Chess is an ideal model system for conducting research into this kind of human-AI alignment, with its rich history as a pivotal testbed for AI research, mature superhuman AI systems like AlphaZero, and precise measurements of skill via chess rating systems. Previous work in modeling human decision-making in chess uses completely independent models to capture human style at different skill levels, meaning they lack coherence in their ability to adapt to the full spectrum of human improvement and are ultimately limited in their effectiveness as AI partners and teaching tools. In this work, we propose a unified modeling approach for human-AI alignment in chess that coherently captures human style across different skill levels and directly captures how people improve. Recognizing the complex, non-linear nature of human learning, we introduce a skill-aware attention mechanism to dynamically integrate players' strengths with encoded chess positions, enabling our model to be sensitive to evolving player skill. Our experimental results demonstrate that this unified framework significantly enhances the alignment between AI and human players across a diverse range of expertise levels, paving the way for deeper insights into human decision-making and AI-guided teaching tools.